Title :
Learning multi-modal densities on Discriminative Temporal Interaction Manifold for group activity recognition
Author :
Ruonan Li ; Chellappa, Rama ; Zhou, S. Kevin
Author_Institution :
Center for Autom. Res., Univ. of Maryland, College Park, MD, USA
Abstract :
While video-based activity analysis and recognition has received much attention, existing body of work mostly deals with single object/person case. Coordinated multi-object activities, or group activities, present in a variety of applications such as surveillance, sports, and biological monitoring records, etc., are the main focus of this paper. Unlike earlier attempts which model the complex spatial temporal constraints among multiple objects with a parametric Bayesian network, we propose a Discriminative Temporal Interaction Manifold (DTIM) framework as a data-driven strategy to characterize the group motion pattern without employing specific domain knowledge. In particular, we establish probability densities on the DTIM, whose element, the discriminative temporal interaction matrix, compactly describes the coordination and interaction among multiple objects in a group activity. For each class of group activity we learn a multi-modal density function on the DTIM. A Maximum a Posteriori (MAP) classifier on the manifold is then designed for recognizing new activities. Experiments on football play recognition demonstrate the effectiveness of the approach.
Keywords :
belief networks; image classification; image motion analysis; pattern recognition equipment; video signal processing; complex spatial temporal constraints; data-driven strategy; discriminative temporal interaction manifold; discriminative temporal interaction matrix; football play recognition; group activity recognition; maximum a posteriori classifier; multimodal density function; multiobject activities; parametric Bayesian network; video-based activity analysis; Automation; Bayesian methods; Biological system modeling; Educational institutions; Monitoring; Pattern recognition; Surveillance; Tensile stress; Tracking; Videos;
Conference_Titel :
Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on
Conference_Location :
Miami, FL
Print_ISBN :
978-1-4244-3992-8
DOI :
10.1109/CVPR.2009.5206676