Chapter 10: Third Working Phase



Similar documents
Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite

IMPLICIT SHAPE MODELS FOR OBJECT DETECTION IN 3D POINT CLOUDS

T O B C A T C A S E G E O V I S A T DETECTIE E N B L U R R I N G V A N P E R S O N E N IN P A N O R A MISCHE BEELDEN

A Comprehensive Set of Image Quality Metrics

Vision based Vehicle Tracking using a high angle camera

Why use ColorGauge Micro Analyzer with the Micro and Nano Targets?

Using MATLAB to Measure the Diameter of an Object within an Image

Optical Flow. Shenlong Wang CSC2541 Course Presentation Feb 2, 2016

Automatic 3D Reconstruction via Object Detection and 3D Transformable Model Matching CS 269 Class Project Report

Automated News Item Categorization

VEHICLE LOCALISATION AND CLASSIFICATION IN URBAN CCTV STREAMS

Programming Exercise 3: Multi-class Classification and Neural Networks

Java Modules for Time Series Analysis

Object Recognition. Selim Aksoy. Bilkent University

Boosting.

Pedestrian Detection with RCNN

TERRAMOBILITA/IQMULUS URBAN POINT CLOUD CLASSIFICATION BENCHMARK

If you are working with the H4D-60 or multi-shot cameras we recommend 8GB of RAM on a 64 bit Windows and 1GB of video RAM.

MulticoreWare. Global Company, 250+ employees HQ = Sunnyvale, CA Other locations: US, China, India, Taiwan

Neovision2 Performance Evaluation Protocol

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

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

Visualizing Data: Scalable Interactivity

UNDERSTANDING THE EFFECTIVENESS OF BANK DIRECT MARKETING Tarun Gupta, Tong Xia and Diana Lee

Lecture 6: CNNs for Detection, Tracking, and Segmentation Object Detection

Orientation Course - Lab Manual

COC131 Data Mining - Clustering

Reflection and Refraction

Deferred Shading & Screen Space Effects

NAVIGATING SCIENTIFIC LITERATURE A HOLISTIC PERSPECTIVE. Venu Govindaraju

Machine Learning Capacity and Performance Analysis and R

The Role of Size Normalization on the Recognition Rate of Handwritten Numerals

User Guide. You will be presented with a login screen which will ask you for your username and password.

Lecture 07: Work and Kinetic Energy. Physics 2210 Fall Semester 2014

QCD as a Video Game?

UTILITIES BACKUP. Figure 25-1 Backup & Reindex utilities on the Main Menu

1. Classification problems

Overview. Swarms in nature. Fish, birds, ants, termites, Introduction to swarm intelligence principles Particle Swarm Optimization (PSO)

Maschinelles Lernen mit MATLAB

OPINION MINING IN PRODUCT REVIEW SYSTEM USING BIG DATA TECHNOLOGY HADOOP

Big Data: Image & Video Analytics

Automatic Labeling of Lane Markings for Autonomous Vehicles

521466S Machine Vision Assignment #7 Hough transform

Introduction to Pattern Recognition

Tutorial for proteome data analysis using the Perseus software platform

EFFICIENCY OF DECISION TREES IN PREDICTING STUDENT S ACADEMIC PERFORMANCE

Kickoff: Anomaly Detection Challenges

How To Use Trackeye

LIBSVX and Video Segmentation Evaluation

Analecta Vol. 8, No. 2 ISSN

Proposal Metrics Dashboard. What Gets Measured Gets Done

Microsoft Office Live Meeting Events User s Guide

Introduction to Imagery and Raster Data in ArcGIS

ARC 3D Webservice How to transform your images into 3D models. Maarten Vergauwen

Removing Web Spam Links from Search Engine Results

Indexing Full Packet Capture Data With Flow

Anomaly detection. Problem motivation. Machine Learning


Digital Photography Central - Beginners Guide

ACTIVITY CENTRE ZONE MAPPING STYLE GUIDE. Guidelines for producing Framework Plans and Precinct Maps for the Activity Centre Zone

Semi-Supervised Support Vector Machines and Application to Spam Filtering

Getting Started With LP360

Estimating and Mapping Reliability for American Community Survey Data

Tracking Groups of Pedestrians in Video Sequences

IE Operating Instruction Manual

CS1112 Spring 2014 Project 4. Objectives. 3 Pixelation for Identity Protection. due Thursday, 3/27, at 11pm

How To Use Neural Networks In Data Mining

Data Mining: A Preprocessing Engine

Neural Network based Vehicle Classification for Intelligent Traffic Control

Experiments in Web Page Classification for Semantic Web

Bootstrapping Big Data

INTERNAL USE ONLY (Set it to white if you do not need it)

IT PROJECT GOVERNANCE GUIDE

1 Laboratory #5: Grating Spectrometer

Support Vector Machine. Tutorial. (and Statistical Learning Theory)

V.I.P. Kit. Video Insight Pilot Kit. (Video Insight Pilot Kit).

Modelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches

Supervised Learning (Big Data Analytics)

Web Document Clustering

How to Use Swiftpage for Microsoft Outlook

automatic road sign detection from survey video

Collaborative Filtering. Radek Pelánek

A Prototype For Eye-Gaze Corrected

Accident configurations and injuries for bicyclists based on the German In-Depth Accident Study. Chiara Orsi

the Ministry of Transport is attributed as the source of the material

CSE 203 Web Programming 1. Prepared by: Asst. Prof. Dr. Maryam Eskandari

Local features and matching. Image classification & object localization

CSE452 Computer Graphics

Deploying Microsoft Operations Manager with the BIG-IP system and icontrol

TekBots TM Oregon State University. usb_cam User Guide. Version 1.0 By Adriaan Smit OSU EE Graduate Student

Active Learning SVM for Blogs recommendation

How to Send Video Images Through Internet

Speed Performance Improvement of Vehicle Blob Tracking System

PRODUCT DATA IMPORT SETUP GUIDE FOR ADVERTISERS

SharePoint Server 2010 Capacity Management: Software Boundaries and Limits

Transcription:

LEARNING AND INFERENCE IN GRAPHICAL MODELS Chapter 10: Third Working Phase Dr. Martin Lauer University of Freiburg Machine Learning Lab Karlsruhe Institute of Technology Institute of Measurement and Control Systems Learning and Inference in Graphical Models. Chapter 10 p. 1/8

Look back to working phase 1 (MNIST) Accuraccy of approaches on benchmark data: group A (Martin, Cem): 78.47% group B (Simon, Daniel): 51.09% group C (Aaron, Oliver): 41.28% group D (Ramin, Parastou):? Confusion matrix and details on our webpage Learning and Inference in Graphical Models. Chapter 10 p. 2/8

Look back to working phase 1 (MNIST) Accuraccy of approaches on benchmark data: group A (Martin, Cem): 78.47% group B (Simon, Daniel): 51.09% group C (Aaron, Oliver): 41.28% group D (Ramin, Parastou):? Confusion matrix and details on our webpage Do you remember the test errors presented? Learning and Inference in Graphical Models. Chapter 10 p. 2/8

Working phase 3 goal: detection and classification of traffic participants in camera images. KITTI-Objectrecognition-dataset http: //www.cvlibs.net/datasets/kitti/eval_object.php 7481 RGB training images containing approx. 40,000 relevant objects, manually labeled 7518 RGB benchmark images with an unknown number of objects object classes: Car (28742), Van (2914), Truck (1094), Tram (511), Cyclist (1627), Pedestrian (4487), Person sitting (222), Misc (973) Learning and Inference in Graphical Models. Chapter 10 p. 3/8

Benchmarking KITTI offers a possibility to evaluate and compare your final results on the benchmark image set. you apply your final approach on the benchmark images and write one label file with the detected objects KITTI provides accuracy measures for your detections and classifications comparison with other methods provided on the KITTI webpage the role of the DontCare objects: these show potentially relevant objects, however, they are not used for the performance evaluation (e.g. object too small, too much occluded, etc.) non-maxima suppression: for each object only one bounding box should be returned. This function will be provided by us (somewhen during the next weeks) Learning and Inference in Graphical Models. Chapter 10 p. 4/8

What you should do develop an approach to detect and classify traffic participants in RGB images based on the training images provided by KITTI potentially using other data sources (cf. KITTI webpage) potentially using image distortion and preprocessing techniques (color transformation, filtering, feature calculation/selection) using one or more approaches of deep learning architectures Learning and Inference in Graphical Models. Chapter 10 p. 5/8

What you should do develop an approach to detect and classify traffic participants in RGB images based on the training images provided by KITTI potentially using other data sources (cf. KITTI webpage) potentially using image distortion and preprocessing techniques (color transformation, filtering, feature calculation/selection) using one or more approaches of deep learning architectures until 9. Feb. 2014, 24:00 apply your best approach on the benchmark images and create one label file for each benchmark image zip the label files (using zip or tar/gnuzip=tgz) send the zip archive to me by email (martin.lauer@kit.edu) Learning and Inference in Graphical Models. Chapter 10 p. 5/8

What you should do develop an approach to detect and classify traffic participants in RGB images based on the training images provided by KITTI potentially using other data sources (cf. KITTI webpage) potentially using image distortion and preprocessing techniques (color transformation, filtering, feature calculation/selection) using one or more approaches of deep learning architectures until 9. Feb. 2014, 24:00 apply your best approach on the benchmark images and create one label file for each benchmark image zip the label files (using zip or tar/gnuzip=tgz) send the zip archive to me by email (martin.lauer@kit.edu) until 12. Feb. 2014, 12:30 prepare a presentation (10 minutes+questions) on your approach present your slides in the final lesson on 12. Feb. 2014 Learning and Inference in Graphical Models. Chapter 10 p. 5/8

Some technical notes where do you get the data? KITTI webpage www.cvlibs.net/datasets/kitti/eval_object.php download left images of object data set (12GB) download training labels of object data (5MB) if you like, download the object development kit (contains a readme file that explains the label file format) Learning and Inference in Graphical Models. Chapter 10 p. 6/8

Some technical notes where do you get the data? KITTI webpage www.cvlibs.net/datasets/kitti/eval_object.php download left images of object data set (12GB) download training labels of object data (5MB) if you like, download the object development kit (contains a readme file that explains the label file format) tools for reading writing images and label files in Lua/Torch and display results is provided on our webpage (kitti tools.lua) read_image loads a KITTI image with given file path and image number read_labels loads a KITTI label file and provides a table of objects write_labels writes a KITTI label file with a given set ob objects add_labels_to_images creates an image that displays the detected objects with bounding boxes Learning and Inference in Graphical Models. Chapter 10 p. 6/8

Some technical notes each object is represented in Lua/Torch as a table with attributes: type: string that indicates the class label ( Car, Pedestrian,...) x1, y1, x2, y2: the pixel coordinates of the left, upper, right, lower bound of the bounding box around the object score: a real number the indicates the confidence of your classification. The more confident the classifier is the larger the number should be (is used to calculate precision/recall curves) truncated: a number between 0 and 1 that indicates up to which extend the object is truncated at the image boundaries (0=non-truncated, 1=largely truncated) occluded: an integer between 0 and 3 that indicates whether the object is non-occluded (0), partly occluded (1), largely occluded (2) or the amount of occlusion is unknown (3) Learning and Inference in Graphical Models. Chapter 10 p. 7/8

Grouping group β: Martin, Ramin group γ: Oliver, Simon, Aaron group δ: Daniel, Cem Learning and Inference in Graphical Models. Chapter 10 p. 8/8