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

The object trajectory: (a) in the spatial dimension (b) in the temporal-spatial dimension; and (c) the direction of motion path.
© Copyright Policy
Related In: Results  -  Collection

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

f2-sensors-15-16040: The object trajectory: (a) in the spatial dimension (b) in the temporal-spatial dimension; and (c) the direction of motion path.

Mentions: The object trajectories are represented in the temporal-spatial dimension. Example object trajectories illustrated in the spatial domain are shown in Figure 2a; those in the temporal-spatial domain are shown in Figure 2b. To determine the orientation of the object trajectory, the absolute angle α of the current location is calculated through the following equation:(1)αi=arcsin(yixi2+yi2)where (xi, yi) are the coordinates of the object at the i-th frame. A direction computation example is shown in Figure 2c. Only one angle value corresponding to the current frame is acquired. Each moving object is described by two features: the location and the direction. During a specific time period of the input video, which is presented under the number of input frames from ta to tb, the trajectory of an object is formed as:(2)Okta−b=[(xkta,ykta,αkta),(xkta+1,ykta+1,αkta+1),…,(xktb,yktb,αktb)]where and are the X and Y coordinate, respectively. is the moving direction of the k-th detected object at current frame ta. The object Ok presents the trajectory vector in (tb − ta) frames. Assuming that each input video has n frames, the trajectory is defined as follows:(3)Okn=[(xk1,yk1,αk1),(xk2,yk2,αk2),…,(xkn,ykn,αkn)]


Traffic Behavior Recognition Using the Pachinko Allocation Model.

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

The object trajectory: (a) in the spatial dimension (b) in the temporal-spatial dimension; and (c) the direction of motion path.
© Copyright Policy
Related In: Results  -  Collection

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

f2-sensors-15-16040: The object trajectory: (a) in the spatial dimension (b) in the temporal-spatial dimension; and (c) the direction of motion path.
Mentions: The object trajectories are represented in the temporal-spatial dimension. Example object trajectories illustrated in the spatial domain are shown in Figure 2a; those in the temporal-spatial domain are shown in Figure 2b. To determine the orientation of the object trajectory, the absolute angle α of the current location is calculated through the following equation:(1)αi=arcsin(yixi2+yi2)where (xi, yi) are the coordinates of the object at the i-th frame. A direction computation example is shown in Figure 2c. Only one angle value corresponding to the current frame is acquired. Each moving object is described by two features: the location and the direction. During a specific time period of the input video, which is presented under the number of input frames from ta to tb, the trajectory of an object is formed as:(2)Okta−b=[(xkta,ykta,αkta),(xkta+1,ykta+1,αkta+1),…,(xktb,yktb,αktb)]where and are the X and Y coordinate, respectively. is the moving direction of the k-th detected object at current frame ta. The object Ok presents the trajectory vector in (tb − ta) frames. Assuming that each input video has n frames, the trajectory is defined as follows:(3)Okn=[(xk1,yk1,αk1),(xk2,yk2,αk2),…,(xkn,ykn,αkn)]

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