Multiple small objects tracking based on dynamic Bayesian networks with spatial prior. Yao, R., Zhang, Y., Zhou, Y., & Xia, S. Optik - International Journal for Light and Electron Optics, 125(10):2243-2247, 5, 2014. ![Multiple small objects tracking based on dynamic Bayesian networks with spatial prior [link]](https://bibbase.org/img/filetypes/link.svg "link")
Website doi abstract bibtex This paper proposes an end-to-end algorithm for multiple small objects tracking in noisy video using a combination of Gaussian mixture based background segmentation along with a Dynamic Bayesian Networks (DBNs) based tracking. Background segmentation is based on an adaptive backgrounding method that models each pixel as a mixture of Gaussians with spatial prior and uses an online approximation to update the model, the spatial prior is constructed for small objects. Furthermore, we create observation model with hidden variable based on multi-cue statistical object model and employ Kalman filter as inference algorithm. Finally, we use linear assignment problem (LAP) algorithm to perform the models matching. The experimental results show the proposed method outperforms competing method, and demonstrate the effectiveness of the proposed method.
@article{
title = {Multiple small objects tracking based on dynamic Bayesian networks with spatial prior},
type = {article},
year = {2014},
keywords = {Data association,Dynamic Bayesian Networks,Multi-cue integration,Multiple small objects tracking},
pages = {2243-2247},
volume = {125},
websites = {http://www.sciencedirect.com/science/article/pii/S0030402613014964},
month = {5},
id = {b7cfbbcb-0200-3478-a20c-acfc15a08e92},
created = {2020-10-23T21:05:14.915Z},
accessed = {2015-04-11},
file_attached = {false},
profile_id = {95e10851-cdf3-31de-9f82-1ab629e601b0},
group_id = {4a6a1914-6ba6-3cdc-b1f4-f10a6e56cb6c},
last_modified = {2020-10-23T21:05:14.915Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
private_publication = {false},
abstract = {This paper proposes an end-to-end algorithm for multiple small objects tracking in noisy video using a combination of Gaussian mixture based background segmentation along with a Dynamic Bayesian Networks (DBNs) based tracking. Background segmentation is based on an adaptive backgrounding method that models each pixel as a mixture of Gaussians with spatial prior and uses an online approximation to update the model, the spatial prior is constructed for small objects. Furthermore, we create observation model with hidden variable based on multi-cue statistical object model and employ Kalman filter as inference algorithm. Finally, we use linear assignment problem (LAP) algorithm to perform the models matching. The experimental results show the proposed method outperforms competing method, and demonstrate the effectiveness of the proposed method.},
bibtype = {article},
author = {Yao, Rui and Zhang, Yanning and Zhou, Yong and Xia, Shixiong},
doi = {10.1016/j.ijleo.2013.10.108},
journal = {Optik - International Journal for Light and Electron Optics},
number = {10}
}
Downloads: 0
{"_id":"vikSyqjt82kqKoWeE","authorIDs":[],"author_short":["Yao, R.","Zhang, Y.","Zhou, Y.","Xia, S."],"bibbaseid":"yao-zhang-zhou-xia-multiplesmallobjectstrackingbasedondynamicbayesiannetworkswithspatialprior-2014","bibdata":{"title":"Multiple small objects tracking based on dynamic Bayesian networks with spatial prior","type":"article","year":"2014","keywords":"Data association,Dynamic Bayesian Networks,Multi-cue integration,Multiple small objects tracking","pages":"2243-2247","volume":"125","websites":"http://www.sciencedirect.com/science/article/pii/S0030402613014964","month":"5","id":"b7cfbbcb-0200-3478-a20c-acfc15a08e92","created":"2020-10-23T21:05:14.915Z","accessed":"2015-04-11","file_attached":false,"profile_id":"95e10851-cdf3-31de-9f82-1ab629e601b0","group_id":"4a6a1914-6ba6-3cdc-b1f4-f10a6e56cb6c","last_modified":"2020-10-23T21:05:14.915Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"private_publication":false,"abstract":"This paper proposes an end-to-end algorithm for multiple small objects tracking in noisy video using a combination of Gaussian mixture based background segmentation along with a Dynamic Bayesian Networks (DBNs) based tracking. Background segmentation is based on an adaptive backgrounding method that models each pixel as a mixture of Gaussians with spatial prior and uses an online approximation to update the model, the spatial prior is constructed for small objects. Furthermore, we create observation model with hidden variable based on multi-cue statistical object model and employ Kalman filter as inference algorithm. Finally, we use linear assignment problem (LAP) algorithm to perform the models matching. The experimental results show the proposed method outperforms competing method, and demonstrate the effectiveness of the proposed method.","bibtype":"article","author":"Yao, Rui and Zhang, Yanning and Zhou, Yong and Xia, Shixiong","doi":"10.1016/j.ijleo.2013.10.108","journal":"Optik - International Journal for Light and Electron Optics","number":"10","bibtex":"@article{\n title = {Multiple small objects tracking based on dynamic Bayesian networks with spatial prior},\n type = {article},\n year = {2014},\n keywords = {Data association,Dynamic Bayesian Networks,Multi-cue integration,Multiple small objects tracking},\n pages = {2243-2247},\n volume = {125},\n websites = {http://www.sciencedirect.com/science/article/pii/S0030402613014964},\n month = {5},\n id = {b7cfbbcb-0200-3478-a20c-acfc15a08e92},\n created = {2020-10-23T21:05:14.915Z},\n accessed = {2015-04-11},\n file_attached = {false},\n profile_id = {95e10851-cdf3-31de-9f82-1ab629e601b0},\n group_id = {4a6a1914-6ba6-3cdc-b1f4-f10a6e56cb6c},\n last_modified = {2020-10-23T21:05:14.915Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n private_publication = {false},\n abstract = {This paper proposes an end-to-end algorithm for multiple small objects tracking in noisy video using a combination of Gaussian mixture based background segmentation along with a Dynamic Bayesian Networks (DBNs) based tracking. Background segmentation is based on an adaptive backgrounding method that models each pixel as a mixture of Gaussians with spatial prior and uses an online approximation to update the model, the spatial prior is constructed for small objects. Furthermore, we create observation model with hidden variable based on multi-cue statistical object model and employ Kalman filter as inference algorithm. Finally, we use linear assignment problem (LAP) algorithm to perform the models matching. The experimental results show the proposed method outperforms competing method, and demonstrate the effectiveness of the proposed method.},\n bibtype = {article},\n author = {Yao, Rui and Zhang, Yanning and Zhou, Yong and Xia, Shixiong},\n doi = {10.1016/j.ijleo.2013.10.108},\n journal = {Optik - International Journal for Light and Electron Optics},\n number = {10}\n}","author_short":["Yao, R.","Zhang, Y.","Zhou, Y.","Xia, S."],"urls":{"Website":"http://www.sciencedirect.com/science/article/pii/S0030402613014964"},"biburl":"https://bibbase.org/service/mendeley/95e10851-cdf3-31de-9f82-1ab629e601b0","bibbaseid":"yao-zhang-zhou-xia-multiplesmallobjectstrackingbasedondynamicbayesiannetworkswithspatialprior-2014","role":"author","keyword":["Data association","Dynamic Bayesian Networks","Multi-cue integration","Multiple small objects tracking"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/95e10851-cdf3-31de-9f82-1ab629e601b0","creationDate":"2015-04-14T03:38:30.842Z","downloads":0,"keywords":["data association","dynamic bayesian networks","multi-cue integration","multiple small objects tracking"],"search_terms":["multiple","small","objects","tracking","based","dynamic","bayesian","networks","spatial","prior","yao","zhang","zhou","xia"],"title":"Multiple small objects tracking based on dynamic Bayesian networks with spatial prior","year":2014,"dataSources":["8hwkQbNZz66Dc7LzM","ya2CyA73rpZseyrZ8","2252seNhipfTmjEBQ"]}