Distributed Bayesian Inference for Consistent Labeling of Tracked Objects in Nonoverlapping Camera Networks
One of the fundamental requirements for visual surveillance using nonoverlapping camera networks is the correct labeling of tracked objects on each camera in a consistent way, in the sense that the observations of the same object at different cameras should be assigned with the same label. In this p...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2013-12-01
|
| Series: | International Journal of Distributed Sensor Networks |
| Online Access: | https://doi.org/10.1155/2013/613246 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832547218369806336 |
|---|---|
| author | Jiuqing Wan Li Liu |
| author_facet | Jiuqing Wan Li Liu |
| author_sort | Jiuqing Wan |
| collection | DOAJ |
| description | One of the fundamental requirements for visual surveillance using nonoverlapping camera networks is the correct labeling of tracked objects on each camera in a consistent way, in the sense that the observations of the same object at different cameras should be assigned with the same label. In this paper, we formulate this task as a Bayesian inference problem and propose a distributed inference framework in which the posterior distribution of labeling variable corresponding to each observation is calculated based solely on local information processing on each camera and mutual information exchanging between neighboring cameras. In our framework, the number of objects presenting in the monitored region does not need to be specified beforehand. Instead, it can be determined automatically on the fly. In addition, we make no assumption about the appearance distribution of a single object, but use “similarity” scores between appearance pairs as appearance likelihood for inference. To cope with the problem of missing detection, we consider an enlarged neighborhood of each camera during inference and use a mixture model to describe the higher order spatiotemporal constraints. Finally, we demonstrate the effectiveness of our method through experiments on an indoor office building dataset and an outdoor campus garden dataset. |
| format | Article |
| id | doaj-art-4b88a7bb1d9f46ffa2e171a78cd7cbf2 |
| institution | Kabale University |
| issn | 1550-1477 |
| language | English |
| publishDate | 2013-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Distributed Sensor Networks |
| spelling | doaj-art-4b88a7bb1d9f46ffa2e171a78cd7cbf22025-02-03T06:45:33ZengWileyInternational Journal of Distributed Sensor Networks1550-14772013-12-01910.1155/2013/613246613246Distributed Bayesian Inference for Consistent Labeling of Tracked Objects in Nonoverlapping Camera NetworksJiuqing WanLi LiuOne of the fundamental requirements for visual surveillance using nonoverlapping camera networks is the correct labeling of tracked objects on each camera in a consistent way, in the sense that the observations of the same object at different cameras should be assigned with the same label. In this paper, we formulate this task as a Bayesian inference problem and propose a distributed inference framework in which the posterior distribution of labeling variable corresponding to each observation is calculated based solely on local information processing on each camera and mutual information exchanging between neighboring cameras. In our framework, the number of objects presenting in the monitored region does not need to be specified beforehand. Instead, it can be determined automatically on the fly. In addition, we make no assumption about the appearance distribution of a single object, but use “similarity” scores between appearance pairs as appearance likelihood for inference. To cope with the problem of missing detection, we consider an enlarged neighborhood of each camera during inference and use a mixture model to describe the higher order spatiotemporal constraints. Finally, we demonstrate the effectiveness of our method through experiments on an indoor office building dataset and an outdoor campus garden dataset.https://doi.org/10.1155/2013/613246 |
| spellingShingle | Jiuqing Wan Li Liu Distributed Bayesian Inference for Consistent Labeling of Tracked Objects in Nonoverlapping Camera Networks International Journal of Distributed Sensor Networks |
| title | Distributed Bayesian Inference for Consistent Labeling of Tracked Objects in Nonoverlapping Camera Networks |
| title_full | Distributed Bayesian Inference for Consistent Labeling of Tracked Objects in Nonoverlapping Camera Networks |
| title_fullStr | Distributed Bayesian Inference for Consistent Labeling of Tracked Objects in Nonoverlapping Camera Networks |
| title_full_unstemmed | Distributed Bayesian Inference for Consistent Labeling of Tracked Objects in Nonoverlapping Camera Networks |
| title_short | Distributed Bayesian Inference for Consistent Labeling of Tracked Objects in Nonoverlapping Camera Networks |
| title_sort | distributed bayesian inference for consistent labeling of tracked objects in nonoverlapping camera networks |
| url | https://doi.org/10.1155/2013/613246 |
| work_keys_str_mv | AT jiuqingwan distributedbayesianinferenceforconsistentlabelingoftrackedobjectsinnonoverlappingcameranetworks AT liliu distributedbayesianinferenceforconsistentlabelingoftrackedobjectsinnonoverlappingcameranetworks |