A Framework for High-Level Feedback to Adaptive, Per-Pixel, Mixture-of-Gaussian Background Models
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Toward a sentient environment: real-time wide area multiple human tracking with identities
Machine Vision and Applications
A People Counting System Based on Dense and Close Stereovision
ICISP '08 Proceedings of the 3rd international conference on Image and Signal Processing
Hybrid model for people counting in a video stream
ICCOMP'08 Proceedings of the 12th WSEAS international conference on Computers
People detection and tracking with multiple stereo cameras using particle filters
Journal of Visual Communication and Image Representation
Robust pedestrian detection and tracking in crowded scenes
Image and Vision Computing
Multi-sensor human tracking with the Bayesian occupancy filter
DSP'09 Proceedings of the 16th international conference on Digital Signal Processing
A case study in distributed deployment of embedded software for camera networks
Proceedings of the Conference on Design, Automation and Test in Europe
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Multiple-person tracker with a fixed slanting stereo camera
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Multiple-Person tracking using a plan-view map with error estimation
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I
Shape from pairwise silhouettes for plan-view map generation
Image and Vision Computing
People counting by learning their appearance in a multi-view camera environment
Pattern Recognition Letters
Hi-index | 0.00 |
Stores and shopping malls would like to keep track of shopper volume by employing automatic techniques for counting shoppers. Existing approaches instrument doors with infrared beams and count beam interruptions, but this approach cannot resolve groups of people well. We are applying a vision-based approach that detects and tracks people from a stereo camera mounted above a door and pointing down. After applying real-time stereo vision and 3D image reconstruction, the system segments the scene by selecting stereo pixels falling inside a 3D volume of interest, which is placed to capture the heads and torsos of adult shoppers. The main novelties of our approach include (1) remapping the stereo disparities to an orthographic "occupancy map", which simplifies person modeling, and (2) tracking people using a Gaussian mixture model. On a test set of 900 enter/exit events in four hours of video, our system has achieved a net counting error rate of just 1.4%.