L0 Regularized Stationary Time Estimation for Crowd Group Analysis
Authors:
- Shuai YiSYShuai Yi
- Xiaogang WangXWXiaogang Wang
- Cewu LuCLCewu Lu
- Jiaya JiaJJJiaya Jia
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 2219-2226
Abstract
We tackle stationary crowd analysis in this paper, which is similarly important as modeling mobile groups in crowd scenes and finds many applications in surveillance. Our key contribution is to propose a robust algorithm of estimating how long a foreground pixel becomes stationary. It is much more challenging than only subtracting background because failure at a single frame due to local movement of objects, lighting variation, and occlusion could lead to large errors on stationary time estimation. To accomplish decent results, sparse constraints along spatial and temporal dimensions are jointly added by mixed partials to shape a 3D stationary time map. It is formulated as a L0 optimization problem. Besides background subtraction, it distinguishes among different foreground objects, which are close or overlapped in the spatio-temporal space by using a locally shared foreground codebook. The proposed technologies are used to detect four types of stationary group activities and analyze crowd scene structures. We provide the first public benchmark dataset for stationary time estimation and stationary group analysis.Keywords
This publication has 28 references indexed in Scilit:
- Incremental Activity Modeling in Multiple Disjoint CamerasIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Discriminative Latent Models for Recognizing Contextual Group ActivitiesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Data-driven crowd analysis in videos2011
- Anomaly detection in crowded scenes2010
- The Walking Behaviour of Pedestrian Social Groups and Its Impact on Crowd DynamicsPLOS ONE, 2010
- You'll never walk alone: Modeling social behavior for multi-target tracking2009
- Learning pedestrian dynamics from the real world2009
- Abnormal crowd behavior detection using social force model2009
- Real-time foreground–background segmentation using codebook modelReal-Time Imaging, 2005
- Improved adaptive Gaussian mixture model for background subtraction2004