Yunpeng Wu
ABSTRACT
Detecting coherent motion is significant for analysing the crowd motion in video applications. In this study, we propose the Collective Density Clustering(CDC) approach to recognize both local and global coherent motion having arbitrary shapes and varying densities. Firstly, the collective density is defined to reveal the underlying patterns with varying levels of density. Based on collective density, the collective clustering algorithm is further presented to recognize the local consistency, where density-based clustering is more adaptive to recognize clusters with arbitrary shapes. This algorithm has salient properties including single step of clustering process, automatical decision of clustering number and accurate identification of outliers. Finally, the collective merging algorithm is introduced to fully characterize the global consistency. Experiments on diverse crowd scenes, including pedestrians, traffic and bacterial colony, demonstrate the effectiveness for coherent motion detection. The comparisons show that our approach outperforms state-of-the-art coherent detection techniques.
- S. Ali and M. Shah. A lagrangian particle dynamics approach for crowd flow segmentation and stability analysis. IEEE Conference on Computer Vision and Pattern Recognition, pages 1--6, 2007.Google Scholar
Cross Ref
- S. Ali and M. Shah. Floor fields for tracking in high density crowd scenes. European Conference on Computer Vision, pages 1--14, 2008. Google ScholarDigital Library
- T. Brox and J. Malik. Object segmentation by long term analysis of point trajectories. European Conference on Computer Vision, pages 282--295, 2010. Google ScholarDigital Library
- W. Choi and S. Savarese. Understanding collective activities of people from videos. IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 1242--1257, 2013. Google ScholarDigital Library
- W. Choi, K. Shahid, and S. Savarese. Learning context for collective activity recognition. IEEE Conference on Computer Vision and Pattern Recognition, pages 3273--3280, 2011. Google ScholarDigital Library
- I. Couzin. Collective minds. Nature, 445(7129):715--715, 2007.Google ScholarCross Ref
- M. Ester, H.-P. Kriegel, J. Sander, and X. Xu. A density-based algorithm for discovering clusters in large spatial databases with noise. International Conference on Knowledge Discovery and Data Mining, 96:226--231, 1996.Google ScholarDigital Library
- W. Ge, R. T. Collins, and R. B. Ruback. Vision-based analysis of small groups in pedestrian crowds. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(5):1003--1016, 2012. Google ScholarDigital Library
- M. Hu, S. Ali, and M. Shah. Learning motion patterns in crowded scenes using motion flow field. International Conference on Pattern Recognition, pages 1--5, 2008.Google ScholarCross Ref
- L. Kratz and K. Nishino. Going with the flow: pedestrian efficiency in crowded scenes. European Conference on Computer Vision, pages 558--572, 2012. Google ScholarDigital Library
- L. Kratz and K. Nishino. Tracking pedestrians using local spatio-temporal motion patterns in extremely crowded scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(5):987--1002, 2012. Google ScholarDigital Library
- V. Mahadevan, W. Li, V. Bhalodia, and N. Vasconcelos. Anomaly detection in crowded scenes. IEEE Conference on Computer Vision and Pattern Recognition, pages 1975--1981, 2010.Google ScholarCross Ref
- R. Mehran, B. E. Moore, and M. Shah. A streakline representation of flow in crowded scenes. European Conference on Computer Vision, pages 439--452, 2010. Google ScholarDigital Library
- R. Mehran, A. Oyama, and M. Shah. Abnormal crowd behavior detection using social force model. IEEE Conference on Computer Vision and Pattern Recognition, pages 935--942, 2009.Google ScholarCross Ref
- V. Rabaud and S. Belongie. Counting crowded moving objects. IEEE Conference on Computer Vision and Pattern Recognition, 1:705--711, 2006. Google ScholarDigital Library
- A. Rodriguez and A. Laio. Clustering by fast search and find of density peaks. Science, 344(6191):1492--1496, 2014.Google ScholarCross Ref
- X. Sun, H. Yao, R. Ji, X. Liu, and P. Xu. Unsupervised fast anomaly detection in crowds. ACM international conference on Multimedia, pages 1469--1472, 2011. Google ScholarDigital Library
- X. Tang, H. Zhang, B. Zhou, and X. Wang. Measuring crowd collectiveness. IEEE Transactions on Pattern Analysis and Machine Intelligence, page 1, 2014. Google ScholarDigital Library
- T. Vicsek, A. Czirók, E. Ben-Jacob, I. Cohen, and O. Shochet. Novel type of phase transition in a system of self-driven particles. Physical Review Letters, 75(6):1226, 1995.Google ScholarCross Ref
- T. Vicsek and A. Zafeiris. Collective motion. Physics Reports, 517(3):71--140, 2012.Google ScholarCross Ref
- W. Wang, W. Lin, Y. Chen, J. Wu, J. Wang, and B. Sheng. Finding coherent motions and semantic regions in crowd scenes: A diffusion and clustering approach. European Conference on Computer Vision, pages 756--771, 2014.Google ScholarCross Ref
- S. Wu and H. San Wong. Crowd motion partitioning in a scattered motion field. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 42(5):1443--1454, 2012. Google ScholarDigital Library
- C. Zhang, X. Yang, J. Zhu, and W. Lin. Parsing collective behaviors by hierarchical model with varying structure. ACM international conference on Multimedia, pages 1085--1088, 2012. Google ScholarDigital Library
- H. P. Zhang, A. Be'er, E.-L. Florin, and H. L. Swinney. Collective motion and density fluctuations in bacterial colonies. Proceedings of the National Academy of Sciences, 107(31):13626--13630, 2010.Google ScholarCross Ref
- B. Zhou, X. Tang, and X. Wang. Coherent filtering: detecting coherent motions from crowd clutters. European Conference on Computer Vision, pages 857--871, 2012. Google ScholarDigital Library
- B. Zhou, X. Tang, and X. Wang. Measuring crowd collectiveness. IEEE Conference on Computer Vision and Pattern Recognition, pages 3049--3056, 2013. Google ScholarDigital Library
Index Terms
- Coherent Motion Detection with Collective Density Clustering
Recommendations
Density-Based Manifold Collective Clustering for Coherent Motion Detection
ICMVA '18: Proceedings of the International Conference on Machine Vision and ApplicationsDetecting coherent motion remains a challenging problem with important applications for the video surveillance and understanding of crowds. In this study, we propose the Density-based Manifold Collective Clustering approach to recognize both local and ...
Unifying Density-Based Clustering and Outlier Detection
WKDD '09: Proceedings of the 2009 Second International Workshop on Knowledge Discovery and Data MiningDensity-based clustering and density-based outlier detection have been extensively studied in the data mining. However, Existing works address density-based clustering or density-based outlier detection solely. But for many scenarios, it is more ...
On cluster tree for nested and multi-density data clustering
Clustering is one of the important data mining tasks. Nested clusters or clusters of multi-density are very prevalent in data sets. In this paper, we develop a hierarchical clustering approach-a cluster tree to determine such cluster structure and ...
Comments