Thursday, July 20, 2017

 

The goal of people counting is to estimate the number of people or the density of crowds in a monitored environment. Both the long-term and short-term statistics of people counts of an environment provide useful information for strategy planning or event detection. However, detecting or estimating the density of crowds is always a challenging task due to some potential difficulties, such as partial occlusions, low-quality images, clutter backgrounds, and so on. To this end, we focus on the framework where multiple cameras with different angles of view are available, and consider the visual cues captured by each camera as a knowledge source, carrying out cross-camera knowledge transfer to alleviate the difficulties.

 

Single-Camera People Counting

  • Cross-camera people counting
    • Applicable to various environments
    • Online training data acquisition and camera perspective estimation
  • Occlusion handling: Coupled Gaussian processes
    • First-pass Gaussian processes: Visible part
    • Second-pass Gaussian processes: Occluded part

 

 

Why Predict Conflict Works

  • An example: prediction conflict between horizontal and vertical gradients for occlusion handling

    • Legend
      • ---- Ground truth
      • ---- Prediction by the feature of horizontal gradients
      • ---- Prediction by the feature of vertical gradients

 

 

Blob Representation

  • We focus on foreground objects (pedestrians) in images
  • Background subtraction
  • Grouping spatially connected pixels

 

 

People Counting with Multiple Cameras

  • Why multiple cameras?
    • Complementary information
    • Dealing with resolution issues, occlusions, ...
  • Our approach
    • Ground plane matching + Visual knowledge transfer

 

 

Why Bob Matching?

  • Find the same groups of pedestrians across cameras
    • Synchronized frames
      • The numbers of people are not always equal, particularly when FOVs are quite different
    • We work on corresponding blob sets: blob clusters

 

 

Observation

  • Approximating the people counts in an image in two parts
    • Regular part: intra-camera visual features
    • Residual part: inter-camera visual knowledge
  • Formulate it as a transfer learning problem

 

 

Demo

Single-view Demo

Multi-view Demo

 

Publications

 

Visual Knowledge Transfer among Multiple Cameras for People Counting with Occlusion Handling

Ming-Fang Weng, Yen-Yu Lin, Nick C. Tang, and Hong-Yuan Mark Liao


ACM International Conference on Multimedia (MM), October 2012, (full paper)


Paper

 

Cross Camera People Counting with Perspective Estimation and Occlusion Handling

Tsung-Yi Lin, Yen-Yu Lin, Ming-Fang Weng, Yu-Chiang Wang, Yu-Feng Hsu, and Hong-Yuan Mark Liao


IEEE International Workshop on Information Forensics and Security (WIFS), November 2011


Paper