Human detection in a challenging situation

Authors:
Ya-Li Hou;Grantham K. H. Pang
Affiliations:
Industrial Automation Research Laboratory, Department of Electrical and Electronic Engineering, The University of Hong Kong;Industrial Automation Research Laboratory, Department of Electrical and Electronic Engineering, The University of Hong Kong
Venue:
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Year:
2009

Citing 9
Cited 0

Using Adaptive Tracking to Classify and Monitor Activities in a Site

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Tracking Multiple Humans in Complex Situations

IEEE Transactions on Pattern Analysis and Machine Intelligence
Histograms of Oriented Gradients for Human Detection

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Simultaneous Estimation of Segmentation and Shape

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Counting Crowded Moving Objects

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Unsupervised Bayesian Detection of Independent Motion in Crowds

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part Detectors

International Journal of Computer Vision
Segmentation and Tracking of Multiple Humans in Crowded Environments

IEEE Transactions on Pattern Analysis and Machine Intelligence
Estimation of number of people in crowded scenes using perspective transformation

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

Quantified Score

Hi-index	0.01

Visualization

Abstract

Although there have been a lot of studies on human detection in recent years, most of them have some particular requirements. However, some videos may have complicated scenes with low resolution and include both moving and standing people. The paper aims for individual detection under the challenging situation. An EM (Expectation-Maximum) based method has been developed to detect individuals in a common outdoor scenario. A new cluster model is employed in the method for human detection. The method can work well even for low-resolution images. Both moving and standing people can be detected as long as they show some occasional movements, which is satisfied in most cases. Some promising results have been presented and analyzed in a scene with around 100 people.