In the process of crowd movement,pedestrians are often affected by their neighbors.In order to describe the consistency of adjacent individuals and collectivity of a group,this paper learns from the rules of the flock...In the process of crowd movement,pedestrians are often affected by their neighbors.In order to describe the consistency of adjacent individuals and collectivity of a group,this paper learns from the rules of the flocking behavior,such as segregation,alignment and cohesion,and proposes a method for crowd motion simulation based on the Boids model and social force model.Firstly,the perception area of individuals is divided into zone of segregation,alignment and cohesion.Secondly,the interactive force among individuals is calculated based upon the zone information,velocity vector and the group information.The interactive force among individuals is the synthesis of three forces:the repulsion force to avoid collisions,the alignment force to keep consistent with the velocity direction,and the attractive force to get close to the members of group.In segregation and alignment areas,the repulsion force and alignment force among pedestrians are limited by visual field factors.Finally,the interactive force among individuals,the driving force of destination and the repulsion force of obstacles work together to drive the behavior of crowd motion.The simulation results show that the proposed method can not only effectively simulate the interactive behavior between adjacent individuals but also the collective behavior of group.展开更多
In this paper, we propose a novel method for anomalous crowd behaviour detection and localization with divergent centers in intelligent video sequence through multiple SVM (support vector machines) based appearance mo...In this paper, we propose a novel method for anomalous crowd behaviour detection and localization with divergent centers in intelligent video sequence through multiple SVM (support vector machines) based appearance model. In multi-dimension SVM crowd detection, many features are available to track the object robustly with three main features which include 1) identification of an object by gray scale value, 2) histogram of oriented gradients (HOG) and 3) local binary pattern (LBP). We propose two more powerful features namely gray level co-occurrence matrix (GLCM) and Gaber feature for more accurate and authenticate tracking result. To combine and process the corresponding SVMs obtained from each features, a new collaborative strategy is developed on the basis of the confidence distribution of the video samples which are weighted by entropy method. We have adopted subspace evolution strategy for reconstructing the image of the object by constructing an update model. Also, we determine reconstruction error from the samples and again automatically build an update model for the target which is tracked in the video sequences. Considering the movement of the targeted object, occlusion problem is considered and overcome by constructing a collaborative model from that of appearance model and update model. Also if update model is of discriminative model type, binary classification problem is taken into account and overcome by collaborative model. We run the multi-view SVM tracking method in real time with subspace evolution strategy to track and detect the moving objects in the crowded scene accurately. As shown in the result part, our method also overcomes the occlusion problem that occurs frequently while objects under rotation and illumination change due to different environmental conditions.展开更多
文摘In the process of crowd movement,pedestrians are often affected by their neighbors.In order to describe the consistency of adjacent individuals and collectivity of a group,this paper learns from the rules of the flocking behavior,such as segregation,alignment and cohesion,and proposes a method for crowd motion simulation based on the Boids model and social force model.Firstly,the perception area of individuals is divided into zone of segregation,alignment and cohesion.Secondly,the interactive force among individuals is calculated based upon the zone information,velocity vector and the group information.The interactive force among individuals is the synthesis of three forces:the repulsion force to avoid collisions,the alignment force to keep consistent with the velocity direction,and the attractive force to get close to the members of group.In segregation and alignment areas,the repulsion force and alignment force among pedestrians are limited by visual field factors.Finally,the interactive force among individuals,the driving force of destination and the repulsion force of obstacles work together to drive the behavior of crowd motion.The simulation results show that the proposed method can not only effectively simulate the interactive behavior between adjacent individuals but also the collective behavior of group.
文摘In this paper, we propose a novel method for anomalous crowd behaviour detection and localization with divergent centers in intelligent video sequence through multiple SVM (support vector machines) based appearance model. In multi-dimension SVM crowd detection, many features are available to track the object robustly with three main features which include 1) identification of an object by gray scale value, 2) histogram of oriented gradients (HOG) and 3) local binary pattern (LBP). We propose two more powerful features namely gray level co-occurrence matrix (GLCM) and Gaber feature for more accurate and authenticate tracking result. To combine and process the corresponding SVMs obtained from each features, a new collaborative strategy is developed on the basis of the confidence distribution of the video samples which are weighted by entropy method. We have adopted subspace evolution strategy for reconstructing the image of the object by constructing an update model. Also, we determine reconstruction error from the samples and again automatically build an update model for the target which is tracked in the video sequences. Considering the movement of the targeted object, occlusion problem is considered and overcome by constructing a collaborative model from that of appearance model and update model. Also if update model is of discriminative model type, binary classification problem is taken into account and overcome by collaborative model. We run the multi-view SVM tracking method in real time with subspace evolution strategy to track and detect the moving objects in the crowded scene accurately. As shown in the result part, our method also overcomes the occlusion problem that occurs frequently while objects under rotation and illumination change due to different environmental conditions.
