Interactive event detection in crowd scenes

Authors:
Lei Qin;Zhongwei Cheng;Qingming Huang;Junbiao Pang
Affiliations:
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China;Graduate University of Chinese Academy of Sciences, Beijing, China;Graduate University of Chinese Academy of Sciences, Beijing, China;Beijing Univ. of Tech., China
Venue:
Proceedings of the 4th International Conference on Internet Multimedia Computing and Service
Year:
2012

Citing 8
Cited 0

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
On Space-Time Interest Points

International Journal of Computer Vision
Behavior recognition via sparse spatio-temporal features

ICCCN '05 Proceedings of the 14th International Conference on Computer Communications and Networks
Actions as Space-Time Shapes

IEEE Transactions on Pattern Analysis and Machine Intelligence
Query-based retrieval of complex activities using "strings of motion-words"

WMVC'09 Proceedings of the 2009 international conference on Motion and video computing
Group Activity Recognition by Gaussian Processes Estimation

ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
Action Recognition Using Spatial-Temporal Context

ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
Human activity analysis: A review

ACM Computing Surveys (CSUR)

Quantified Score

Hi-index	0.00

Visualization

Abstract

As an important aspect in video content analysis, event detection is still an open problem. In particular, the study on detecting interactive events in crowd scenes is still limited. In this paper, we investigate detecting interactive events between persons, e.g. PeopleMeet, PeopleSplitUp and Embrace in complex scenes using a sequence learning based approach. By sequence learning, the spatial-temporal context information is introduced in the learning stage. Experiments have been performed over TRECVid Event Detection 2010 dataset, which contains totally 144 hours surveillance video of London Gatwick airport. According to the TRECVid-ED 2010 formal evaluation, our approach obtains promising results, with the top performance (NDCR) for PeopleMeet and PeopleSplit-Up, and second-best performance (NDCR) for Embrace.