ROBUST REAL-TIME ON-BOARD VEHICLE TRACKING SYSTEM USING PARTICLES FILTER. Ecole des Mines de Paris, Paris, France

Size: px
Start display at page:

Download "ROBUST REAL-TIME ON-BOARD VEHICLE TRACKING SYSTEM USING PARTICLES FILTER. Ecole des Mines de Paris, Paris, France"

Transcription

1 ROBUST REAL-TIME ON-BOARD VEHICLE TRACKING SYSTEM USING PARTICLES FILTER Bruno Steux Yotam Abramson Ecole des Mines de Paris, Paris, France Abstract: We describe a system for detection and tracking of vehicles from a single on-board frontal camera, developed as a part of the European CAMELLIA project. Five image processing algorithms are used to detect target vehicles, classify them and maintain their exact localization. The fusion of the result of the algorithms is done using particle filtering. We assert that the particles filter forms the optimal mechanism to exploit the perceived data since it maintains the full probability density function based on all available algorithm in a given illumination and weather conditions. The algorithms are designed to exploit a set of low-level image processing operations, provided by a smart imaging core developed in the project. The result is that the system runs on 20 images/sec even on a regular pentium PC, and is design to run on real time using an ARM and the hardware core. The system was tested on many sequences and performs well even in hard conditions like rain and night. Keywords: Vehicle Detection, Adaptive Cruise Control, Stop&Go, Smart Imaging Core 1. INTRODUCTION Detection and tracking vehicles from a frontal onboard camera, installed on a moving vehicle, is a problem with several applications in driver assistance system. This paper describes an application for vehicle detection and tracking developed as a part of the European IST CAMEL- LIA project, which focuses on a platform-based development of a smart imaging core to be embedded in smart cameras. This imaging core provides low-level image processing operations like morphological and arithmetic operations, and the applications developed in this context are designed to take advantage of these operations. This paper will concentrate only on one of the applications of the project (namely low-speed obstacle detection). The interested reader is referred to (Jachalsky et al., 2003) or to the CAMELLIA project website at for information about other parts of the project. The application we present here (the high-level part) combines the output of several pedestriandetection medium-level algorithms in order to obtain an exact detection and localization of pedestrians. These medium-level algorithms do not access the image pixels directly but use the low-level operations mentioned above (a full description of the low-level operations, including the source code, is found online in The medium-level algorithms used are: (1) Shadow detection (2) Vertical edges detection

2 (3) Rear lights detection (4) Symmetry detection (5) Motion estimation A particle filtering framework is used to handle the analysis of these five algorithm and to maintain the knowledge about the existing targets. 2. THE PARTICLES FILTER FRAMEWORK Particle filtering is a useful method to track targets in non-linear, non-gaussian environment (Doucet et al., 2002), and the tracking of vehicles according to observation from five different algorithms is one such environment. In this application we use particle filtering to fuse the results of the five algorithms in order to perform accurate detection, localization and tracking of one or several vehicles. Particle filtering is a technique for implementing a recursive Bayesian filter by Monte Carlo simulations. The reader is referred to (Arulampalam et al., 2002) for a complete overview. We maintain, for each target, at each step k, a probability density function (PDF) p(x k z 1 k ) of the state x k of the target, according to a set of observations z 1 k = z 1,..., z k received at steps 1 to k. The PDF is represented using a set of N random samples with associated weights {x i k, wi k }N i=1, or particles. In our particular case, The state x i k is a triple X, Y, T representing a box-like vehicle whose bottom rear edge is centered around the ground point X, Y, 0. The parameter T can have one of the three values {MOT O, CAR, T RACK}, corresponding to motorcycle, car and truck, and the vehicle dimensions are determined by T using table??. Vehicle is assumed to aligned with the axes system (i.e. θ = 0, φ = 0, ψ = 0), as well as the ground, which is supposed to be flat in the area of interest. Vehicles with θ 0 (e.g. when driving on a turn) are treated in a later work. Observations z j k, j = are arriving at step k from the four algorithms. These observations are available through the likelihood functions l j (x k ) = p(z j k x k ) [0, 1] {DONT KNOW }, j = provided by the different algorithms. An algorithm returning DONT- KNOW is saying that it has no opinion about this particle, having not enough information available. This can happen, for example, when there is not enough illumination for shadow detection or when a car is entering from the left, still not exposed enough to perform symmetry analysis. 2.1 the likelihood function The final likelihood function which is used to update the weights of the particles is calculated as a product of all the likelihood values (except the ones equal to DONTKNOW), since they represent independent probabilities. A full description of the likelihood functions exceeds the scope of this paper; Naturally, each algorithm uses its special observation z k of the k th image (and, in the case of the motion estimator, also the k 1 th ) to estimate the probability p(z k x i k ) for each of the particles x 1 k... xn k of each existing target. Table 1 describes one iteration of the algorithm. The chosen particles filter version is the Sampling Importance Resampling (SIR) filter (see (Arulampalam et al., 2002), section B.1), which is efficient, simple and functions well when the distribution of the likelihood p(z k x k ) is not tighter than the prior density p(x k x k 1 ), as is the case here. The prior density - i.e. the evolution and noise model of the states - is calculated using the smoothed vehicle speed from the previous results. 2.2 Initialization of targets Targets are initialized by the shadow, the rearlights and the motion detectors. Each of the algorithm initialize a target anywhere it has an observation (a shadow, rear-lights or motion) which is not assigned to any existing targets. It is important to note that the algorithms are tune to prefer false initialization than missed target. This is because a falsely initialized target can be eliminated by low likelihood after it exists. A vehicle entering from the sides (so-called Cutin situation) is initialized as early as the time it appears on the screen, much before its rear part is visible. This is done using the motion detector, while using the shadow, and later the lights, as first likelihood values (see section for examples). Once appearing on the screen, the target is assumed to be in the nearest lane, with a lateral distance of 3.5 meters from the host vehicle. The true location is refined by the likelihood values. 3. THE ALGORITHMS When speaking about image processing algorithms in this context, we are referring to a type of algorithms which is being ran one time per every image of the video sequence. Typical algorithm will get as input the image, plus some additional information about already existing targets. For some algorithms this additional information is crucial because they are target-specific. For others this information is needed only to improve performance. After the algorithm is ran, it uses the results in two ways: create new targets and support/decline

3 Input: A target T already detected at step l of the algorithm (where l < k), represented by a set of particles {x i k 1, wi k 1 }N i=1 A likelihood function l(x) = p(z k x), provided using observations z k associated with the target T by the nearest neighbor method. A constant W 3, the speed calculation moving window width; V, a threshold for the variance of the speed; σnoise 2, the variance of the pedestrian movement noise; and N - number of particles. Calculate SS, the smoothed speed of the target: avr(s l+1,... s k 1 ) if k l > W and SS { var(s l+1,... s k 1 ) > V 0 otherwise N Where s k = i=1 (wi k xi k wi k 1 xi k 1 ) is the transient speed of the object at step k. Do for i = 1... N - Draw particle x i k normal(xi k 1 + SS, σ2 noise ) - Calculate w i k = l(xi k ) Calculate total weight t = N i=1 wi k Normalize particles weights: wk i wi k t, i = 1... N Resample using standard particles resampling algorithm (see (?)). Table 1. Step k of the particles filter on a given target theses (=particles) of existing targets. To create new targets, an algorithm provides us with a list of new targets, and for each target a list of hypotheses (=particles) where it believes the target is found. To support or decline the hypotheses of existing target, algorithms provide their likelihood function. We hereby briefly review the five algorithms used in our applications. These algorithms, except the motion detector, were used in (?), in the framework of a bayesian network. 3.1 vehicle shadow detection Shadow detection is based on the thresholding of images to find areas of darkness on the road. These areas are often shadows made by vehicles. The results are used both to generate new targets and to support/decline the existence of already discovered targets. The algorithm first selects a rectangle which is likely to fall entirely on the road, as demonstrated on Figure??. Then it computes the histogram of pixel values on this rectangle, as shown in Figure??. It threshold the entire image with a threshold value equal to 90% of the peek of the histogram (the threshold value is filtered in time, to prevent artifacts). Since this value is a little lower than the intensity of the road, the resulting blobs are the shadows. Shadows, which are located on reasonable locations (i.e. represent an approximate vehicle size when retroprojected to the world coordinates systems) are used to calculate likelihood values of existing targets - if they are close to one - or to initialize new ones otherwise. The system allows two separate shadows to match one vehicle, as shown in figure??. 3.2 rear-lights detection Lights detection is based on the detecting the rear lights and license plate of a car. The algorithm creates a histogram of the V image plane, and thresolds the images with a value equal to 95% of the maximum of the histogram, as shown in figure??. Then it searches for couples of blobs representing lights, or triples representing lights and plate. These values are used to initialize new targets or to provide likelihood value to existing targets particles. 3.3 symmetry detection Symmetry detection is based on the calculating the SAD (Sum of Absolute Differences) between some area of the image and its adjacent area in the mirror image, as seen in Figure??. If the two areas are two parts of a symmetry, the SAD will be zero. We repeat this algorithm on a set of adjacent pairs of regions to find the symmetry function as shown in Figure??. The results are used only to support/decline the existence of already discovered targets. Note that when the target is a vehicle, the symmetry function will typical have significantly low values in its middle and very high values in its sides, as seen in figure??. The low symmetry on the sides is as important as the symmetry at the middle. To understand this, observe that the sky have good symmetry in all the places. The algorithm does not initialize new targets. It provides the likelihood value by convultion of the result with the ideal function as shown in figure??. 3.4 vertical edges detection Vertical edges detection is based on looking for typical patterns of the vertical summing of the sobel image. The results are used only to support/decline the existence of already discovered

4 targets. Summing of the sobel typically gives a 3-peek function as shown in figure??. The 3 peeks become two when the vehicle is completely aligned ahead. Like in the symmetry algorithm, this algorithm does not initialize new targets, and provides the likelihood value by convultion of the result with the ideal function as shown in figure??. 3.5 motion segmentation are would like to add to the system is a learning This algorithm uses the motion detector of (Wittebroodalgorithm based on AdaBoost as done in (Viola and de Haan, 2001), which is highly efficient. The and Jones, 2001) for the detection of vehicles, with system computes motion models for each image the boosting values being the likelihood value. block, then groups blocks with similar motion, to form objects. These objects pass through a temporal filter that keeps only the motions which are consistent for several consecutive images. The algorithm is used to initalize targets and to provide likelihood values. The calculation is done simply by correlation with the detected moving objects. As will be seen in section 4, the likelihood value of this algorithm is quite coarse; it s important value is in initializing targets. We suggest that the particle filtering mechanism forms a good framework to fuse together any combination of algorithms to perform vehicle tracking. In another work being made as a part of the FADE2 Renault project, we combined laserradar information as just another algorithm which gives precise longitudinal information when a beam hits an object in front, and DONT- KNOW otherwise (see figure??). As expected, the mechanism performed well in exploiting this information. Other sources of information which Other extensions to the system to be done in the future include enlargement of the state space with θ 0 - that is, cars which are not directed straight ahead (e.g. when driving on a turn). This should be done carefully because merely adding dimensions to the state space might severely degrade performance. ACKNOWLEDGMENT 4. THE SYSTEM IN PRACTISE In this section we demonstrate, by showing reallife situations, that the particle filtering mechanism optimally exploits the analysis coming from the five algorithms. Figure 1 shows a typical daylight situation. A car is found about 30 meters in front of the host vehicle, and is initialized by the shadow detector. The target is quickly validated by all the algorithms except the motion detector (since the projected image of the car is not moving). In figure 2 we see a continuation of that sequence with a car entering from the right ( cut-in situation). The car is initialized very early by the shadow or motion detection (whichever detects first; usually in the second image after the appearance) and is maintained at the beginning mainly by the shadow detection, based on the assumptions outlines in section 2.2. The figure shows the scene a little bit later, after the rear of the car is beginning to appear. At this stage we can already see some initial contributions from the lights and vertical edges detection. As seen, motion detection is giving a high probability to the existence of the target but very little localization information. 5. CONCLUSION AND FUTURE WORK We have presented an application for vehicle detection and tracking based on particle filtering. This work was supported by the European IST CAMELLIA project and by the FADE- 2 Renault project. We would like to thank our partners including Renault research division, Philips Eindhoven, Phillips semiconductors Hamburg, and the universities of Hannover and Las- Palmas. REFERENCES Arulampalam, S., S. Maskell, N. Gordon and T. Clapp (2002). A tutorial on particle filters for on-line non-linear/non-gaussian bayesian tracking. IEEE Transactions on Signal Processing 50(2), Doucet, Arnaud, de Freitas, Nando and Gordon, Neil, Eds.) (2002). Sequential Monte Carlo Methods in Practice. Statistics for Engineering and Information Science. Springer-Verlag, New York Berlin Heidelberg. Jachalsky, J., M. Wahle, P. Pirsch, S. Capperon, W. Gehrke, W.M. Kruijtzer and A. Nuez (2003). A core for ambient and mobile intelligent imaging applications. In: Proceedings of the 2003 IEEE International Conference on Multimedia & Expo (ICME 2003). p. CDROM. Viola, Paul and Michael Jones (2001). Rapid object detection using a boosted cascade of simple features. In: Proceedings IEEE Conf. on Computer Vision and Pattern Recognition. Wittebrood, R.B. and G. de Haan (2001). Real-time recursive motion segmentation of

5 (a) (b) (c) (d) (e) (f) Fig. 1. A typical situation of a vehicle in front of our car. The frontal view (2(f)) and likelihood functions (from bird s eye view) of the shadow detection (2(a)), the vertical edges detector (2(b)), the symmetry detector (2(c)), the motion estimator (2(d)) and the rear lights detector (2(e)). Values are denoted from black (0) to white (1). (a) (b) (c) (d) (e) (f) Fig. 2. A vehicle entering from the left ( cut-in situation). The frontal view (2(f)) and likelihood functions (from bird s eye view) of the shadow detection (2(a)), the vertical edges detector (2(b)), the symmetry detector (2(c)), the motion estimator (2(d)) and the rear lights detector (2(e)). Values are denoted from black (0) to white (1).

6 video data on a programmable device. In: IEEE Transactions on Consumer Electronics. pp

VEHICLE TRACKING USING ACOUSTIC AND VIDEO SENSORS

VEHICLE 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 information

Vision-Based Blind Spot Detection Using Optical Flow

Vision-Based Blind Spot Detection Using Optical Flow Vision-Based Blind Spot Detection Using Optical Flow M.A. Sotelo 1, J. Barriga 1, D. Fernández 1, I. Parra 1, J.E. Naranjo 2, M. Marrón 1, S. Alvarez 1, and M. Gavilán 1 1 Department of Electronics, University

More information

Speed Performance Improvement of Vehicle Blob Tracking System

Speed 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 information

A Robust Multiple Object Tracking for Sport Applications 1) Thomas Mauthner, Horst Bischof

A Robust Multiple Object Tracking for Sport Applications 1) Thomas Mauthner, Horst Bischof A Robust Multiple Object Tracking for Sport Applications 1) Thomas Mauthner, Horst Bischof Institute for Computer Graphics and Vision Graz University of Technology, Austria {mauthner,bischof}@icg.tu-graz.ac.at

More information

Mean-Shift Tracking with Random Sampling

Mean-Shift Tracking with Random Sampling 1 Mean-Shift 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 information

A Reliability Point and Kalman Filter-based Vehicle Tracking Technique

A Reliability Point and Kalman Filter-based Vehicle Tracking Technique A Reliability Point and Kalman Filter-based 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 information

A PHOTOGRAMMETRIC APPRAOCH FOR AUTOMATIC TRAFFIC ASSESSMENT USING CONVENTIONAL CCTV CAMERA

A 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 information

A Study on SURF Algorithm and Real-Time Tracking Objects Using Optical Flow

A Study on SURF Algorithm and Real-Time Tracking Objects Using Optical Flow , pp.233-237 http://dx.doi.org/10.14257/astl.2014.51.53 A Study on SURF Algorithm and Real-Time Tracking Objects Using Optical Flow Giwoo Kim 1, Hye-Youn Lim 1 and Dae-Seong Kang 1, 1 Department of electronices

More information

3-d Blood Flow Reconstruction from 2-d Angiograms

3-d Blood Flow Reconstruction from 2-d Angiograms 3-d Blood Flow Reconstruction from 2-d Angiograms Esther-S. Platzer 1, Frank Deinzer 2, Dietrich Paulus 3, Joachim Denzler 1 1 Institut für Mathematik/Informatik, Friedrich-Schiller-Universität Jena, 07743

More information

Face Recognition in Low-resolution Images by Using Local Zernike Moments

Face Recognition in Low-resolution Images by Using Local Zernike Moments Proceedings of the International Conference on Machine Vision and Machine Learning Prague, Czech Republic, August14-15, 014 Paper No. 15 Face Recognition in Low-resolution Images by Using Local Zernie

More information

A Tutorial on Particle Filters for Online Nonlinear/Non-Gaussian Bayesian Tracking

A Tutorial on Particle Filters for Online Nonlinear/Non-Gaussian Bayesian Tracking 174 IEEE TRANSACTIONS ON SIGNAL PROCESSING, VOL. 50, NO. 2, FEBRUARY 2002 A Tutorial on Particle Filters for Online Nonlinear/Non-Gaussian Bayesian Tracking M. Sanjeev Arulampalam, Simon Maskell, Neil

More information

An Energy-Based Vehicle Tracking System using Principal Component Analysis and Unsupervised ART Network

An Energy-Based Vehicle Tracking System using Principal Component Analysis and Unsupervised ART Network Proceedings of the 8th WSEAS Int. Conf. on ARTIFICIAL INTELLIGENCE, KNOWLEDGE ENGINEERING & DATA BASES (AIKED '9) ISSN: 179-519 435 ISBN: 978-96-474-51-2 An Energy-Based Vehicle Tracking System using Principal

More information

High Quality Image Magnification using Cross-Scale Self-Similarity

High Quality Image Magnification using Cross-Scale Self-Similarity High Quality Image Magnification using Cross-Scale Self-Similarity André Gooßen 1, Arne Ehlers 1, Thomas Pralow 2, Rolf-Rainer Grigat 1 1 Vision Systems, Hamburg University of Technology, D-21079 Hamburg

More information

How To Fix Out Of Focus And Blur Images With A Dynamic Template Matching Algorithm

How To Fix Out Of Focus And Blur Images With A Dynamic Template Matching Algorithm IJSTE - International Journal of Science Technology & Engineering Volume 1 Issue 10 April 2015 ISSN (online): 2349-784X Image Estimation Algorithm for Out of Focus and Blur Images to Retrieve the Barcode

More information

Vehicle Tracking System Robust to Changes in Environmental Conditions

Vehicle Tracking System Robust to Changes in Environmental Conditions INORMATION & COMMUNICATIONS Vehicle Tracking System Robust to Changes in Environmental Conditions Yasuo OGIUCHI*, Masakatsu HIGASHIKUBO, Kenji NISHIDA and Takio KURITA Driving Safety Support Systems (DSSS)

More information

Distributed Vision Processing in Smart Camera Networks

Distributed Vision Processing in Smart Camera Networks Distributed Vision Processing in Smart Camera Networks CVPR-07 Hamid Aghajan, Stanford University, USA François Berry, Univ. Blaise Pascal, France Horst Bischof, TU Graz, Austria Richard Kleihorst, NXP

More information

Robust Real-Time Face Detection

Robust Real-Time Face Detection Robust Real-Time Face Detection International Journal of Computer Vision 57(2), 137 154, 2004 Paul Viola, Michael Jones 授 課 教 授 : 林 信 志 博 士 報 告 者 : 林 宸 宇 報 告 日 期 :96.12.18 Outline Introduction The Boost

More information

Rear-end Collision Prevention Using Mobile Devices

Rear-end Collision Prevention Using Mobile Devices Rear-end Collision Prevention Using Mobile Devices Nanxiang Li, Amardeep Sathyanarayana, Carlos Busso, John H.L. Hansen Center for Robust Speech Systems (CRSS) Dept. of Electrical Engineering, Jonsson

More information

Automatic Traffic Estimation Using Image Processing

Automatic Traffic Estimation Using Image Processing Automatic Traffic Estimation Using Image Processing Pejman Niksaz Science &Research Branch, Azad University of Yazd, Iran Pezhman_1366@yahoo.com Abstract As we know the population of city and number of

More information

2. Colour based particle filter for 3-D tracking

2. Colour based particle filter for 3-D tracking MULTI-CAMERA 3-D TRACKING USING PARTICLE FILTER Pablo Barrera, José M. Cañas, Vicente Matellán, and Francisco Martín Grupo de Robótica, Universidad Rey Juan Carlos Móstoles, Madrid (Spain) {barrera,jmplaza,vmo,fmartin}@gsyc.escet.urjc.es

More information

Detection and Restoration of Vertical Non-linear Scratches in Digitized Film Sequences

Detection and Restoration of Vertical Non-linear Scratches in Digitized Film Sequences Detection and Restoration of Vertical Non-linear Scratches in Digitized Film Sequences Byoung-moon You 1, Kyung-tack Jung 2, Sang-kook Kim 2, and Doo-sung Hwang 3 1 L&Y Vision Technologies, Inc., Daejeon,

More information

Detection and Recognition of Mixed Traffic for Driver Assistance System

Detection and Recognition of Mixed Traffic for Driver Assistance System Detection and Recognition of Mixed Traffic for Driver Assistance System Pradnya Meshram 1, Prof. S.S. Wankhede 2 1 Scholar, Department of Electronics Engineering, G.H.Raisoni College of Engineering, Digdoh

More information

Performance evaluation of multi-camera visual tracking

Performance evaluation of multi-camera visual tracking Performance evaluation of multi-camera visual tracking Lucio Marcenaro, Pietro Morerio, Mauricio Soto, Andrea Zunino, Carlo S. Regazzoni DITEN, University of Genova Via Opera Pia 11A 16145 Genoa - Italy

More information

HANDS-FREE PC CONTROL CONTROLLING OF MOUSE CURSOR USING EYE MOVEMENT

HANDS-FREE PC CONTROL CONTROLLING OF MOUSE CURSOR USING EYE MOVEMENT International Journal of Scientific and Research Publications, Volume 2, Issue 4, April 2012 1 HANDS-FREE PC CONTROL CONTROLLING OF MOUSE CURSOR USING EYE MOVEMENT Akhil Gupta, Akash Rathi, Dr. Y. Radhika

More information

MODULAR TRAFFIC SIGNS RECOGNITION APPLIED TO ON-VEHICLE REAL-TIME VISUAL DETECTION OF AMERICAN AND EUROPEAN SPEED LIMIT SIGNS

MODULAR TRAFFIC SIGNS RECOGNITION APPLIED TO ON-VEHICLE REAL-TIME VISUAL DETECTION OF AMERICAN AND EUROPEAN SPEED LIMIT SIGNS MODULAR TRAFFIC SIGNS RECOGNITION APPLIED TO ON-VEHICLE REAL-TIME VISUAL DETECTION OF AMERICAN AND EUROPEAN SPEED LIMIT SIGNS Fabien Moutarde and Alexandre Bargeton Robotics Laboratory Ecole des Mines

More information

Laser Gesture Recognition for Human Machine Interaction

Laser Gesture Recognition for Human Machine Interaction International Journal of Computer Sciences and Engineering Open Access Research Paper Volume-04, Issue-04 E-ISSN: 2347-2693 Laser Gesture Recognition for Human Machine Interaction Umang Keniya 1*, Sarthak

More information

A Learning Based Method for Super-Resolution of Low Resolution Images

A Learning Based Method for Super-Resolution of Low Resolution Images A Learning Based Method for Super-Resolution 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 information

Towards License Plate Recognition: Comparying Moving Objects Segmentation Approaches

Towards License Plate Recognition: Comparying Moving Objects Segmentation Approaches 1 Towards License Plate Recognition: Comparying Moving Objects Segmentation Approaches V. J. Oliveira-Neto, G. Cámara-Chávez, D. Menotti UFOP - Federal University of Ouro Preto Computing Department Ouro

More information

Fall detection in the elderly by head tracking

Fall detection in the elderly by head tracking Loughborough University Institutional Repository Fall detection in the elderly by head tracking This item was submitted to Loughborough University's Institutional Repository by the/an author. Citation:

More information

Detecting and positioning overtaking vehicles using 1D optical flow

Detecting and positioning overtaking vehicles using 1D optical flow Detecting and positioning overtaking vehicles using 1D optical flow Daniel Hultqvist 1, Jacob Roll 1, Fredrik Svensson 1, Johan Dahlin 2, and Thomas B. Schön 3 Abstract We are concerned with the problem

More information

Least Squares Estimation

Least Squares Estimation Least Squares Estimation SARA A VAN DE GEER Volume 2, pp 1041 1045 in Encyclopedia of Statistics in Behavioral Science ISBN-13: 978-0-470-86080-9 ISBN-10: 0-470-86080-4 Editors Brian S Everitt & David

More information

UNIVERSITY OF CENTRAL FLORIDA AT TRECVID 2003. Yun Zhai, Zeeshan Rasheed, Mubarak Shah

UNIVERSITY OF CENTRAL FLORIDA AT TRECVID 2003. Yun Zhai, Zeeshan Rasheed, Mubarak Shah UNIVERSITY OF CENTRAL FLORIDA AT TRECVID 2003 Yun Zhai, Zeeshan Rasheed, Mubarak Shah Computer Vision Laboratory School of Computer Science University of Central Florida, Orlando, Florida ABSTRACT In this

More information

Mini-project in TSRT04: Cell Phone Coverage

Mini-project in TSRT04: Cell Phone Coverage Mini-project in TSRT04: Cell hone Coverage 19 August 2015 1 roblem Formulation According to the study Swedes and Internet 2013 (Stiftelsen för Internetinfrastruktur), 99% of all Swedes in the age 12-45

More information

Real-time Visual Tracker by Stream Processing

Real-time Visual Tracker by Stream Processing Real-time Visual Tracker by Stream Processing Simultaneous and Fast 3D Tracking of Multiple Faces in Video Sequences by Using a Particle Filter Oscar Mateo Lozano & Kuzahiro Otsuka presented by Piotr Rudol

More information

Automatic Labeling of Lane Markings for Autonomous Vehicles

Automatic 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 information

Tracking of Small Unmanned Aerial Vehicles

Tracking 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 information

3D Vision An enabling Technology for Advanced Driver Assistance and Autonomous Offroad Driving

3D Vision An enabling Technology for Advanced Driver Assistance and Autonomous Offroad Driving 3D Vision An enabling Technology for Advanced Driver Assistance and Autonomous Offroad Driving AIT Austrian Institute of Technology Safety & Security Department Christian Zinner Safe and Autonomous Systems

More information

BENEFIT OF DYNAMIC USE CASES TO EARLY DESIGN A DRIVING ASSISTANCE SYSTEM FOR PEDESTRIAN/TRUCK COLLISION AVOIDANCE

BENEFIT OF DYNAMIC USE CASES TO EARLY DESIGN A DRIVING ASSISTANCE SYSTEM FOR PEDESTRIAN/TRUCK COLLISION AVOIDANCE BENEFIT OF DYNAMIC USE CASES TO EARLY DESIGN A DRIVING ASSISTANCE SYSTEM FOR PEDESTRIAN/TRUCK COLLISION AVOIDANCE Hélène Tattegrain, Arnaud Bonnard, Benoit Mathern, LESCOT, INRETS France Paper Number 09-0489

More information

A System for Capturing High Resolution Images

A System for Capturing High Resolution Images A System for Capturing High Resolution Images G.Voyatzis, G.Angelopoulos, A.Bors and I.Pitas Department of Informatics University of Thessaloniki BOX 451, 54006 Thessaloniki GREECE e-mail: pitas@zeus.csd.auth.gr

More information

False alarm in outdoor environments

False 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 Pre-processing 4 3 Detection,

More information

REAL TIME TRAFFIC LIGHT CONTROL USING IMAGE PROCESSING

REAL 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 information

Vision based Vehicle Tracking using a high angle camera

Vision 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 information

Introduction to Mobile Robotics Bayes Filter Particle Filter and Monte Carlo Localization

Introduction to Mobile Robotics Bayes Filter Particle Filter and Monte Carlo Localization Introduction to Mobile Robotics Bayes Filter Particle Filter and Monte Carlo Localization Wolfram Burgard, Maren Bennewitz, Diego Tipaldi, Luciano Spinello 1 Motivation Recall: Discrete filter Discretize

More information

Building an Advanced Invariant Real-Time Human Tracking System

Building an Advanced Invariant Real-Time Human Tracking System UDC 004.41 Building an Advanced Invariant Real-Time 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, German-Jordanian

More information

Video Surveillance System for Security Applications

Video Surveillance System for Security Applications Video Surveillance System for Security Applications Vidya A.S. Department of CSE National Institute of Technology Calicut, Kerala, India V. K. Govindan Department of CSE National Institute of Technology

More information

Tracking in flussi video 3D. Ing. Samuele Salti

Tracking 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 information

Application of Face Recognition to Person Matching in Trains

Application of Face Recognition to Person Matching in Trains Application of Face Recognition to Person Matching in Trains May 2008 Objective Matching of person Context : in trains Using face recognition and face detection algorithms With a video-surveillance camera

More information

Modelling, 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 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 information

The Visual Internet of Things System Based on Depth Camera

The Visual Internet of Things System Based on Depth Camera The Visual Internet of Things System Based on Depth Camera Xucong Zhang 1, Xiaoyun Wang and Yingmin Jia Abstract The Visual Internet of Things is an important part of information technology. It is proposed

More information

Discrete Frobenius-Perron Tracking

Discrete Frobenius-Perron Tracking Discrete Frobenius-Perron Tracing Barend J. van Wy and Michaël A. van Wy French South-African Technical Institute in Electronics at the Tshwane University of Technology Staatsartillerie Road, Pretoria,

More information

M3S ANPR Automatic Number Plates Recognize System

M3S ANPR Automatic Number Plates Recognize System Zakopianska 6 Str. 03-934 Warsaw tel. (22) 511 19 99 fax: (22) 511 19 95 www.polixel.pl M3S ANPR Automatic Number Plates Recognize System M3S-ANPR Automatic Number Plates Recognize system is authorial

More information

Optimal Vision Using Cameras for Intelligent Transportation Systems

Optimal Vision Using Cameras for Intelligent Transportation Systems WHITE PAPER www.baslerweb.com Optimal Vision Using Cameras for Intelligent Transportation Systems Intelligent Transportation Systems (ITS) require intelligent vision solutions. Modern camera technologies

More information

Tracking and Recognition in Sports Videos

Tracking 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 information

Deterministic Sampling-based Switching Kalman Filtering for Vehicle Tracking

Deterministic Sampling-based Switching Kalman Filtering for Vehicle Tracking Proceedings of the IEEE ITSC 2006 2006 IEEE Intelligent Transportation Systems Conference Toronto, Canada, September 17-20, 2006 WA4.1 Deterministic Sampling-based Switching Kalman Filtering for Vehicle

More information

Object tracking in video scenes

Object tracking in video scenes A Seminar On Object tracking in video scenes Presented by Alok K. Watve M.Tech. IT 1st year Indian Institue of Technology, Kharagpur Under the guidance of Dr. Shamik Sural Assistant Professor School of

More information

The Scientific Data Mining Process

The 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 information

Automated Process for Generating Digitised Maps through GPS Data Compression

Automated Process for Generating Digitised Maps through GPS Data Compression Automated Process for Generating Digitised Maps through GPS Data Compression Stewart Worrall and Eduardo Nebot University of Sydney, Australia {s.worrall, e.nebot}@acfr.usyd.edu.au Abstract This paper

More information

Probabilistic Latent Semantic Analysis (plsa)

Probabilistic Latent Semantic Analysis (plsa) Probabilistic Latent Semantic Analysis (plsa) SS 2008 Bayesian Networks Multimedia Computing, Universität Augsburg Rainer.Lienhart@informatik.uni-augsburg.de www.multimedia-computing.{de,org} References

More information

Real-Time Tracking of Pedestrians and Vehicles

Real-Time Tracking of Pedestrians and Vehicles Real-Time 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 information

Multisensor Data Fusion and Applications

Multisensor Data Fusion and Applications Multisensor Data Fusion and Applications Pramod K. Varshney Department of Electrical Engineering and Computer Science Syracuse University 121 Link Hall Syracuse, New York 13244 USA E-mail: varshney@syr.edu

More information

Practical Tour of Visual tracking. David Fleet and Allan Jepson January, 2006

Practical 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 information

An Active Head Tracking System for Distance Education and Videoconferencing Applications

An Active Head Tracking System for Distance Education and Videoconferencing Applications An Active Head Tracking System for Distance Education and Videoconferencing Applications Sami Huttunen and Janne Heikkilä Machine Vision Group Infotech Oulu and Department of Electrical and Information

More information

Development of an automated Red Light Violation Detection System (RLVDS) for Indian vehicles

Development of an automated Red Light Violation Detection System (RLVDS) for Indian vehicles CS11 59 Development of an automated Red Light Violation Detection System (RLVDS) for Indian vehicles Satadal Saha 1, Subhadip Basu 2 *, Mita Nasipuri 2, Dipak Kumar Basu # 2 # AICTE Emeritus Fellow 1 CSE

More information

CS231M Project Report - Automated Real-Time Face Tracking and Blending

CS231M Project Report - Automated Real-Time Face Tracking and Blending CS231M Project Report - Automated Real-Time 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 information

DYNAMIC RANGE IMPROVEMENT THROUGH MULTIPLE EXPOSURES. Mark A. Robertson, Sean Borman, and Robert L. Stevenson

DYNAMIC 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 information

Analecta Vol. 8, No. 2 ISSN 2064-7964

Analecta Vol. 8, No. 2 ISSN 2064-7964 EXPERIMENTAL APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS IN ENGINEERING PROCESSING SYSTEM S. Dadvandipour Institute of Information Engineering, University of Miskolc, Egyetemváros, 3515, Miskolc, Hungary,

More information

Learning Detectors from Large Datasets for Object Retrieval in Video Surveillance

Learning Detectors from Large Datasets for Object Retrieval in Video Surveillance 2012 IEEE International Conference on Multimedia and Expo Learning Detectors from Large Datasets for Object Retrieval in Video Surveillance Rogerio Feris, Sharath Pankanti IBM T. J. Watson Research Center

More information

Static Environment Recognition Using Omni-camera from a Moving Vehicle

Static Environment Recognition Using Omni-camera from a Moving Vehicle Static Environment Recognition Using Omni-camera from a Moving Vehicle Teruko Yata, Chuck Thorpe Frank Dellaert The Robotics Institute Carnegie Mellon University Pittsburgh, PA 15213 USA College of Computing

More information

Very Low Frame-Rate Video Streaming For Face-to-Face Teleconference

Very Low Frame-Rate Video Streaming For Face-to-Face Teleconference Very Low Frame-Rate Video Streaming For Face-to-Face Teleconference Jue Wang, Michael F. Cohen Department of Electrical Engineering, University of Washington Microsoft Research Abstract Providing the best

More information

Lecture 10: Regression Trees

Lecture 10: Regression Trees Lecture 10: Regression Trees 36-350: Data Mining October 11, 2006 Reading: Textbook, sections 5.2 and 10.5. The next three lectures are going to be about a particular kind of nonlinear predictive model,

More information

Motion Activated Video Surveillance Using TI DSP

Motion Activated Video Surveillance Using TI DSP Motion Activated Video Surveillance Using TI DSP Ching-Kai Huang and Tsuhan Chen Dept. of Electrical and Computer Engineering Carnegie Mellon University 5000 Forbes Avenue, Pittsburgh, PA 15213 tsuhan@cmu.edu

More information

MVA ENS Cachan. Lecture 2: Logistic regression & intro to MIL Iasonas Kokkinos Iasonas.kokkinos@ecp.fr

MVA ENS Cachan. Lecture 2: Logistic regression & intro to MIL Iasonas Kokkinos Iasonas.kokkinos@ecp.fr Machine Learning for Computer Vision 1 MVA ENS Cachan Lecture 2: Logistic regression & intro to MIL Iasonas Kokkinos Iasonas.kokkinos@ecp.fr Department of Applied Mathematics Ecole Centrale Paris Galen

More information

Simultaneous Gamma Correction and Registration in the Frequency Domain

Simultaneous 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 information

A Computer Vision System on a Chip: a case study from the automotive domain

A Computer Vision System on a Chip: a case study from the automotive domain A Computer Vision System on a Chip: a case study from the automotive domain Gideon P. Stein Elchanan Rushinek Gaby Hayun Amnon Shashua Mobileye Vision Technologies Ltd. Hebrew University Jerusalem, Israel

More information

Demo: Real-time Tracking of Round Object

Demo: Real-time Tracking of Round Object Page 1 of 1 Demo: Real-time Tracking of Round Object by: Brianna Bikker and David Price, TAMU Course Instructor: Professor Deepa Kundur Introduction Our project is intended to track the motion of a round

More information

Towards robust automatic detection of vulnerable road users: monocular pedestrian tracking from a moving vehicle

Towards robust automatic detection of vulnerable road users: monocular pedestrian tracking from a moving vehicle Towards robust automatic detection of vulnerable road users: monocular pedestrian tracking from a moving vehicle Kristof Van Beeck 1, Floris De Smedt 1, Sander Beckers 1, Lars Struyf 1, Joost Vennekens

More information

ROBUST VEHICLE TRACKING IN VIDEO IMAGES BEING TAKEN FROM A HELICOPTER

ROBUST VEHICLE TRACKING IN VIDEO IMAGES BEING TAKEN FROM A HELICOPTER ROBUST VEHICLE TRACKING IN VIDEO IMAGES BEING TAKEN FROM A HELICOPTER Fatemeh Karimi Nejadasl, Ben G.H. Gorte, and Serge P. Hoogendoorn Institute of Earth Observation and Space System, Delft University

More information

Seventh IEEE Workshop on Embedded Computer Vision. Ego-Motion Compensated Face Detection on a Mobile Device

Seventh IEEE Workshop on Embedded Computer Vision. Ego-Motion Compensated Face Detection on a Mobile Device Seventh IEEE Workshop on Embedded Computer Vision Ego-Motion Compensated Face Detection on a Mobile Device Björn Scheuermann, Arne Ehlers, Hamon Riazy, Florian Baumann, Bodo Rosenhahn Leibniz Universität

More information

The Trip Scheduling Problem

The Trip Scheduling Problem The Trip Scheduling Problem Claudia Archetti Department of Quantitative Methods, University of Brescia Contrada Santa Chiara 50, 25122 Brescia, Italy Martin Savelsbergh School of Industrial and Systems

More information

VEHICLE LOCALISATION AND CLASSIFICATION IN URBAN CCTV STREAMS

VEHICLE 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 information

Traffic Flow Monitoring in Crowded Cities

Traffic 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 information

An Instructional Aid System for Driving Schools Based on Visual Simulation

An Instructional Aid System for Driving Schools Based on Visual Simulation An Instructional Aid System for Driving Schools Based on Visual Simulation Salvador Bayarri, Rafael Garcia, Pedro Valero, Ignacio Pareja, Institute of Traffic and Road Safety (INTRAS), Marcos Fernandez

More information

Chapter 4 Software Lifecycle and Performance Analysis

Chapter 4 Software Lifecycle and Performance Analysis Chapter 4 Software Lifecycle and Performance Analysis This chapter is aimed at illustrating performance modeling and analysis issues within the software lifecycle. After having introduced software and

More information

Tracking Moving Objects In Video Sequences Yiwei Wang, Robert E. Van Dyck, and John F. Doherty Department of Electrical Engineering The Pennsylvania State University University Park, PA16802 Abstract{Object

More information

Probability Hypothesis Density filter versus Multiple Hypothesis Tracking

Probability Hypothesis Density filter versus Multiple Hypothesis Tracking Probability Hypothesis Density filter versus Multiple Hypothesis Tracing Kusha Panta a, Ba-Ngu Vo a, Sumeetpal Singh a and Arnaud Doucet b a Co-operative Research Centre for Sensor and Information Processing

More information

PHOTON mapping is a practical approach for computing global illumination within complex

PHOTON mapping is a practical approach for computing global illumination within complex 7 The Photon Mapping Method I get by with a little help from my friends. John Lennon, 1940 1980 PHOTON mapping is a practical approach for computing global illumination within complex environments. Much

More information

STT315 Chapter 4 Random Variables & Probability Distributions KM. Chapter 4.5, 6, 8 Probability Distributions for Continuous Random Variables

STT315 Chapter 4 Random Variables & Probability Distributions KM. Chapter 4.5, 6, 8 Probability Distributions for Continuous Random Variables Chapter 4.5, 6, 8 Probability Distributions for Continuous Random Variables Discrete vs. continuous random variables Examples of continuous distributions o Uniform o Exponential o Normal Recall: A random

More information

Kristine L. Bell and Harry L. Van Trees. Center of Excellence in C 3 I George Mason University Fairfax, VA 22030-4444, USA kbell@gmu.edu, hlv@gmu.

Kristine L. Bell and Harry L. Van Trees. Center of Excellence in C 3 I George Mason University Fairfax, VA 22030-4444, USA kbell@gmu.edu, hlv@gmu. POSERIOR CRAMÉR-RAO BOUND FOR RACKING ARGE BEARING Kristine L. Bell and Harry L. Van rees Center of Excellence in C 3 I George Mason University Fairfax, VA 22030-4444, USA bell@gmu.edu, hlv@gmu.edu ABSRAC

More information

Method for detecting software anomalies based on recurrence plot analysis

Method for detecting software anomalies based on recurrence plot analysis Journal of Theoretical and Applied Computer Science Vol. 6, No. 1, 2012, pp. 3-12 ISSN 2299-2634 http://www.jtacs.org Method for detecting software anomalies based on recurrence plot analysis Michał Mosdorf

More information

Visual Perception and Tracking of Vehicles for Driver Assistance Systems

Visual Perception and Tracking of Vehicles for Driver Assistance Systems 3-11 Visual Perception and Tracking of Vehicles for Driver Assistance Systems Cristina Hilario, Juan Manuel Collado, Jose Maria Armingol and Arturo de la Escalera Intelligent Systems Laboratory, Department

More information

Real time vehicle detection and tracking on multiple lanes

Real time vehicle detection and tracking on multiple lanes Real time vehicle detection and tracking on multiple lanes Kristian Kovačić Edouard Ivanjko Hrvoje Gold Department of Intelligent Transportation Systems Faculty of Transport and Traffic Sciences University

More information

Cloud tracking with optical flow for short-term solar forecasting

Cloud tracking with optical flow for short-term solar forecasting Cloud tracking with optical flow for short-term solar forecasting Philip Wood-Bradley, José Zapata, John Pye Solar Thermal Group, Australian National University, Canberra, Australia Corresponding author:

More information

Last Mile Intelligent Driving in Urban Mobility

Last Mile Intelligent Driving in Urban Mobility 底 盘 电 子 控 制 系 统 研 究 室 Chassis Electronic Control Systems Laboratory 姓 学 名 号 Hui CHEN School 学 of 院 ( Automotive 系 ) Studies, Tongji University, Shanghai, China 学 科 专 业 hui-chen@tongji.edu.cn 指 导 老 师 陈

More information

Using fractal compression scheme to embed a digital signature into an image

Using fractal compression scheme to embed a digital signature into an image Using fractal compression scheme to embed a digital signature into an image Joan Puate, Fred Jordan Swiss federal institute of technology Signal Processing Laboratory CH-1015 Lausanne Switzerland Email:

More information

The Trade-off between Image Resolution and Field of View: the Influence of Lens Selection

The Trade-off between Image Resolution and Field of View: the Influence of Lens Selection The Trade-off between Image Resolution and Field of View: the Influence of Lens Selection I want a lens that can cover the whole parking lot and I want to be able to read a license plate. Sound familiar?

More information

CHAPTER 6 TEXTURE ANIMATION

CHAPTER 6 TEXTURE ANIMATION CHAPTER 6 TEXTURE ANIMATION 6.1. INTRODUCTION Animation is the creating of a timed sequence or series of graphic images or frames together to give the appearance of continuous movement. A collection of

More information

Robert Collins CSE598G. More on Mean-shift. R.Collins, CSE, PSU CSE598G Spring 2006

Robert Collins CSE598G. More on Mean-shift. R.Collins, CSE, PSU CSE598G Spring 2006 More on Mean-shift R.Collins, CSE, PSU Spring 2006 Recall: Kernel Density Estimation Given a set of data samples x i ; i=1...n Convolve with a kernel function H to generate a smooth function f(x) Equivalent

More information

Head and Facial Animation Tracking using Appearance-Adaptive Models and Particle Filters

Head and Facial Animation Tracking using Appearance-Adaptive Models and Particle Filters Head and Facial Animation Tracking using Appearance-Adaptive Models and Particle Filters F. Dornaika and F. Davoine CNRS HEUDIASYC Compiègne University of Technology 625 Compiègne Cedex, FRANCE {dornaika,

More information

Semantic Video Annotation by Mining Association Patterns from Visual and Speech Features

Semantic Video Annotation by Mining Association Patterns from Visual and Speech Features Semantic Video Annotation by Mining Association Patterns from and Speech Features Vincent. S. Tseng, Ja-Hwung Su, Jhih-Hong Huang and Chih-Jen Chen Department of Computer Science and Information Engineering

More information

Navigation Aid And Label Reading With Voice Communication For Visually Impaired People

Navigation Aid And Label Reading With Voice Communication For Visually Impaired People Navigation Aid And Label Reading With Voice Communication For Visually Impaired People A.Manikandan 1, R.Madhuranthi 2 1 M.Kumarasamy College of Engineering, mani85a@gmail.com,karur,india 2 M.Kumarasamy

More information