This course focuses on improving human detection, tracking, and segmentation in surveillance videos by utilizing scene-specific information. Students will learn to employ a DPM human detector, train an SVM classifier using superpixel-based Bag-of-Words, and develop part-based person-specific SVM classifiers to handle occlusions. The teaching method includes utilizing Conditional Random Field for segmentation, tracklet-based Gaussian Mixture Models for tracking, and implementing a real-time tracking system using Intel Threading Building Blocks. The course is intended for individuals interested in computer engineering, computer vision, or video surveillance technology.
Human Detection, Tracking and Segmentation in Surveillance Video
University of Central Florida via YouTube
Overview
Syllabus
Motivation
Video Surveillance Tasks
Outline
Problems
Initial Detection
Training and Classification
Iteratively Learning
Superpixel Segmentation
Bag-of-Words
Qualitative Results
From Detection to Tracking
Part-based Model in Tracking
Features and Classifiers
Data Association
Proposed Method
DPM with Occlusion Handling
Occlusion handling Results
Occlusion Handling in Tracking
Occlusion Reasoning Results
Quantitative Results -- Town Center
Boston Airport
Parking Lot 1
Parking Lot dataset
From Detection to Segmentation
Human Detection
Background Gaussian Mixture Model (GMM)
Part-based Detection Potential
Graph Optimization
Initial Results
Multi-frame Segmentation
Obtaining Tracklets
Multi-frame CRF Optimization
Datasets and Groundtruth
Comparison with Background Subtraction
Segmentation Results (by frame)
For Real-World Application
Objective: Tracking
Multi-threaded Implementation
Tracking Overview
Adaptive Scaling
Local Frame Differencing
Summary
Dissertation Conclusion
Future Work
Publication
Taught by
UCF CRCV
