Multiple Object Tracking for Dense Pedestrians by Markov Random Field Model with Improvement on Potentials
Pedestrian tracking in dense crowds is a challenging task, even when using a multi-camera system. In this paper, a new Markov random field (MRF) model is proposed for the association of tracklet couplings. Equipped with a new potential function improvement method, this model can associate the small...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/3/628 |
| _version_ | 1828273510348226560 |
|---|---|
| author | Peixin Liu Xiaofeng Li Yang Wang Zhizhong Fu |
| author_facet | Peixin Liu Xiaofeng Li Yang Wang Zhizhong Fu |
| author_sort | Peixin Liu |
| collection | DOAJ |
| description | Pedestrian tracking in dense crowds is a challenging task, even when using a multi-camera system. In this paper, a new Markov random field (MRF) model is proposed for the association of tracklet couplings. Equipped with a new potential function improvement method, this model can associate the small tracklet coupling segments caused by dense pedestrian crowds. The tracklet couplings in this paper are obtained through a data fusion method based on image mutual information. This method calculates the spatial relationships of tracklet pairs by integrating position and motion information, and adopts the human key point detection method for correction of the position data of incomplete and deviated detections in dense crowds. The MRF potential function improvement method for dense pedestrian scenes includes assimilation and extension processing, as well as a message selective belief propagation algorithm. The former enhances the information of the fragmented tracklets by means of a soft link with longer tracklets and expands through sharing to improve the potentials of the adjacent nodes, whereas the latter uses a message selection rule to prevent unreliable messages of fragmented tracklet couplings from being spread throughout the MRF network. With the help of the iterative belief propagation algorithm, the potentials of the model are improved to achieve valid association of the tracklet coupling fragments, such that dense pedestrians can be tracked more robustly. Modular experiments and system-level experiments are conducted using the PETS2009 experimental data set, where the experimental results reveal that the proposed method has superior tracking performance. |
| first_indexed | 2024-04-13T06:22:28Z |
| format | Article |
| id | doaj.art-2a79b64fce40436f9a27a9d9ef9157b6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T06:22:28Z |
| publishDate | 2020-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-2a79b64fce40436f9a27a9d9ef9157b62022-12-22T02:58:35ZengMDPI AGSensors1424-82202020-01-0120362810.3390/s20030628s20030628Multiple Object Tracking for Dense Pedestrians by Markov Random Field Model with Improvement on PotentialsPeixin Liu0Xiaofeng Li1Yang Wang2Zhizhong Fu3School of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC), 2006 Xiyuan Avenue, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC), 2006 Xiyuan Avenue, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC), 2006 Xiyuan Avenue, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC), 2006 Xiyuan Avenue, Chengdu 611731, ChinaPedestrian tracking in dense crowds is a challenging task, even when using a multi-camera system. In this paper, a new Markov random field (MRF) model is proposed for the association of tracklet couplings. Equipped with a new potential function improvement method, this model can associate the small tracklet coupling segments caused by dense pedestrian crowds. The tracklet couplings in this paper are obtained through a data fusion method based on image mutual information. This method calculates the spatial relationships of tracklet pairs by integrating position and motion information, and adopts the human key point detection method for correction of the position data of incomplete and deviated detections in dense crowds. The MRF potential function improvement method for dense pedestrian scenes includes assimilation and extension processing, as well as a message selective belief propagation algorithm. The former enhances the information of the fragmented tracklets by means of a soft link with longer tracklets and expands through sharing to improve the potentials of the adjacent nodes, whereas the latter uses a message selection rule to prevent unreliable messages of fragmented tracklet couplings from being spread throughout the MRF network. With the help of the iterative belief propagation algorithm, the potentials of the model are improved to achieve valid association of the tracklet coupling fragments, such that dense pedestrians can be tracked more robustly. Modular experiments and system-level experiments are conducted using the PETS2009 experimental data set, where the experimental results reveal that the proposed method has superior tracking performance.https://www.mdpi.com/1424-8220/20/3/628multi-camera multi-object trackingdense pedestrian crowdscross-view data fusionimage mutual informationmarkov random field model |
| spellingShingle | Peixin Liu Xiaofeng Li Yang Wang Zhizhong Fu Multiple Object Tracking for Dense Pedestrians by Markov Random Field Model with Improvement on Potentials Sensors multi-camera multi-object tracking dense pedestrian crowds cross-view data fusion image mutual information markov random field model |
| title | Multiple Object Tracking for Dense Pedestrians by Markov Random Field Model with Improvement on Potentials |
| title_full | Multiple Object Tracking for Dense Pedestrians by Markov Random Field Model with Improvement on Potentials |
| title_fullStr | Multiple Object Tracking for Dense Pedestrians by Markov Random Field Model with Improvement on Potentials |
| title_full_unstemmed | Multiple Object Tracking for Dense Pedestrians by Markov Random Field Model with Improvement on Potentials |
| title_short | Multiple Object Tracking for Dense Pedestrians by Markov Random Field Model with Improvement on Potentials |
| title_sort | multiple object tracking for dense pedestrians by markov random field model with improvement on potentials |
| topic | multi-camera multi-object tracking dense pedestrian crowds cross-view data fusion image mutual information markov random field model |
| url | https://www.mdpi.com/1424-8220/20/3/628 |
| work_keys_str_mv | AT peixinliu multipleobjecttrackingfordensepedestriansbymarkovrandomfieldmodelwithimprovementonpotentials AT xiaofengli multipleobjecttrackingfordensepedestriansbymarkovrandomfieldmodelwithimprovementonpotentials AT yangwang multipleobjecttrackingfordensepedestriansbymarkovrandomfieldmodelwithimprovementonpotentials AT zhizhongfu multipleobjecttrackingfordensepedestriansbymarkovrandomfieldmodelwithimprovementonpotentials |