A Viewpoint Invariant Approach for Crowd Counting

Authors:
Dan Kong;Doug Gray;Hai Tao
Affiliations:
University of California, Santa Cruz;University of California, Santa Cruz;University of California, Santa Cruz
Venue:
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Year:
2006

Citing 0
Cited 10

Crowd analysis: a survey

Machine Vision and Applications
Detection and Segmentation of Multiple, Partially Occluded Objects by Grouping, Merging, Assigning Part Detection Responses

International Journal of Computer Vision
Counting People in Groups

AVSS '09 Proceedings of the 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance
Simple camera calibration from a single image using five points on two orthogonal 1-D objects

IEEE Transactions on Image Processing
A method for counting moving people in video surveillance videos

EURASIP Journal on Advances in Signal Processing - Special issue on video analysis for human behavior understanding
Semi-supervised Elastic net for pedestrian counting

Pattern Recognition
A self-trainable system for moving people counting by scene partitioning

ICIAR'11 Proceedings of the 8th international conference on Image analysis and recognition - Volume Part II
An energy model approach to people counting for abnormal crowd behavior detection

Neurocomputing
People counting by learning their appearance in a multi-view camera environment

Pattern Recognition Letters
Counting crowd flow based on feature points

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a viewpoint invariant learningbased method for counting people in crowds from a single camera. Our method takes into account feature normalization to deal with perspective projection and different camera orientation. The training features include edge orientation and blob size histograms resulted from edge detection and background subtraction. A density map that measures the relative size of individuals and a global scale measuring camera orientation are estimated and used for feature normalization. The relationship between the feature histograms and the number of pedestrians in the crowds is learned from labeled training data. Experimental results from different sites with different camera orientation demonstrate the performance and the potential of our method.