Multiple camera people detection and tracking using support integration

Authors:
Thiago T. Santos;Carlos H. Morimoto
Affiliations:
Institute of Mathematics and Statistics, University of São Paulo, Rua do Matão 1010, 05508-090 São Paulo, Brazil;Institute of Mathematics and Statistics, University of São Paulo, Rua do Matão 1010, 05508-090 São Paulo, Brazil
Venue:
Pattern Recognition Letters
Year:
2011

Citing 8
Cited 3

Single View Metrology

International Journal of Computer Vision
Mean Shift, Mode Seeking, and Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiple View Geometry in Computer Vision

Multiple View Geometry in Computer Vision
Principal Axis-Based Correspondence between Multiple Cameras for People Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multicamera People Tracking with a Probabilistic Occupancy Map

IEEE Transactions on Pattern Analysis and Machine Intelligence
People Detection under Occlusion in Multiple Camera Views

SIBGRAPI '08 Proceedings of the 2008 XXI Brazilian Symposium on Computer Graphics and Image Processing
Tracking Multiple Occluding People by Localizing on Multiple Scene Planes

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multi-camera tracking and segmentation of occluded people on ground plane using search-guided particle filtering

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III

A novel multi-object detection method in complex scene using synthetic aperture imaging

Pattern Recognition
A comparative study on multi-person tracking using overlapping cameras

ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems
HEASK: Robust homography estimation based on appearance similarity and keypoint correspondences

Pattern Recognition

Quantified Score

Hi-index	0.10

Visualization

Abstract

This paper proposes a method to locate and track people by combining evidence from multiple cameras using the homography constraint. The proposed method use foreground pixels from simple background subtraction to compute evidence of the location of people on a reference ground plane. The algorithm computes the amount of support that basically corresponds to the ''foreground mass'' above each pixel. Therefore, pixels that correspond to ground points have more support. The support is normalized to compensate for perspective effects and accumulated on the reference plane for all camera views. The detection of people on the reference plane becomes a search for regions of local maxima in the accumulator. Many false positives are filtered by checking the visibility consistency of the detected candidates against all camera views. The remaining candidates are tracked using Kalman filters and appearance models. Experimental results using challenging data from PETS'06 show good performance of the method in the presence of severe occlusion. Ground truth data also confirms the robustness of the method.