|
|
- 2018
基于因果分析的群体行为识别
|
Abstract:
该文提出一种基于因果分析的群体行为识别方法，利用Grange因果检验分析个体行为间的因果关系，在此基础上，结合个体间的因果关系、空间位置关系和视觉注意力范围，利用基于主集的聚类法检测行为群体。为了有效地表示群体行为，用方向梯度直方图和光流直方图描述个体行为，用因果特征描述个体间的交互行为。采用稀疏表示进行群体行为识别，在公共数据库BEHAVE和collective activity上对该方法进行验证，并与其他方法进行对比试验，结果表明了该方法的有效性。
| [1] | NI B, YAN S, KASSIM A. Recognizing human group activities with localized causalities[C]//IEEE Conference on Computer Vision and Pattern Recognition. Miam:IEEE, 2009:1470-1477. |
| [2] | CHENG Z, QIN L, HUANG Q. Group activity recognition by gaussian processes estimation[C]//IEEE International Conference on Pattern Recognition. Istanbul:IEEE, 2010. |
| [3] | BULO S R, BOMZE I M. Infection and immunization:a new class of evolutionary game dynamics[J]. GAMES and Economic Behavior, 2011, 71(1):193-211. |
| [4] | MILAN A, SCHINDLER K, ROTH S. Multi-target tracking by discrete-continuous energy minimization[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(10):2054-2068. |
| [5] | ZHANG Y S, GUO Y. 2D OMP algorithm for space-time parameters estimation of moving targets[J]. Electronics Letters, 2015, 51(22):1809-1820. |
| [6] | MUKHERJEE S, BASU R, SEELAMANTULA C S. 1-K-SVD:a robust dictionary learning algorithm with simultaneous update[J]. Signal Processing, 2016, 123:42-52. |
| [7] | KANEKO T, SHIMOSAKA M, ODASHIMA S. A fully connected model for consistent collective activity recognition in videos[J]. Pattern Recognition Letters, 2014, 43(1):109-118. |
| [8] | AMER M R, TODOROVIC S. A chains model for localizing participantsof group activities in videos[C]//IEEE International Conference on Computer Vision. Barcelona:IEEE, 2011:786-793. |
| [9] | ZHU G, YAN S, HAN T, et al. Generative group activity analysis with quaternion descriptor[J]. Adv Multimed Model, 2011, 6524:1-11. |
| [10] | ZHOU Y, HUANG T S, NI B, et al. Recognizing pair-activities by causality analysis[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(5):1-20. |
| [11] | YIN Y, YANG G, XU J. Small group human activity recognition[C]//IEEE International Conference on Image Processing. Lake Buena Vista:IEEE, 2012:2709-2712. |
| [12] | JU J, YANG C, SCHERER S. Recognition of human group activity for video analytics[C]//Pacific-Rim Conference on Multimedia. Gwangju:IEEE, 2015. |
| [13] | KIM Y J, CHO N G, LEE S W. Group activity recognition with group interaction zone[C]//International Conference on Pattern Recognition. Stockholm:IEEE, 2014:3517-3521. |
| [14] | STEPHENS K, BORS A G. Group activity recognition on outdoor scenes[C]//IEEE International Conference on Advanced Video and Signal Based Surveillance. Colorado Springs:IEEE, 2016:59-65. |
| [15] | ZHANG C, YANG X, LIN W, et al. Recognizing human group behaviors with multi-group causalities[C]//International Conference on Web Intelligence and Intelligent Agent Technology Workshops. Macau:IEEE, 2012:44-48. |
| [16] | CHO N G, KIM Y J, PARK U. Group activity recognition with group interaction zone based on relative distance between human objects[J]. International Journal Pattern Recognition and Artificial Intelligence,2015, 29(5):1-10. |
| [17] | TRAN K N, YAN Xu, KAKADIARIS I A, et al. A hybrid approach for individual and group activity analysis in crowded scene[J]. Communications in Computer and Information Science, 2016, 598:189-204. |
| [18] | GRANGER C. Investigating causal relations by econometric models and cross-spectral methods[J]. Econometrica, 1969, 37(3):424-438. |
| [19] | PAVAN M, PELILLO M. Dominant sets and pairwise clustering[J]. IEEE Transactions on PAMI, 2007, 29(1):167-172. |
