Most research on anomaly detection has focused on event that is different from its spatial-temporal neighboring events.It is still a significant challenge to detect anomalies that involve multiple normal events intera...Most research on anomaly detection has focused on event that is different from its spatial-temporal neighboring events.It is still a significant challenge to detect anomalies that involve multiple normal events interacting in an unusual pattern.In this work,a novel unsupervised method based on sparse topic model was proposed to capture motion patterns and detect anomalies in traffic surveillance.scale-invariant feature transform(SIFT)flow was used to improve the dense trajectory in order to extract interest points and the corresponding descriptors with less interference.For the purpose of strengthening the relationship of interest points on the same trajectory,the fisher kernel method was applied to obtain the representation of trajectory which was quantized into visual word.Then the sparse topic model was proposed to explore the latent motion patterns and achieve a sparse representation for the video scene.Finally,two anomaly detection algorithms were compared based on video clip detection and visual word analysis respectively.Experiments were conducted on QMUL Junction dataset and AVSS dataset.The results demonstrated the superior efficiency of the proposed method.展开更多
The objective of this work is to develop a novel feature for traffic flow models, when traffic queues on two-way arterials periodically extend until then they block an upstream signal in oversaturated conditions. The ...The objective of this work is to develop a novel feature for traffic flow models, when traffic queues on two-way arterials periodically extend until then they block an upstream signal in oversaturated conditions. The new model, proposed as conditional cell transmission model （CCTM） has been developed with two improvements. First, cell transmission model （CTM） is expanded for two-way arterials by taking account of all diverging and merging activities at intersections. Second, a conditional cell is added to simulate periodic spillback and blockages at an intersection. The results of experiments for a multilane, two-way, three-signal sample network demonstrate that CCTM can accommodate various traffic demands and accurate representation of blockages at intersections. The delay of left turns is underestimated by 40 % in moderate conditions and by 58% in oversamrated condition when using the CTM rather than CCTM. Finally, the consistency between HCS 2000 and CCTM shows that CCTM is a reliable methodology of modeling traffic flow in oversaturated condition.展开更多
基金Project(50808025)supported by the National Natural Science Foundation of ChinaProject(20090162110057)supported by the Doctoral Fund of Ministry of Education,China
文摘Most research on anomaly detection has focused on event that is different from its spatial-temporal neighboring events.It is still a significant challenge to detect anomalies that involve multiple normal events interacting in an unusual pattern.In this work,a novel unsupervised method based on sparse topic model was proposed to capture motion patterns and detect anomalies in traffic surveillance.scale-invariant feature transform(SIFT)flow was used to improve the dense trajectory in order to extract interest points and the corresponding descriptors with less interference.For the purpose of strengthening the relationship of interest points on the same trajectory,the fisher kernel method was applied to obtain the representation of trajectory which was quantized into visual word.Then the sparse topic model was proposed to explore the latent motion patterns and achieve a sparse representation for the video scene.Finally,two anomaly detection algorithms were compared based on video clip detection and visual word analysis respectively.Experiments were conducted on QMUL Junction dataset and AVSS dataset.The results demonstrated the superior efficiency of the proposed method.
基金Project(51108343) supported by the National Natural Science Foundation of ChinaProject(06121) supported by University of Transportation Center for Alabama,USA
文摘The objective of this work is to develop a novel feature for traffic flow models, when traffic queues on two-way arterials periodically extend until then they block an upstream signal in oversaturated conditions. The new model, proposed as conditional cell transmission model （CCTM） has been developed with two improvements. First, cell transmission model （CTM） is expanded for two-way arterials by taking account of all diverging and merging activities at intersections. Second, a conditional cell is added to simulate periodic spillback and blockages at an intersection. The results of experiments for a multilane, two-way, three-signal sample network demonstrate that CCTM can accommodate various traffic demands and accurate representation of blockages at intersections. The delay of left turns is underestimated by 40 % in moderate conditions and by 58% in oversamrated condition when using the CTM rather than CCTM. Finally, the consistency between HCS 2000 and CCTM shows that CCTM is a reliable methodology of modeling traffic flow in oversaturated condition.
