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

Pachinko allocation model: (a) hierarchical topic model (b) graphic model.
© Copyright Policy
Related In: Results  -  Collection

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

f3-sensors-15-16040: Pachinko allocation model: (a) hierarchical topic model (b) graphic model.

Mentions: In the following subsection, the details of the proposed model based on PAM are introduced with the algorithm for the estimation of the parameters. Although PAM employs arbitrary DAGs to model the topic correlations, this work proposes a four-level hierarchy structure as a special case of PAM [37]. This structure consists of one root topic, u super topics at the second level = {p1, p2, …, pu}, v subtopics at the third level = {q1, q2, …, qv} and the words at the bottom. Words refer here to the object features comprising the location and direction information, which were organized in the previous stage. The super topic and subtopic correspond to the traffic behavior and activity, respectively. The root is associated with behaviors; the behaviors are fully associated with activities; and the activities are fully connected to the features, as shown in Figure 3a. The multinomials of the root and behaviors are sampled for each frame based on a single Dirichlet distribution gr (δr) and , respectively. The activities are modeled with multinomial distributions and sampled from Dirichlet distribution g (β) and g (γ), which are used for sampling the location and direction features. Figure 3b depicts a graphic model for the four-levels PAM. The particular notations used in PAM are summarized in Table 1. According to the standard PAM [35], considered a scene as a document d consisting of a the sequence of n frames = {d1, d2, …, dn}, this is modeled as follows:


Traffic Behavior Recognition Using the Pachinko Allocation Model.

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

Pachinko allocation model: (a) hierarchical topic model (b) graphic model.
© Copyright Policy
Related In: Results  -  Collection

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

f3-sensors-15-16040: Pachinko allocation model: (a) hierarchical topic model (b) graphic model.
Mentions: In the following subsection, the details of the proposed model based on PAM are introduced with the algorithm for the estimation of the parameters. Although PAM employs arbitrary DAGs to model the topic correlations, this work proposes a four-level hierarchy structure as a special case of PAM [37]. This structure consists of one root topic, u super topics at the second level = {p1, p2, …, pu}, v subtopics at the third level = {q1, q2, …, qv} and the words at the bottom. Words refer here to the object features comprising the location and direction information, which were organized in the previous stage. The super topic and subtopic correspond to the traffic behavior and activity, respectively. The root is associated with behaviors; the behaviors are fully associated with activities; and the activities are fully connected to the features, as shown in Figure 3a. The multinomials of the root and behaviors are sampled for each frame based on a single Dirichlet distribution gr (δr) and , respectively. The activities are modeled with multinomial distributions and sampled from Dirichlet distribution g (β) and g (γ), which are used for sampling the location and direction features. Figure 3b depicts a graphic model for the four-levels PAM. The particular notations used in PAM are summarized in Table 1. According to the standard PAM [35], considered a scene as a document d consisting of a the sequence of n frames = {d1, d2, …, dn}, this is modeled as follows:

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