Limits...
Incremental structured dictionary learning for video sensor-based object tracking.

Xue M, Yang H, Zheng S, Zhou Y, Yu Z - Sensors (Basel) (2014)

Bottom Line: To formulate the training and classification process, a multiple linear classifier group based on a K-combined voting (KCV) function is proposed.As the dictionary evolves, the models are also trained to timely adapt the target appearance variation.We also illustrate its relay application in visual sensor networks.

View Article: PubMed Central - PubMed

Affiliation: Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai 200240, China. xue@sjtu.edu.cn.

ABSTRACT
To tackle robust object tracking for video sensor-based applications, an online discriminative algorithm based on incremental discriminative structured dictionary learning (IDSDL-VT) is presented. In our framework, a discriminative dictionary combining both positive, negative and trivial patches is designed to sparsely represent the overlapped target patches. Then, a local update (LU) strategy is proposed for sparse coefficient learning. To formulate the training and classification process, a multiple linear classifier group based on a K-combined voting (KCV) function is proposed. As the dictionary evolves, the models are also trained to timely adapt the target appearance variation. Qualitative and quantitative evaluations on challenging image sequences compared with state-of-the-art algorithms demonstrate that the proposed tracking algorithm achieves a more favorable performance. We also illustrate its relay application in visual sensor networks.

No MeSH data available.


Tracking process with a shared dictionary across all the cameras.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3958219&req=5

f13-sensors-14-03130: Tracking process with a shared dictionary across all the cameras.

Mentions: In order to make use of the visual information acquired as much as possible, we establish the tracking process with a shared dictionary across all the cameras, shown in Figure 13. When the cameras are switched on, their trackers begin to work. Here, we assume that the person entering the scene is the one we are going to track. We apply foreground extraction based on Gaussian background modeling [33] to detect the newly appeared person in the boundary area (5% of the frame height and width in this paper). When the foreground area is larger than a predefined threshold, the person is considered to be detected. Once one camera detects the target, it records the corresponding location and starts to track the target. If there is no foreground detected, the process sends the dictionary learned during the tracking process in this camera. All the other trackers corresponding to different cameras would replace the old dictionary with a newly received one, so that the visual information on the dictionary level can be shared across the network. An empty dictionary is also sent in the no foreground detection and no tracking case. For a straight forward implementation, the person entering the boundary area for the second time is considered as a disappearance, so that the tracking process in the current camera stops.


Incremental structured dictionary learning for video sensor-based object tracking.

Xue M, Yang H, Zheng S, Zhou Y, Yu Z - Sensors (Basel) (2014)

Tracking process with a shared dictionary across all the cameras.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3958219&req=5

f13-sensors-14-03130: Tracking process with a shared dictionary across all the cameras.
Mentions: In order to make use of the visual information acquired as much as possible, we establish the tracking process with a shared dictionary across all the cameras, shown in Figure 13. When the cameras are switched on, their trackers begin to work. Here, we assume that the person entering the scene is the one we are going to track. We apply foreground extraction based on Gaussian background modeling [33] to detect the newly appeared person in the boundary area (5% of the frame height and width in this paper). When the foreground area is larger than a predefined threshold, the person is considered to be detected. Once one camera detects the target, it records the corresponding location and starts to track the target. If there is no foreground detected, the process sends the dictionary learned during the tracking process in this camera. All the other trackers corresponding to different cameras would replace the old dictionary with a newly received one, so that the visual information on the dictionary level can be shared across the network. An empty dictionary is also sent in the no foreground detection and no tracking case. For a straight forward implementation, the person entering the boundary area for the second time is considered as a disappearance, so that the tracking process in the current camera stops.

Bottom Line: To formulate the training and classification process, a multiple linear classifier group based on a K-combined voting (KCV) function is proposed.As the dictionary evolves, the models are also trained to timely adapt the target appearance variation.We also illustrate its relay application in visual sensor networks.

View Article: PubMed Central - PubMed

Affiliation: Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai 200240, China. xue@sjtu.edu.cn.

ABSTRACT
To tackle robust object tracking for video sensor-based applications, an online discriminative algorithm based on incremental discriminative structured dictionary learning (IDSDL-VT) is presented. In our framework, a discriminative dictionary combining both positive, negative and trivial patches is designed to sparsely represent the overlapped target patches. Then, a local update (LU) strategy is proposed for sparse coefficient learning. To formulate the training and classification process, a multiple linear classifier group based on a K-combined voting (KCV) function is proposed. As the dictionary evolves, the models are also trained to timely adapt the target appearance variation. Qualitative and quantitative evaluations on challenging image sequences compared with state-of-the-art algorithms demonstrate that the proposed tracking algorithm achieves a more favorable performance. We also illustrate its relay application in visual sensor networks.

No MeSH data available.