Complex video event detection via pairwise fusion of trajectory and multi-label hypergraphs
- 184 Downloads
The video data is rich in motion event information. Detecting complex events and analyzing the inherent high-level semantics information have been a hot topic in video analysis and understanding. Detecting complex events in the video involves detecting multiple semantic concepts, describing features of multiple moving targets and discovering the relationship between low-level features and high-level semantic concepts. It can extract semantic concept patterns from various video features and original video data, thus bridging the semantic gap. Based on the hypergraph theory, this paper proposes to construct trajectory and multi-label hypergraphs considering the features of moving targets. The two hypergraphs are fused to detect complex events. The experimental results show that in comparison with other methods including ordinary graph based method and hypergraph based multi-label semi-supervised learning method, our method achieves better average precision and average recall when detecting complex events.
KeywordsHypergraph Trajectory Multi-label Pairwise fusion Spectral segmentation
This research has partially been supported by National Natural Science Foundation of China under Grant No. 41374129, 60673190 and 61203244, College Natural Science Research of Jiangsu Province under Grant No. 14KJB520008, Senior Technical Personnel of Scientific Research Fund of Jiangsu University under Grant No. 13JDG126.
- 2.Chen ZJ, Chen XJ, He H (2007) Moving object detection based on improved mixture gaussian models. J Image Graph 12(9):1585–1589Google Scholar
- 3.Chen DW, Liu R, Yuan ZM et al (2011) Research on multi-concept learning based on inter-concept relation. Comput Sci 38(4):244–248Google Scholar
- 9.Huang YC, Liu QS, Dimitris M (2009) Video object segmentation by hypergraph Cut[C]// Proceedings of Int’l Conf. Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, Miami, pp 1738–1735Google Scholar
- 11.Jiang Y, She QQ, Li M et al (2008) A transductive multilabel text categorization approach. J Comput Res Dev 45(11):1817–1822Google Scholar
- 14.Ke J, Zhan YZ, Chen XJ (2009) The research of detect moving target algorithm pseudo invariant line moment-based[C]// Proceedings of ICIC2009,LNCS 5754. Springer, Ulsan, pp 615–624Google Scholar
- 17.Lu H, Tan YP (2001) Sports video analysis and structuring [C]// Proceedings of the IEEE 4th Workshop on Multimedia Signal Processing. Institute of Electrical and Electronics Engineers Inc, Cannes, pp 45–50Google Scholar
- 18.Maggio E, Cavallaro A (2005) Hybrid particle filter and mean shift trajectoryer with adaptive transition model[C]//Proceedings of IEEE Signal Processing Society International Conference on Acoustics, Speech, and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers Inc, Philadelphia, pp 221–224. doi:10.1109/ICASSP.2005.1415381 Google Scholar