Address for Correspondence *1 Professor, 2 Student, HITAM, JNTUH, Hyderabad, AP, India


 Leon Tyler
 2 years ago
 Views:
Transcription
1 Research Paper TARGET TRACKING SYSTEM USING KALMAN FILTER Dr. K Rameshbabu* 1, J.Swarnadurga 2, G.Archana 2, K.Menaka 2 Address for Correspondence *1 Professor, 2 Student, HITAM, JNTUH, Hyderabad, AP, India ABSTRACT Kalman filtering was very popular in the research field of navigation and aviation because of its magnificent accurate estimation characteristic. Since then, electrical engineers manipulate its advantages to useful purpose in target tracking systems. Consequently, today it had become a popular filtering technique for estimating and resolving redundant errors involves in tracing the target. This project proposes a system for tracking a target (ball) in video streams, returning its body and head bounding boxes. The proposed system comprises a variation of Stauffer s adaptive background algorithm with spaciotemporal adaptation of the learning parameters and a Kalman tracker in a feedback configuration. In the feed forward path, the adaptive background module provides object evidence to the Kalman tracker. In the feedback path, the Kalman tracker adapts the learning parameters of the adaptive background module. The first just does detection by background subtraction. This can be considered as the ground truth. The second feeds the detection output into a Kalman filter. The predicted position from the kalman filter (red) is compared against the actual ground truth position (green).target tracking systems has many applications, like surveillance, security, smart spaces, pervasive computing, and humanmachine interfaces to name a few. In these applications the targets are either human bodies, or vehicles. The common property of these targets is that sooner or later they exhibit some movement which is evidence that distinguishes them from the background and identifies them as foreground targets. KEYWORDS kalman filter, tracking system, navigation, stauffer s, spaciotemporal adaption. I.INTRODUCTION In 1960, R.E. Kalman published his famous paper describing a recursive solution to the discretedata linear filtering problem. Since that time, the Kalman filter has been the subject of extensive research and application, particularly in the area of autonomous or assisted navigation. The Kalman filter is a mathematical power tool that is playing an increasingly important role in computer graphics as we include sensing of the real world in our systems. I.1About Kalman Filter: Theoretically, the Kalman Filter is an estimator for what is called the linear quadratic problem, which focuses on estimating the instantaneous state of a linear dynamic system perturbed by white noise. Statistically, this estimator is optimal with respect to any quadratic function of estimation errors. Time Update equations and Measurement Update equations. The time update equations can also be thought of as predictor equations, while the measurement update equations can be thought of as corrector equations. This recursive nature is one of the very appealing features of the Kalman filter it makes practical implementations much more feasible than (for example) an implementation of a Wiener filter which is designed to operate on all of the data directly for each estimate. Instead, the Kalman filter recursively conditions the current estimate on all of the past measurements. Once again, notice how the time update equations in fig 1 project its state, x and covariance, p k estimates forward from time step k1 to step k. Initial conditions for the filter are discussed in the earlier section. I.2. Probabilistic Origins of the Filter: This section is a short section describing the justification as mentioned in the previous section for this justification is rooted in the probability of a priori estimate conditioned on all prior z k measurements (Bayes rule). For now it is suffice to point out that the Kalman filter maintains the first two moments of the state distribution, I.3 Discrete Algorithm: This section will begin with a broad overview, covering the "highlevel" operation of one form of the discrete Kalman filter. After presenting this highlevel view, I will narrow the focus to the specific equations and their use in this discrete version of the filter. Firstly, it the posteriori state estimate of reflects the mean (the first moment) of the state distribution it is normally distributed if the conditions are met. The posteriori estimate error covariance of reflects the variance of the state distribution estimates a process by using a form of feedback control loop whereby the filter estimates the process state at some time and then obtains feedback in the form of (noisy) measurements. As such, these equations for the Kalman filter fall into two groups: Fig: 1.1 Measurement updates equation I.4 Filter Parameters and Tuning: The measurement noise covariance R is usually measured before the operation of the filter when it comes to the actual implementation of Kalman filter. Generally, measuring the measurement noise covariance R is practically possible due to the fact that the necessary requirement to measure the process noise covariance Q (while operating the filter), therefore it should be possible to take some offline sample measurements in order to determine the variance of the measurement noise. As for determining of the process noise covariance Q, it will be generally more difficult. This is due to the reason that the process to be estimated is unable to be directly observed. Sometimes a relatively simple (poor) process model can produce acceptable results if one "injects" enough uncertainty into the process via the selection of Q The vision and sensor fusion techniques described in the previous chapters provide a measurement of target locations for each image
2 frame. In its raw form, this information is of limited use for camera control because it is imprecise due to measurement noise; it may include falsepositive detections of people; and it provides no association between new measurements and previous target locations. I.5 Coordinate Transformation: The coordinates measured by the camera system must be transformed into Cartesian coordinates for tracking and data association. This is important for measuring the distance between targets and measurements, and for using state estimation techniques based on Netwon's laws of motion. Each pixel location in a camera image represents a different azimuth and elevation with respect to the camera orientation. Adding these angles to the camera's pan and tilt position defines a line through the real world. I.6 Data Association: For the tracking system to perform properly, the most likely measured potential target location should be used to update the target's state estimator. This is generally known as the data association problem. The probability of the given measurement being correct is a distance function between the predicted state of the target and the measured state. One may measure the color histogram difference, H(I,M), between each new measured object and the previously detected target data using Swain and Ballard's histogram intersection technique. In the above equation Ij is the jth color histogram bin of an object in the current frame, and Mj is the jth color bin of a tracked object in the previous frame. In order to obtain a distance metric for data association that incorporates both the histogram intersection and position difference, we calculate the joint probability of these two measurements. This probability may be incorporated into association/tracking algorithms such as nearestneighbour, joint probabilistic data association, and multihypothesis track splitting. For persontracking, the color/position metric has been found to be good enough for a simple winnertakeall nearestneighbour data association scheme to suffice. If one assumes equal prior probabilities for all Xi,j, one may simplify the nearest neighbour decision process to one that seeks to maximize the value Fy(Yi,j)Fz(Zi,j). For this project, a simple nearestneighbour assignment policy was used for target measurement updates.in target tracking applications, the most popular methods for updating target assumes that the dynamics of the target can be modelled, and that noise affecting the target dynamics and sensor data is stationary and zero mean The objective of using this model to remove measurement noise with a Kalman filter/state estimator. This optimal solution incorporates the target model, state disturbances, and estimates of sensor noise variance. Figure 2.2 shows the model of the target including the state disturbance noise, W(k) and the sensor noise, V(k). I.7 Estimation Update: This Kalman filter is based on a current observer state estimator that provides an estimate, q(k), of the current system state x(k), as well as a prediction,, of the state at sample k+1. From [120], the filter equations are Kalman filter design develops the observer sensor feedback matrix G(k) such that the values of G(k) lead to an optimal estimator, where the expected values of the squared estimation errors are minimized. The determination of G(k) is recursive, and must be calculated at runtime for this application since the sensor covariance Rv(k) changes depending on target position. From the following equations are used to find G(k) Here M(k) is the covariance of the prediction errors, P(k) is the covariance of the estimation errors, and B1 = B. When a new target is detected and its tracked path is initialized, the values of q(k) and q~(k) are set equal to the current sensor measurement and M(k) is set equal to the identity matrix. If the measurement error for each dimension of movement (x, y, and z) were statistically independent, then a separate Kalman filter state estimator could be used for each dimension. For this reason, the three dimensions must be combined in the vector, increasing the size of the vectors and matrices that make up the filter. The model of human motion dynamics and in Cartesian coordinates provides the basis for filtering and smoothing the sensor data. Target position data may then be used for camera control or for intelligent room applications. However, question of which target to follow and how to look for targets still remains. Target tracking is often complicated by the measurement noise. The noise must be filtered out in order to predict the true path of a moving target. In this study of linear filtering, the Kalman filter, a recursive linear filtering model, was used to estimate tracks. There are two types of noise; the measurement noise is caused by inaccuracies in the tracking device, and state noise is caused by turbulence or human error and other environmental factors. Kalman described his new approach to linear filtering, a series of recursive equations that seek to minimize error by decreasing the covariance, increasing accuracy of the filter s prediction as each position coordinate is provided by target trackers such as radars. The Kalman filter is a variant of Bayesian filters. Bayesian filters are utilized for their excellent ability to hone in on the true track of the target as more noisy input data is supplied. However, the Kalman Filter is used in most modern target tracking systems because of its computational efficiency. First of all, the filter computes without storing past data. This simplicity allows a single personal computer to track upwards of thousands of targets at once. The recursive formulas produce more confident predictions, valuing future points less heavily as compared to the experience gained (abstractly called the Kalman Gain ) from successfully decreasing the magnitude of error in its predictions. Additionally, the filter adapts to varying measurement time intervals and is able to provide error estimates.
3 Fig: 1. 2 Model of target Dynamics I.8 The kalman Filter: The Kalman Filter is a set of equations that provides a method to estimate the state of a process. This series of equations consist of two steps: Predict and Correct. These two steps of predict and correct are used recursively. In real time, the raw data would be added to the filter during the correct step. After the current data points are received, the correct step is used to estimate the state and its variances. The projected positions of the two planes were updated. Upon reaching two consecutive alerts, the program reinitializes the filter with a new set of starting parameters and conditions. The notation of means given the state of. is the prediction of the X vector at time step k+1 given the information known at time step k. Equation projects the next predicted state given the previous state. The P matrix in Equation is the state covariance matrix representing the covariance of the position coordinates and the covariance of the velocity vectors. The Q matrix in Equation is a covariance matrix of the process noise. Equation updates the state covariance matrix based on the Kalman gain and the predicted state covariance matrix. is an identity matrix. Note that the updated state covariance matrix can never be larger than the previous state covariance matrix, which means that the estimate gets more accurate. However, simply comparing the distance between the predicted point and the measured point is insufficient due to state uncertainty, as described in our state covariance matrix. Thus, in order to find the relative distance from the two points, distance must be measured in terms of relative probability, in units of standard deviations. At each timestep, we can calculate the residual in our correct procedure, enabling our filter to effectively detect sharp maneuvers. Our implementation reinitializes the filter upon detecting two consecutive data points with residuals over four standard deviations, which provides a certainty better than one in a thousand. Fig 1.3 Path of Maneuvering Target II TARGET INTERCEPTION: Though the Kalman filter can be used to predict the path of a moving target, the applications of the filter can also be useful in calculating the path of interception. To do so requires first calculating the position and velocity of the target, projecting its path, and then computing the angle of interception for the designated course. As shown below in Figure 2.1, the interceptor successfully follows the interception path of the target, ending with a successful interception. Fig: 2.1 Paths of Interceptor and Target II.1 tracking multiple targets: The Kalman Filter can be used to track the position of multiple targets. To do this, an objectoriented approach was used: a plane class was created containing the iterate method and all the data associated with the plane. Two instances of the plane class were created upon running the program, one for each target being tracked. The main class read in the data and called the iterate method in each of the plane instances, passing the data to them as parameters. The new data points were then retrieved from both planes and printed out. II.2 Collision Avoidance Systems: one of the applications of multipletarget tracking is for collision avoidance systems. Planes flying at high speeds often cannot see each other in time to communicate and maneuver to avoid a collision. Thus, tracking the position of planes and alerting them in advance when their trajectories would lead to possible future collisions is vital in air traffic control. The projected positions of the two planes were updated. Equation was then used to check if the updated distance was less than 1 mile. If so, a message was sent to both pilots alerting them of the projected point of collision. If the new projected distance was found to be greater than the previous projected distance, meaning the planes were travelling away from each other, the loop ended, as the pilots were not in danger. Otherwise, the positions were updated once more using the above equations. II.3Kalman Filtering for Motion Prediction: Kalman filtering is a technique for temporal association and integration in tracking Based on a second order kinematic model; we can model the affine motion vector evolution as a linear system with sk as the state vector describing the affine motion vector, its first derivative and its second derivative, vk as the model noise, ok as the observation (affine motion) vector and X k as the observation noise. State matrix Aand observation matrix H come from the second order kinematic model. The result will input this Kalman filter, which will output a motion prediction result from update of the state vector. This allows the filter to integrate over time the temporal information of the tracked object]. Data association is an important factor in multiple target tracking (MTT) system. An observation is assigned to the target for maintenance of the true trajectory. Nearest neighbour (NN) is the simplest one among the different data
4 assignment techniques. We propose tracking algorithm which uses genetic algorithm for data association and it tracks multiple maneuvering and nonmaneuvering targets simultaneously in the presence of dense clutter using multiple filter bank (MFB). In real world application target may be maneuvering and nonmaneuvering and there is no apriori knowledge about its movement. This makes the model selection for tracking the target difficult. Along with tracking an observation is to be assigned to track for state update and predict where data assignment plays a major role for maintaining true trajectory in the presence of dense clutter. One of the important characterstic of kalman fitler is it suits for only linear dynamical systems that is the reason it is called a linear quadratic estimation algorithm(lde). If the system is nonlinear is the question that arises in terms of the usage, since usage of nonlinear systems are responsible for noise and many other disturbances an extension for kalman filter is obtained called as extended kalman filter which suits for even for nonlinear dynamical systems. The use of two channels (dark and bright images) for mean shift tracking as well as the experimental determination of the optimal window size and quantization level for mean shift tracking further enhance the performance of our technique. By experimental results, we have demonstrated that the proposed method dramatically improves the robustness and accuracy of eye tracking. II.4 The kalman Model:The Kalman Filter is modeled by utilizing a linear algebra approach using matrices Equation shows Xk+1 that is a matrix representing the updated state and Xk is a vector representing the current state, which contains position and velocity vectors. Matrix is a state transformation matrix that relates the state of one time step to the next. This recursive process includes the use of t to update the new location and velocity of the target. The variable k represents the time step. In our case, Φ is represented by this 4X4 matrix in Equation The qk vector is the process noise. In other words, it is the noise due to uncertainty in the transition. can be described as the error caused by the inaccuracy of our instruments. II.5 Types of sensors used: Locations and orientations of the various sensor types with respect to the system to be estimated. Allowable noise characteristics of the sensors. Prefiltering methods for smoothing sensor noise. Data sampling rates for the various sensor types and the level of model simplification for reducing implementation requirements. A system designer is able to assign an error budget to subsystems of an estimation system, which this is allowed by the analytical capability of the Kalman filter formalism. Moreover, it can trade off the budget allocations to optimize cost or other measures of performance while achieving a required level of estimation accuracy. Target tracking systems has many applications, like surveillance, security, smart spaces, pervasive computing, and humanmachine interfaces to name a few. In these applications the targets are either human bodies, or vehicles. The common property of these targets is that sooner or later they exhibit some movement which is evidence that distinguishes them from the background and identifies them as foreground targets. Fig:2.2 Liner filter characteristics A linear Kalman filter is employed to predict the estimated affine motion parameters based on a second order kinematic model as shown in fig 2.2. A great variety of visual tracking algorithms have been proposed, they can be classified roughly into two categories. The first is the featurebased method A typical instance in this category estimates the 3D pose of a target object to fit into the image features such as contours given a 3D geometric model of the object. The second is the regionbased method. Compared to the featurebased methods the regionbased methods are more robust, insensitive to small partial occlusions. The region based methods can be subdivided into two groups: the viewbased method and the parametric method. The view based method finds the best match of a region in a search area with a reference template. The parametric method assumes a parametric model of changes in the target image and computes optimal fitting of the model to pixel data in a region. III RESULTS COMPARISION: We have studied about kalman filter and results also compared with weiner filter as shown in table. The matrix Yk in Equation is a representation of the current measurement in a 2X1matrix. The H matrix is a transformation matrix Xk s 4X1 into 2X1 To do this, the H matrix must be 2x4. The rk vector is a 2X1 measurement noise vector. Measurement noise
5 Fig 3.1 position tracking face while walking Fig 3.2 tracking a pattern walking IV ADVANTAGES OF KALMAN FILTER Below are some advantages of the Kalman filter, comparing with another famous filter known as the Wiener Filter, which this filter was popular before the introduction of Kalman filter. The information below is obtained from. I. The Kalman filter algorithm is implementable on a digital computer, which this was replaced by analog circuitry for estimation and control when Kalman filter was first introduced. This implementation may be slower compared to analog filters of Wiener; however it is capable of much greater accuracy. II. Stationary properties of the Kalman filter are not required for the deterministic dynamics or random processes. Many applications of importance include non stationary stochastic III. processes. The Kalman filter is compatible with statespace formulation of optimal controllers for dynamic systems. It proves useful towards the 2 properties of estimation and control for these systems. a) The Kalman filter requires less additional mathematical preparation to learn for the modern control engineering student, compared to the Wiener filter. b) Necessary information for mathematically sound, statisticallybased decision methods for detecting and rejecting anomalous measurements are provided through the use of Kalman filter. IV.1 Applications of Kalman filter: Although, the applications of Kalman filtering encompass many fields, its use as a tool is mainly for two purposes: estimation and performance analysis of estimators. Since the Kalman filter uses a complete description of the probability of its estimation errors in determining the optimal filtering gains, this probability distribution may be used in assessing its performance as a function of the design parameters of the following estimation systems: V CONCLUSION: Our project titled Target Tracking System Using Kalman Filter is performed and the results are computed. Kalman filter provides 95%efficeint output even in the noisy environment.in this thesis we have studied several estimation and data association methods for target tracking. A general method of increasing the sampling frequency of a vision sensor by using a predictive Kalman filter and partial window imaging has been introduced and has been demonstrated to work effectively. The method reduces the acquisition and processing time of an image. The acquisition time is reduced by a larger percentage than the processing time and so the image processing is the bottle neck in reducing the sampling frequency. Two processing methods were implemented. This system was not as robust but it does provide a further increase in sampling frequency. VI FUTURE SCOPE: One of the important characteristic of kalman filter is it suits for only linear dynamical systems that is the reason it is called a linear quadratic estimation algorithm (LDE).If the system is nonlinear is the question that arises in terms of the usage, since usage of nonlinear systems are responsible for noise and many other disturbances an extension for kalman filter is obtained called as extended kalman filter which suits for even for nonlinear dynamical systems. REFERENCES: 1. Havran, V.: Heuristic Ray Shooting Algorithms. PhD thesis, Faculty of Electrical Engineering, Czech Technical University in Prague (2001) 2. MacDonald, J.D., Booth, K.S.: Heuristics for Ray Tracing Using Space Subdivision. In: Graphics Interface Proceedings 1989, Wellesley, MA, USA, June 1989, pp A.K. Peters, Ltd. (1989) 3. Stoll, G.: Part I: Introduction to Realtime Ray Tracing. In: SIGGRAPH 2005 Course on Interactive Ray Tracing (2005) 4. Zara, J.: Speeding Up Ray Tracing  SW and HW Approaches. In: Proceedings of 11th Spring Conference on Computer Graphics (SSCG 1995), Bratislava, Slovakia, pp (May 1995) 5. Hunt, W., Stoll, G., Mark, W.: Fast kdtree Construction With An Adaptive ErrorBounded Heuristic. In: Proceedings of the 2006 IEEE Symposium on Interactive RayTracing, pp (September 2006) 6. Wald, I., Havran, V.: On Building Fast kdtrees For Ray Tracing, and on Doing That In O(N log N). In: Proceedings of the 2006 IEEE Symposium on Interactive Ray Tracing, pp (September 2006) 7. Woop, S., Marmitt, G., Slusallek, P.: Bkd trees for Hardware Accelerated Ray Tracing of Dynamic Scenes. In: Proceedings of Graphics Hardware (2006) 8. Foley, T., Sugerman, J.: kdtree Acceleration Structures For A GPU Raytracer. In: Proceedings of the ACM SIGGRAPH/EUROGRAPHICS conference on Graphics hardware, pp (2005) 9. Hussain, S., Grahn, H.: Fast kdtree Construction for 3D Rendering Algorithms like Ray Tracing. In: Bebis, G., Boyle, R., Parvin, B., Koracin, D., Paragios, N., Tanveer, S.M., Ju, T., Liu, Z., Coquillart, S., CruzNeira, C., Müller, T., Malzbender, T. (eds.) ISVC 2007, Part II. LNCS, vol. 4842, pp Springer, Heidelberg (2007) 10. Wald, I.: Realtime Ray Tracing and Interactive Global Illumination. PhD thesis, ComputerGraphics Group, Saarland University, Saarbrucken, Germany (2004) 11. Havran, V.: Heuristic Ray Shooting Algorithm. PhD thesis, Czech Technical University, Prague (2001). 12. Chang, A.Y.: Theoretical and Experimental Aspects of Ray Shooting. PhD Thesis, Polytechnic University, New York (May 2004). 13. Havran, V., Herzog, R., Seidel, H.P.: On Fast Construction of Spatial Hierarchies for Ray Tracing. In: Proceedings of the 2006 IEEE Symposium on Interactive Ray Tracing, pp (September 2006) 14. Benthin, C.: Realtime Raytracing on Current CPU Architectures. PhD thesis, Saarland University (2006) 15. Popov, S., Gunther, J., Seidel, H.P., Slusallek, P.: Experiences with Streaming Construction of SAH KD Trees. In: Proceedings of IEEE Symposium on Interactive Ray Tracing, pp (September 2006) 16. Cleary, J.G., Wyvill, G.: Analysis Of An Algorithm For Fast Ray Tracing Using Uniform Space Subdivision. The Visual Computer (4), (1988).
IMPROVED VIRTUAL MOUSE POINTER USING KALMAN FILTER BASED GESTURE TRACKING TECHNIQUE
39 IMPROVED VIRTUAL MOUSE POINTER USING KALMAN FILTER BASED GESTURE TRACKING TECHNIQUE D.R.A.M. Dissanayake, U.K.R.M.H. Rajapaksha 2 and M.B Dissanayake 3 Department of Electrical and Electronic Engineering,
More informationA Reliability Point and Kalman Filterbased Vehicle Tracking Technique
A Reliability Point and Kalman Filterbased Vehicle Tracing Technique Soo Siang Teoh and Thomas Bräunl Abstract This paper introduces a technique for tracing the movement of vehicles in consecutive video
More informationAn Introduction to the Kalman Filter
An Introduction to the Kalman Filter Greg Welch 1 and Gary Bishop 2 TR 95041 Department of Computer Science University of North Carolina at Chapel Hill Chapel Hill, NC 275993175 Updated: Monday, July 24,
More informationComputer Graphics Global Illumination (2): MonteCarlo Ray Tracing and Photon Mapping. Lecture 15 Taku Komura
Computer Graphics Global Illumination (2): MonteCarlo Ray Tracing and Photon Mapping Lecture 15 Taku Komura In the previous lectures We did ray tracing and radiosity Ray tracing is good to render specular
More informationTracking of Small Unmanned Aerial Vehicles
Tracking of Small Unmanned Aerial Vehicles Steven Krukowski Adrien Perkins Aeronautics and Astronautics Stanford University Stanford, CA 94305 Email: spk170@stanford.edu Aeronautics and Astronautics Stanford
More informationVision Based Traffic Light Triggering for Motorbikes
Vision Based Traffic Light Triggering for Motorbikes Tommy Chheng Department of Computer Science and Engineering University of California, San Diego tcchheng@ucsd.edu Abstract Current traffic light triggering
More informationPOTENTIAL OF STATEFEEDBACK CONTROL FOR MACHINE TOOLS DRIVES
POTENTIAL OF STATEFEEDBACK CONTROL FOR MACHINE TOOLS DRIVES L. Novotny 1, P. Strakos 1, J. Vesely 1, A. Dietmair 2 1 Research Center of Manufacturing Technology, CTU in Prague, Czech Republic 2 SW, Universität
More informationA REVIEW ON KALMAN FILTER FOR GPS TRACKING
A REVIEW ON KALMAN FILTER FOR GPS TRACKING Ms. SONAL(Student, M.Tech ), Dr. AJIT SINGH (Professor in CSE & IT) Computer Science & Engg. (Network Security) BPS Mahila Vishwavidyalaya Khanpur Kalan, Haryana
More informationDeterministic Samplingbased Switching Kalman Filtering for Vehicle Tracking
Proceedings of the IEEE ITSC 2006 2006 IEEE Intelligent Transportation Systems Conference Toronto, Canada, September 1720, 2006 WA4.1 Deterministic Samplingbased Switching Kalman Filtering for Vehicle
More informationVision based Vehicle Tracking using a high angle camera
Vision based Vehicle Tracking using a high angle camera Raúl Ignacio Ramos García Dule Shu gramos@clemson.edu dshu@clemson.edu Abstract A vehicle tracking and grouping algorithm is presented in this work
More informationTracking and Recognition in Sports Videos
Tracking and Recognition in Sports Videos Mustafa Teke a, Masoud Sattari b a Graduate School of Informatics, Middle East Technical University, Ankara, Turkey mustafa.teke@gmail.com b Department of Computer
More informationVEHICLE TRACKING USING ACOUSTIC AND VIDEO SENSORS
VEHICLE TRACKING USING ACOUSTIC AND VIDEO SENSORS Aswin C Sankaranayanan, Qinfen Zheng, Rama Chellappa University of Maryland College Park, MD  277 {aswch, qinfen, rama}@cfar.umd.edu Volkan Cevher, James
More informationEnhancing the SNR of the Fiber Optic Rotation Sensor using the LMS Algorithm
1 Enhancing the SNR of the Fiber Optic Rotation Sensor using the LMS Algorithm Hani Mehrpouyan, Student Member, IEEE, Department of Electrical and Computer Engineering Queen s University, Kingston, Ontario,
More informationObject Tracking System Using Approximate Median Filter, Kalman Filter and Dynamic Template Matching
I.J. Intelligent Systems and Applications, 2014, 05, 8389 Published Online April 2014 in MECS (http://www.mecspress.org/) DOI: 10.5815/ijisa.2014.05.09 Object Tracking System Using Approximate Median
More informationMeanShift Tracking with Random Sampling
1 MeanShift Tracking with Random Sampling Alex Po Leung, Shaogang Gong Department of Computer Science Queen Mary, University of London, London, E1 4NS Abstract In this work, boosting the efficiency of
More informationA PHOTOGRAMMETRIC APPRAOCH FOR AUTOMATIC TRAFFIC ASSESSMENT USING CONVENTIONAL CCTV CAMERA
A PHOTOGRAMMETRIC APPRAOCH FOR AUTOMATIC TRAFFIC ASSESSMENT USING CONVENTIONAL CCTV CAMERA N. Zarrinpanjeh a, F. Dadrassjavan b, H. Fattahi c * a Islamic Azad University of Qazvin  nzarrin@qiau.ac.ir
More informationObject tracking & Motion detection in video sequences
Introduction Object tracking & Motion detection in video sequences Recomended link: http://cmp.felk.cvut.cz/~hlavac/teachpresen/17compvision3d/41imagemotion.pdf 1 2 DYNAMIC SCENE ANALYSIS The input to
More informationAlgorithm (DCABES 2009)
People Tracking via a Modified CAMSHIFT Algorithm (DCABES 2009) Fahad Fazal Elahi Guraya, PierreYves Bayle and Faouzi Alaya Cheikh Department of Computer Science and Media Technology, Gjovik University
More informationSpeed Performance Improvement of Vehicle Blob Tracking System
Speed Performance Improvement of Vehicle Blob Tracking System Sung Chun Lee and Ram Nevatia University of Southern California, Los Angeles, CA 90089, USA sungchun@usc.edu, nevatia@usc.edu Abstract. A speed
More informationVisionBased Pedestrian Detection for Driving Assistance
VisionBased Pedestrian Detection for Driving Assistance Literature Survey Multidimensional DSP Project, Spring 2005 Marco Perez Abstract This survey focuses on some of the most important and recent algorithms
More informationThe Scientific Data Mining Process
Chapter 4 The Scientific Data Mining Process When I use a word, Humpty Dumpty said, in rather a scornful tone, it means just what I choose it to mean neither more nor less. Lewis Carroll [87, p. 214] In
More informationKalman Filter Applied to a Active Queue Management Problem
IOSR Journal of Electrical and Electronics Engineering (IOSRJEEE) eissn: 22781676,pISSN: 23203331, Volume 9, Issue 4 Ver. III (Jul Aug. 2014), PP 2327 Jyoti Pandey 1 and Prof. Aashih Hiradhar 2 Department
More informationTracking in flussi video 3D. Ing. Samuele Salti
Seminari XXIII ciclo Tracking in flussi video 3D Ing. Tutors: Prof. Tullio Salmon Cinotti Prof. Luigi Di Stefano The Tracking problem Detection Object model, Track initiation, Track termination, Tracking
More informationSENSOR FUSION FOR LINEAR MOTORS, AN APPROACH FOR LOWCOST MEASUREMENTS
Proc. of Mechatronics 22, University of Twente, 2426 June 22 SENSOR FUSION FOR LINEAR MOTORS, AN APPROACH FOR LOWCOST MEASUREMENTS Bas J. de Kruif, Bastiaan van Wermeskerken, Theo J. A. de Vries and
More informationA MultiModel Filter for Mobile Terminal Location Tracking
A MultiModel Filter for Mobile Terminal Location Tracking M. McGuire, K.N. Plataniotis The Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, 1 King s College
More informationTracking Groups of Pedestrians in Video Sequences
Tracking Groups of Pedestrians in Video Sequences Jorge S. Marques Pedro M. Jorge Arnaldo J. Abrantes J. M. Lemos IST / ISR ISEL / IST ISEL INESCID / IST Lisbon, Portugal Lisbon, Portugal Lisbon, Portugal
More informationAdaptive DemandForecasting Approach based on Principal Components Timeseries an application of datamining technique to detection of market movement
Adaptive DemandForecasting Approach based on Principal Components Timeseries an application of datamining technique to detection of market movement Toshio Sugihara Abstract In this study, an adaptive
More informationBildverarbeitung und Mustererkennung Image Processing and Pattern Recognition
Bildverarbeitung und Mustererkennung Image Processing and Pattern Recognition 1. Image PreProcessing  Pixel Brightness Transformation  Geometric Transformation  Image Denoising 1 1. Image PreProcessing
More informationCurrent Standard: Mathematical Concepts and Applications Shape, Space, and Measurement Primary
Shape, Space, and Measurement Primary A student shall apply concepts of shape, space, and measurement to solve problems involving two and threedimensional shapes by demonstrating an understanding of:
More informationPractical Tour of Visual tracking. David Fleet and Allan Jepson January, 2006
Practical Tour of Visual tracking David Fleet and Allan Jepson January, 2006 Designing a Visual Tracker: What is the state? pose and motion (position, velocity, acceleration, ) shape (size, deformation,
More informationDegree Reduction of Interval SB Curves
International Journal of Video&Image Processing and Network Security IJVIPNSIJENS Vol:13 No:04 1 Degree Reduction of Interval SB Curves O. Ismail, Senior Member, IEEE Abstract Ball basis was introduced
More informationINTRUSION PREVENTION AND EXPERT SYSTEMS
INTRUSION PREVENTION AND EXPERT SYSTEMS By Avi Chesla avic@vsecure.com Introduction Over the past few years, the market has developed new expectations from the security industry, especially from the intrusion
More informationCS231M Project Report  Automated RealTime Face Tracking and Blending
CS231M Project Report  Automated RealTime Face Tracking and Blending Steven Lee, slee2010@stanford.edu June 6, 2015 1 Introduction Summary statement: The goal of this project is to create an Android
More informationDYNAMIC RANGE IMPROVEMENT THROUGH MULTIPLE EXPOSURES. Mark A. Robertson, Sean Borman, and Robert L. Stevenson
c 1999 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or
More informationUnderstanding and Applying Kalman Filtering
Understanding and Applying Kalman Filtering Lindsay Kleeman Department of Electrical and Computer Systems Engineering Monash University, Clayton 1 Introduction Objectives: 1. Provide a basic understanding
More informationForce/position control of a robotic system for transcranial magnetic stimulation
Force/position control of a robotic system for transcranial magnetic stimulation W.N. Wan Zakaria School of Mechanical and System Engineering Newcastle University Abstract To develop a force control scheme
More informationIn mathematics, there are four attainment targets: using and applying mathematics; number and algebra; shape, space and measures, and handling data.
MATHEMATICS: THE LEVEL DESCRIPTIONS In mathematics, there are four attainment targets: using and applying mathematics; number and algebra; shape, space and measures, and handling data. Attainment target
More informationAn Introduction to Mobile Robotics
An Introduction to Mobile Robotics Who am I. Steve Goldberg 15 years programming robots for NASA/JPL Worked on MSL, MER, BigDog and Crusher Expert in stereo vision and autonomous navigation Currently Telecommuting
More informationFalse alarm in outdoor environments
Accepted 1.0 Savantic letter 1(6) False alarm in outdoor environments Accepted 1.0 Savantic letter 2(6) Table of contents Revision history 3 References 3 1 Introduction 4 2 Preprocessing 4 3 Detection,
More informationC4 Computer Vision. 4 Lectures Michaelmas Term Tutorial Sheet Prof A. Zisserman. fundamental matrix, recovering egomotion, applications.
C4 Computer Vision 4 Lectures Michaelmas Term 2004 1 Tutorial Sheet Prof A. Zisserman Overview Lecture 1: Stereo Reconstruction I: epipolar geometry, fundamental matrix. Lecture 2: Stereo Reconstruction
More informationProfessor, D.Sc. (Tech.) Eugene Kovshov MSTU «STANKIN», Moscow, Russia
Professor, D.Sc. (Tech.) Eugene Kovshov MSTU «STANKIN», Moscow, Russia As of today, the issue of Big Data processing is still of high importance. Data flow is increasingly growing. Processing methods
More informationJiří Matas. Hough Transform
Hough Transform Jiří Matas Center for Machine Perception Department of Cybernetics, Faculty of Electrical Engineering Czech Technical University, Prague Many slides thanks to Kristen Grauman and Bastian
More informationFace Recognition in Lowresolution Images by Using Local Zernike Moments
Proceedings of the International Conference on Machine Vision and Machine Learning Prague, Czech Republic, August1415, 014 Paper No. 15 Face Recognition in Lowresolution Images by Using Local Zernie
More informationBehavior Analysis in Crowded Environments. XiaogangWang Department of Electronic Engineering The Chinese University of Hong Kong June 25, 2011
Behavior Analysis in Crowded Environments XiaogangWang Department of Electronic Engineering The Chinese University of Hong Kong June 25, 2011 Behavior Analysis in Sparse Scenes ZelnikManor & Irani CVPR
More informationDetailed simulation of mass spectra for quadrupole mass spectrometer systems
Detailed simulation of mass spectra for quadrupole mass spectrometer systems J. R. Gibson, a) S. Taylor, and J. H. Leck Department of Electrical Engineering and Electronics, The University of Liverpool,
More informationVEHICLE LOCALISATION AND CLASSIFICATION IN URBAN CCTV STREAMS
VEHICLE LOCALISATION AND CLASSIFICATION IN URBAN CCTV STREAMS Norbert Buch 1, Mark Cracknell 2, James Orwell 1 and Sergio A. Velastin 1 1. Kingston University, Penrhyn Road, Kingston upon Thames, KT1 2EE,
More informationModelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches
Modelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches PhD Thesis by Payam Birjandi Director: Prof. Mihai Datcu Problematic
More informationAn Introduction to Applied Mathematics: An Iterative Process
An Introduction to Applied Mathematics: An Iterative Process Applied mathematics seeks to make predictions about some topic such as weather prediction, future value of an investment, the speed of a falling
More informationBrightness and geometric transformations
Brightness and geometric transformations Václav Hlaváč Czech Technical University in Prague Center for Machine Perception (bridging groups of the) Czech Institute of Informatics, Robotics and Cybernetics
More informationMapping an Application to a Control Architecture: Specification of the Problem
Mapping an Application to a Control Architecture: Specification of the Problem Mieczyslaw M. Kokar 1, Kevin M. Passino 2, Kenneth Baclawski 1, and Jeffrey E. Smith 3 1 Northeastern University, Boston,
More informationInteractive Visualization of Magnetic Fields
JOURNAL OF APPLIED COMPUTER SCIENCE Vol. 21 No. 1 (2013), pp. 107117 Interactive Visualization of Magnetic Fields Piotr Napieralski 1, Krzysztof Guzek 1 1 Institute of Information Technology, Lodz University
More informationDiscrete FrobeniusPerron Tracking
Discrete FrobeniusPerron Tracing Barend J. van Wy and Michaël A. van Wy French SouthAfrican Technical Institute in Electronics at the Tshwane University of Technology Staatsartillerie Road, Pretoria,
More informationEFFICIENT VEHICLE TRACKING AND CLASSIFICATION FOR AN AUTOMATED TRAFFIC SURVEILLANCE SYSTEM
EFFICIENT VEHICLE TRACKING AND CLASSIFICATION FOR AN AUTOMATED TRAFFIC SURVEILLANCE SYSTEM Amol Ambardekar, Mircea Nicolescu, and George Bebis Department of Computer Science and Engineering University
More informationAssessment. Presenter: Yupu Zhang, Guoliang Jin, Tuo Wang Computer Vision 2008 Fall
Automatic Photo Quality Assessment Presenter: Yupu Zhang, Guoliang Jin, Tuo Wang Computer Vision 2008 Fall Estimating i the photorealism of images: Distinguishing i i paintings from photographs h Florin
More informationINSTRUCTOR WORKBOOK Quanser Robotics Package for Education for MATLAB /Simulink Users
INSTRUCTOR WORKBOOK for MATLAB /Simulink Users Developed by: Amir Haddadi, Ph.D., Quanser Peter Martin, M.A.SC., Quanser Quanser educational solutions are powered by: CAPTIVATE. MOTIVATE. GRADUATE. PREFACE
More informationRobot TaskLevel Programming Language and Simulation
Robot TaskLevel Programming Language and Simulation M. Samaka Abstract This paper presents the development of a software application for Offline robot task programming and simulation. Such application
More informationSynthetic Aperture Radar: Principles and Applications of AI in Automatic Target Recognition
Synthetic Aperture Radar: Principles and Applications of AI in Automatic Target Recognition Paulo Marques 1 Instituto Superior de Engenharia de Lisboa / Instituto de Telecomunicações R. Conselheiro Emídio
More informationLinear Threshold Units
Linear Threshold Units w x hx (... w n x n w We assume that each feature x j and each weight w j is a real number (we will relax this later) We will study three different algorithms for learning linear
More informationVehicle Tracking in Occlusion and Clutter
Vehicle Tracking in Occlusion and Clutter by KURTIS NORMAN MCBRIDE A thesis presented to the University of Waterloo in fulfilment of the thesis requirement for the degree of Master of Applied Science in
More informationRobust and accurate global vision system for real time tracking of multiple mobile robots
Robust and accurate global vision system for real time tracking of multiple mobile robots Mišel Brezak Ivan Petrović Edouard Ivanjko Department of Control and Computer Engineering, Faculty of Electrical
More informationAccurate and robust image superresolution by neural processing of local image representations
Accurate and robust image superresolution by neural processing of local image representations Carlos Miravet 1,2 and Francisco B. Rodríguez 1 1 Grupo de Neurocomputación Biológica (GNB), Escuela Politécnica
More informationSystem Identification for Acoustic Comms.:
System Identification for Acoustic Comms.: New Insights and Approaches for Tracking Sparse and Rapidly Fluctuating Channels Weichang Li and James Preisig Woods Hole Oceanographic Institution The demodulation
More informationNavigation of Mobile Robots Using Potential Fields and Computational Intelligence Means
Acta Polytechnica Hungarica Vol. 4, No. 1, 007 Navigation of Mobile Robots Using Potential Fields and Computational Intelligence Means Ján Vaščák Centre for Intelligent Technologies, Department of Cybernetics
More informationWireless Networking Trends Architectures, Protocols & optimizations for future networking scenarios
Wireless Networking Trends Architectures, Protocols & optimizations for future networking scenarios H. Fathi, J. Figueiras, F. Fitzek, T. Madsen, R. Olsen, P. Popovski, HP Schwefel Session 1 Network Evolution
More informationClustering & Visualization
Chapter 5 Clustering & Visualization Clustering in highdimensional databases is an important problem and there are a number of different clustering paradigms which are applicable to highdimensional data.
More informationEL5223. Basic Concepts of Robot Sensors, Actuators, Localization, Navigation, and1 Mappin / 12
Basic Concepts of Robot Sensors, Actuators, Localization, Navigation, and Mapping Basic Concepts of Robot Sensors, Actuators, Localization, Navigation, and1 Mappin / 12 Sensors and Actuators Robotic systems
More informationTraffic Flow Monitoring in Crowded Cities
Traffic Flow Monitoring in Crowded Cities John A. Quinn and Rose Nakibuule Faculty of Computing & I.T. Makerere University P.O. Box 7062, Kampala, Uganda {jquinn,rnakibuule}@cit.mak.ac.ug Abstract Traffic
More informationDesign of Multicamera Based Acts Monitoring System for Effective Remote Monitoring Control
보안공학연구논문지 (Journal of Security Engineering), 제 8권 제 3호 2011년 6월 Design of Multicamera Based Acts Monitoring System for Effective Remote Monitoring Control JiHoon Lim 1), Seoksoo Kim 2) Abstract With
More informationStatic Environment Recognition Using Omnicamera from a Moving Vehicle
Static Environment Recognition Using Omnicamera from a Moving Vehicle Teruko Yata, Chuck Thorpe Frank Dellaert The Robotics Institute Carnegie Mellon University Pittsburgh, PA 15213 USA College of Computing
More informationEssential Mathematics for Computer Graphics fast
John Vince Essential Mathematics for Computer Graphics fast Springer Contents 1. MATHEMATICS 1 Is mathematics difficult? 3 Who should read this book? 4 Aims and objectives of this book 4 Assumptions made
More informationHardware design for ray tracing
Hardware design for ray tracing Jaesung Yoon Introduction Realtime ray tracing performance has recently been achieved even on single CPU. [Wald et al. 2001, 2002, 2004] However, higher resolutions, complex
More informationHSI BASED COLOUR IMAGE EQUALIZATION USING ITERATIVE n th ROOT AND n th POWER
HSI BASED COLOUR IMAGE EQUALIZATION USING ITERATIVE n th ROOT AND n th POWER Gholamreza Anbarjafari icv Group, IMS Lab, Institute of Technology, University of Tartu, Tartu 50411, Estonia sjafari@ut.ee
More informationPHOTOGRAMMETRIC TECHNIQUES FOR MEASUREMENTS IN WOODWORKING INDUSTRY
PHOTOGRAMMETRIC TECHNIQUES FOR MEASUREMENTS IN WOODWORKING INDUSTRY V. Knyaz a, *, Yu. Visilter, S. Zheltov a State Research Institute for Aviation System (GosNIIAS), 7, Victorenko str., Moscow, Russia
More informationIntroduction to Computer Graphics
Introduction to Computer Graphics Torsten Möller TASC 8021 7787822215 torsten@sfu.ca www.cs.sfu.ca/~torsten Today What is computer graphics? Contents of this course Syllabus Overview of course topics
More informationA Learning Based Method for SuperResolution of Low Resolution Images
A Learning Based Method for SuperResolution of Low Resolution Images Emre Ugur June 1, 2004 emre.ugur@ceng.metu.edu.tr Abstract The main objective of this project is the study of a learning based method
More informationJava Modules for Time Series Analysis
Java Modules for Time Series Analysis Agenda Clustering Nonnormal distributions Multifactor modeling Implied ratings Time series prediction 1. Clustering + Cluster 1 Synthetic Clustering + Time series
More informationCOMPUTER SIMULATION OF REAL TIME IDENTIFICATION FOR INDUCTION MOTOR DRIVES
Proceedings of the International Conference on Theory and Applications of Mathematics and Informatics  ICTAMI 2004, Thessaloniki, Greece COMPUTER SIMULATION OF REAL TIME IDENTIFICATION FOR INDUCTION MOTOR
More informationRealTime Tracking of Pedestrians and Vehicles
RealTime Tracking of Pedestrians and Vehicles N.T. Siebel and S.J. Maybank. Computational Vision Group Department of Computer Science The University of Reading Reading RG6 6AY, England Abstract We present
More informationVirtual Mouse Implementation using Color Pointer Detection
International Journal of Research Studies in Science, Engineering and Technology Volume 1, Issue 5, August 2014, PP 2332 ISSN 23494751 (Print) & ISSN 2349476X (Online) Virtual Mouse Implementation using
More informationCCTV  Video Analytics for Traffic Management
CCTV  Video Analytics for Traffic Management Index Purpose Description Relevance for Large Scale Events Technologies Impacts Integration potential Implementation Best Cases and Examples 1 of 12 Purpose
More informationAutomatic parameter regulation for a tracking system with an autocritical function
Automatic parameter regulation for a tracking system with an autocritical function Daniela Hall INRIA RhôneAlpes, St. Ismier, France Email: Daniela.Hall@inrialpes.fr Abstract In this article we propose
More informationDarshan VENKATRAYAPPA Philippe MONTESINOS Daniel DEPP 8/1/2013 1
Darshan VENKATRAYAPPA Philippe MONTESINOS Daniel DEPP 8/1/2013 1 OUTLINE Introduction. Problem Statement. Literature Review. Gesture Modeling. Gesture Analysis Gesture Recognition. People Detection in
More informationLeast Squares Estimation
Least Squares Estimation SARA A VAN DE GEER Volume 2, pp 1041 1045 in Encyclopedia of Statistics in Behavioral Science ISBN13: 9780470860809 ISBN10: 0470860804 Editors Brian S Everitt & David
More informationThe Kalman Filter and its Application in Numerical Weather Prediction
Overview Kalman filter The and its Application in Numerical Weather Prediction Ensemble Kalman filter Statistical approach to prevent filter divergence Thomas Bengtsson, Jeff Anderson, Doug Nychka http://www.cgd.ucar.edu/
More informationDetection and Restoration of Vertical Nonlinear Scratches in Digitized Film Sequences
Detection and Restoration of Vertical Nonlinear Scratches in Digitized Film Sequences Byoungmoon You 1, Kyungtack Jung 2, Sangkook Kim 2, and Doosung Hwang 3 1 L&Y Vision Technologies, Inc., Daejeon,
More informationImage Compression through DCT and Huffman Coding Technique
International Journal of Current Engineering and Technology EISSN 2277 4106, PISSN 2347 5161 2015 INPRESSCO, All Rights Reserved Available at http://inpressco.com/category/ijcet Research Article Rahul
More informationAutomatic Labeling of Lane Markings for Autonomous Vehicles
Automatic Labeling of Lane Markings for Autonomous Vehicles Jeffrey Kiske Stanford University 450 Serra Mall, Stanford, CA 94305 jkiske@stanford.edu 1. Introduction As autonomous vehicles become more popular,
More informationA Movement Tracking Management Model with Kalman Filtering Global Optimization Techniques and Mahalanobis Distance
Loutraki, 21 26 October 2005 A Movement Tracking Management Model with ing Global Optimization Techniques and Raquel Ramos Pinho, João Manuel R. S. Tavares, Miguel Velhote Correia Laboratório de Óptica
More informationSolving Simultaneous Equations and Matrices
Solving Simultaneous Equations and Matrices The following represents a systematic investigation for the steps used to solve two simultaneous linear equations in two unknowns. The motivation for considering
More informationFace detection is a process of localizing and extracting the face region from the
Chapter 4 FACE NORMALIZATION 4.1 INTRODUCTION Face detection is a process of localizing and extracting the face region from the background. The detected face varies in rotation, brightness, size, etc.
More informationBuilding an Advanced Invariant RealTime Human Tracking System
UDC 004.41 Building an Advanced Invariant RealTime Human Tracking System Fayez Idris 1, Mazen Abu_Zaher 2, Rashad J. Rasras 3, and Ibrahiem M. M. El Emary 4 1 School of Informatics and Computing, GermanJordanian
More informationSimultaneous Gamma Correction and Registration in the Frequency Domain
Simultaneous Gamma Correction and Registration in the Frequency Domain Alexander Wong a28wong@uwaterloo.ca William Bishop wdbishop@uwaterloo.ca Department of Electrical and Computer Engineering University
More informationHow does the Kinect work? John MacCormick
How does the Kinect work? John MacCormick Xbox demo Laptop demo The Kinect uses structured light and machine learning Inferring body position is a twostage process: first compute a depth map (using structured
More informationFLEXSYS Motionbased Traffic Analysis and Incident Detection
FLEXSYS Motionbased Traffic Analysis and Incident Detection Authors: Lixin Yang and Hichem Sahli, IBBT/VUBETRO Contents.1 Introduction......................................... 1.2 Traffic flow modelling
More informationSensors in robotic arc welding to support small series production
Sensors in robotic arc welding to support small series production Gunnar Bolmsjö Magnus Olsson Abstract Sensors to guide robots during arc welding have been around for more than twenty years. However,
More informationA Prototype For EyeGaze Corrected
A Prototype For EyeGaze Corrected Video Chat on Graphics Hardware Maarten Dumont, Steven Maesen, Sammy Rogmans and Philippe Bekaert Introduction Traditional webcam video chat: No eye contact. No extensive
More informationParallel Computing for Option Pricing Based on the Backward Stochastic Differential Equation
Parallel Computing for Option Pricing Based on the Backward Stochastic Differential Equation Ying Peng, Bin Gong, Hui Liu, and Yanxin Zhang School of Computer Science and Technology, Shandong University,
More informationREAL TIME TRAFFIC LIGHT CONTROL USING IMAGE PROCESSING
REAL TIME TRAFFIC LIGHT CONTROL USING IMAGE PROCESSING Ms.PALLAVI CHOUDEKAR Ajay Kumar Garg Engineering College, Department of electrical and electronics Ms.SAYANTI BANERJEE Ajay Kumar Garg Engineering
More informationEfficient visual search of local features. Cordelia Schmid
Efficient visual search of local features Cordelia Schmid Visual search change in viewing angle Matches 22 correct matches Image search system for large datasets Large image dataset (one million images
More informationOnline Model Predictive Control of a Robotic System by Combining Simulation and Optimization
Mohammad Rokonuzzaman Pappu Online Model Predictive Control of a Robotic System by Combining Simulation and Optimization School of Electrical Engineering Department of Electrical Engineering and Automation
More information