Video Tracking and Crowd-Scene Analysis

Lecture Outline

• Title: Video Tracking and Crowd-Scene Analysis
• Part 1: Tracking Foundations
• Appearance-based vs tracking-by-detection
• Single target tracking
  • Recursive filtering
  • Dynamic programming
• Multiple target tracking
  • Filtering + data association
  • Multi-frame formulations
• Part 2: Analyzing Crowd Behavior
  • Detection and counting
  • Crowd flow analysis
  • Social force models
  • Detecting small groups

Lecture Notes (PDF Slides)

• Part 1: Tracking Foundations
• Part 2: Analyzing Crowd Behavior

Background Papers

• Recursive Filtering and Data Association

  • An MCMC-based Particle Filter for Tracking Multiple Interacting Targets
  • Tracking Large Variable Numbers of Objects in Clutter

• Dynamic Programming for Tracking

  • GraphTrack: Fast and Globally Optimal Tracking in Videos

• Multi-frame, Multi-target Formulations

  • Global Data Association for Multi-Object Tracking Using Network Flows
  • Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects
  • Multitarget Data Association with Higher-Order Motion Models

• Crowd Detection and Counting

  • Crowd Detection from Still Images
  • Counting Crowded Moving Objects

• Crowd Flow Analysis

  • Floor Fields for Tracking in High Density Crowd Scenes
  • Tracking Pedestrians using Local Spatio-temporal Motion Patterns in Extremely Crowded Scenes
  • Data-driven Crowd Analysis in Videos

• Social Force Models

  • Social Force Model for Pedestrian Dynamics
  • You’ll Never Walk Alone: Modeling Social Behavior for Multi-target Tracking

• Detecting Small Groups

  • Vision-based Analysis of Small Groups in Pedestrian Crowds

My VLPR Lectures from Prior Years (PDF Slides)

• VLPR 2009, Beijing, China
• VLPR 2010, Xi'an, China