Limits...
Traffic Behavior Recognition Using the Pachinko Allocation Model.

Huynh-The T, Banos O, Le BV, Bui DM, Yoon Y, Lee S - Sensors (Basel) (2015)

Bottom Line: As a key innovation, PAM captures not only the correlation among the activities, but also among the behaviors based on the arbitrary directed acyclic graph (DAG).The SVM classifier is then utilized on top to train and recognize the traffic activity and behavior.The proposed model shows more flexibility and greater expressive power than the commonly-used latent Dirichlet allocation (LDA) approach, leading to a higher recognition accuracy in the behavior classification.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Engineering, Kyung Hee University, Suwon 446-701, Korea. thienht@oslab.khu.ac.kr.

ABSTRACT
CCTV-based behavior recognition systems have gained considerable attention in recent years in the transportation surveillance domain for identifying unusual patterns, such as traffic jams, accidents, dangerous driving and other abnormal behaviors. In this paper, a novel approach for traffic behavior modeling is presented for video-based road surveillance. The proposed system combines the pachinko allocation model (PAM) and support vector machine (SVM) for a hierarchical representation and identification of traffic behavior. A background subtraction technique using Gaussian mixture models (GMMs) and an object tracking mechanism based on Kalman filters are utilized to firstly construct the object trajectories. Then, the sparse features comprising the locations and directions of the moving objects are modeled by PAMinto traffic topics, namely activities and behaviors. As a key innovation, PAM captures not only the correlation among the activities, but also among the behaviors based on the arbitrary directed acyclic graph (DAG). The SVM classifier is then utilized on top to train and recognize the traffic activity and behavior. The proposed model shows more flexibility and greater expressive power than the commonly-used latent Dirichlet allocation (LDA) approach, leading to a higher recognition accuracy in the behavior classification.

No MeSH data available.


Related in: MedlinePlus

Confusion matrix of the SVM classifier for the mixing of all vertical and horizontal traffic with overall classification accuracy: (a) PAM 86.4%; (b) LDA 80.4%; and (c) MCTM 81.6%.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4541867&req=5

f6-sensors-15-16040: Confusion matrix of the SVM classifier for the mixing of all vertical and horizontal traffic with overall classification accuracy: (a) PAM 86.4%; (b) LDA 80.4%; and (c) MCTM 81.6%.

Mentions: In the experiments, the authors evaluated the performance in the classification accuracy of the proposed method for the detection of the vertical and horizontal traffic. Moreover, the method was compared with similar approaches using standard latent Dirichlet allocation (LDA) [36] and Markov clustering topic mode (MCTM) [30] for topic modeling. At first, the activity classification was applied to each separate dataset of the vertical and horizontal clips. The confusion matrices of the SVM-BTA classifier using PAM and LDA are reported in Tables 3–5 for the vertical and in Tables 6–8 for the horizontal traffic dataset. The mixture of all vertical and horizontal traffic activity classification results are presented in the confusion matrix shown in Figure 6 with 14 classes in total. Secondly, the behavior classification was evaluated for all clips to identify the category of the input clip. For behavior classification, all clips in the merged dataset were evaluated using the binary SVM classifier. The quantitative results of the evaluated metrics are represented in Table 9. It is important to note that only the binary SVM classifier was utilized for the behavior classification (either vertical or horizontal) instead of the multi-class SVM classifier for the activity case.


Traffic Behavior Recognition Using the Pachinko Allocation Model.

Huynh-The T, Banos O, Le BV, Bui DM, Yoon Y, Lee S - Sensors (Basel) (2015)

Confusion matrix of the SVM classifier for the mixing of all vertical and horizontal traffic with overall classification accuracy: (a) PAM 86.4%; (b) LDA 80.4%; and (c) MCTM 81.6%.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4541867&req=5

f6-sensors-15-16040: Confusion matrix of the SVM classifier for the mixing of all vertical and horizontal traffic with overall classification accuracy: (a) PAM 86.4%; (b) LDA 80.4%; and (c) MCTM 81.6%.
Mentions: In the experiments, the authors evaluated the performance in the classification accuracy of the proposed method for the detection of the vertical and horizontal traffic. Moreover, the method was compared with similar approaches using standard latent Dirichlet allocation (LDA) [36] and Markov clustering topic mode (MCTM) [30] for topic modeling. At first, the activity classification was applied to each separate dataset of the vertical and horizontal clips. The confusion matrices of the SVM-BTA classifier using PAM and LDA are reported in Tables 3–5 for the vertical and in Tables 6–8 for the horizontal traffic dataset. The mixture of all vertical and horizontal traffic activity classification results are presented in the confusion matrix shown in Figure 6 with 14 classes in total. Secondly, the behavior classification was evaluated for all clips to identify the category of the input clip. For behavior classification, all clips in the merged dataset were evaluated using the binary SVM classifier. The quantitative results of the evaluated metrics are represented in Table 9. It is important to note that only the binary SVM classifier was utilized for the behavior classification (either vertical or horizontal) instead of the multi-class SVM classifier for the activity case.

Bottom Line: As a key innovation, PAM captures not only the correlation among the activities, but also among the behaviors based on the arbitrary directed acyclic graph (DAG).The SVM classifier is then utilized on top to train and recognize the traffic activity and behavior.The proposed model shows more flexibility and greater expressive power than the commonly-used latent Dirichlet allocation (LDA) approach, leading to a higher recognition accuracy in the behavior classification.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Engineering, Kyung Hee University, Suwon 446-701, Korea. thienht@oslab.khu.ac.kr.

ABSTRACT
CCTV-based behavior recognition systems have gained considerable attention in recent years in the transportation surveillance domain for identifying unusual patterns, such as traffic jams, accidents, dangerous driving and other abnormal behaviors. In this paper, a novel approach for traffic behavior modeling is presented for video-based road surveillance. The proposed system combines the pachinko allocation model (PAM) and support vector machine (SVM) for a hierarchical representation and identification of traffic behavior. A background subtraction technique using Gaussian mixture models (GMMs) and an object tracking mechanism based on Kalman filters are utilized to firstly construct the object trajectories. Then, the sparse features comprising the locations and directions of the moving objects are modeled by PAMinto traffic topics, namely activities and behaviors. As a key innovation, PAM captures not only the correlation among the activities, but also among the behaviors based on the arbitrary directed acyclic graph (DAG). The SVM classifier is then utilized on top to train and recognize the traffic activity and behavior. The proposed model shows more flexibility and greater expressive power than the commonly-used latent Dirichlet allocation (LDA) approach, leading to a higher recognition accuracy in the behavior classification.

No MeSH data available.


Related in: MedlinePlus