Projects > Modeling Spatial Relationships in Human and Object Interactions for Human Activity Understanding in Video Surveillance

Modeling Spatial Relationships in Human and Object Interactions for Human Activity Understanding in Video Surveillance


Project Team: Prof. YUEN, Pong Chi

Project description
Human action recognition plays an important role in video and image understanding and analysis. It can be applied to Intelligent Video Surveillance systems to analyze surveillance data automatically. With the rapid growth in the use of CCTV cameras for video surveillance, the amount of surveillance data to be processed increases significantly. Such a huge demand in automation makes human action recognition became more and more important in our society.

While human activity understanding has been an active research area in the past decades, most of the existing approaches focus on analyzing the movement of the human subject being tracked. On the other hand, less attention has been paid on extracting context in human-object interactions to provide addition information for analysis. This project will focus on developing a new representation model in this challenging research topic. In particular, we will develop a view-insensitive spatial relation based model to represent human-object interactions. Preliminary results show that the prototype of our new representation is robust in different situations. By using our method, the accuracy of video and image understanding and analysis can be improved.
Examples of human-object interactions. Images are obtained from the POETICON enacted scenario corpus
(http://poeticoncorpus.kyb.mpg.de/).
Funded projects
  • "A Multi-resolution Spatial Relation based Representation for Close Character Interactions Analysis and Synthesis", PI, RGC General Research Fund (RGC/HKBU210813), 2013-2015
  • "Modelling Human-Object Interactions based on Spatial Relations for Robust Action Recognition", PI, National Natural Science Foundation of China Young Scientists Fund (Project No.: 61302176), 2014-2016
Relevant publications
  1. Edmond S. L. Ho, Hubert P. H. Shum, Yiu-ming Cheung, P. C. Yuen. "Topology Aware Data-Driven Inverse Kinematics". To appear in Computer Graphics Forum (Proceedings of Pacific Graphics 2013), Oct 2013.
  2. Edmond S. L. Ho, Jacky C. P. Chan, Taku Komura, Howard Leung. "Interactive Partner Control in Close Interactions for Real-time Applications". ACM Transactions on Multimedia Computing, Communications and Applications, vol 9(3), June 2013.
  3. Edmond S.L. Ho, Taku Komura, Chiew-Lan Tai. "Spatial Relationship Preserving Character Motion Adaptation". ACM Transactions on Graphics (Proceedings of SIGGRAPH 2010), vol. 29(4), July 2010.
  4. Edmond S. L. Ho and Taku Komura. "Indexing and Retrieving Motions of Characters in Close Contact". IEEE Transactions on Visualization and Computer Graphics, vol. 15, issue 3, May/June 2009.
  5. Edmond S. L. Ho and Taku Komura. "Character Motion Synthesis by Topology Coordinates". Computer Graphics Forum (Proceedings of Eurographics 2009), vol. 28, issue 2, Mar 2009.


For further information on this project, please contact Prof. YUEN, Pong Chi.
Top