Multi-object tracking using binary masks. J, H., S., &., H. In Proc. 15th International Conference on Image Processing (ICIP 2008), San Diego, pages 2640-2643, 2008. abstract bibtex In this paper, we introduce a new method for tracking multiple objects. The method combines Kalman filtering and the Expectation Maximization (EM) algorithm in a novel way to deal with observations that obey a Gaussian mixture model instead of a unimodal distribution that is assumed by the ordinary Kalman filter. It also involves a new approach to measuring the object locations using a series of morphological operations with binary masks. The benefit of this approach is that soft assignment of the measurements to corresponding objects can be performed automatically using their a posteriori probabilities. This is a general approach for multi-object tracking, and there are basically various ways to segment the objects, but in this paper we use simple color features simply to demonstrate the feasibility of the concept.
@inProceedings{
title = {Multi-object tracking using binary masks.},
type = {inProceedings},
year = {2008},
pages = {2640-2643},
id = {482e3dc1-c66d-303e-b2ac-b0400b8d2197},
created = {2019-11-19T13:01:23.414Z},
file_attached = {false},
profile_id = {bddcf02d-403b-3b06-9def-6d15cc293e20},
group_id = {17585b85-df99-3a34-98c2-c73e593397d7},
last_modified = {2019-11-19T13:47:32.855Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
citation_key = {mvg:1205},
source_type = {inproceedings},
private_publication = {false},
abstract = {In this paper, we introduce a new method for tracking multiple objects. The method combines Kalman filtering and the Expectation Maximization (EM) algorithm in a novel way to deal with observations that obey a Gaussian mixture model instead of a unimodal distribution that is assumed by the ordinary Kalman filter. It also involves a new approach to measuring the object locations using a series of morphological operations with binary masks. The benefit of this approach is that soft assignment of the measurements to corresponding objects can be performed automatically using their a posteriori probabilities. This is a general approach for multi-object tracking, and there are basically various ways to segment the objects, but in this paper we use simple color features simply to demonstrate the feasibility of the concept.},
bibtype = {inProceedings},
author = {J, Huttunen S & Heikkilä},
booktitle = {Proc. 15th International Conference on Image Processing (ICIP 2008), San Diego}
}
Downloads: 0
{"_id":"mPmqeGf68B6omjEcW","bibbaseid":"j-multiobjecttrackingusingbinarymasks-2008","authorIDs":[],"author_short":["J, H., S., &., H."],"bibdata":{"title":"Multi-object tracking using binary masks.","type":"inProceedings","year":"2008","pages":"2640-2643","id":"482e3dc1-c66d-303e-b2ac-b0400b8d2197","created":"2019-11-19T13:01:23.414Z","file_attached":false,"profile_id":"bddcf02d-403b-3b06-9def-6d15cc293e20","group_id":"17585b85-df99-3a34-98c2-c73e593397d7","last_modified":"2019-11-19T13:47:32.855Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"mvg:1205","source_type":"inproceedings","private_publication":false,"abstract":"In this paper, we introduce a new method for tracking multiple objects. The method combines Kalman filtering and the Expectation Maximization (EM) algorithm in a novel way to deal with observations that obey a Gaussian mixture model instead of a unimodal distribution that is assumed by the ordinary Kalman filter. It also involves a new approach to measuring the object locations using a series of morphological operations with binary masks. The benefit of this approach is that soft assignment of the measurements to corresponding objects can be performed automatically using their a posteriori probabilities. This is a general approach for multi-object tracking, and there are basically various ways to segment the objects, but in this paper we use simple color features simply to demonstrate the feasibility of the concept.","bibtype":"inProceedings","author":"J, Huttunen S & Heikkilä","booktitle":"Proc. 15th International Conference on Image Processing (ICIP 2008), San Diego","bibtex":"@inProceedings{\n title = {Multi-object tracking using binary masks.},\n type = {inProceedings},\n year = {2008},\n pages = {2640-2643},\n id = {482e3dc1-c66d-303e-b2ac-b0400b8d2197},\n created = {2019-11-19T13:01:23.414Z},\n file_attached = {false},\n profile_id = {bddcf02d-403b-3b06-9def-6d15cc293e20},\n group_id = {17585b85-df99-3a34-98c2-c73e593397d7},\n last_modified = {2019-11-19T13:47:32.855Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {mvg:1205},\n source_type = {inproceedings},\n private_publication = {false},\n abstract = {In this paper, we introduce a new method for tracking multiple objects. The method combines Kalman filtering and the Expectation Maximization (EM) algorithm in a novel way to deal with observations that obey a Gaussian mixture model instead of a unimodal distribution that is assumed by the ordinary Kalman filter. It also involves a new approach to measuring the object locations using a series of morphological operations with binary masks. The benefit of this approach is that soft assignment of the measurements to corresponding objects can be performed automatically using their a posteriori probabilities. This is a general approach for multi-object tracking, and there are basically various ways to segment the objects, but in this paper we use simple color features simply to demonstrate the feasibility of the concept.},\n bibtype = {inProceedings},\n author = {J, Huttunen S & Heikkilä},\n booktitle = {Proc. 15th International Conference on Image Processing (ICIP 2008), San Diego}\n}","author_short":["J, H., S., &., H."],"bibbaseid":"j-multiobjecttrackingusingbinarymasks-2008","role":"author","urls":{},"downloads":0},"bibtype":"inProceedings","creationDate":"2019-11-19T13:17:06.603Z","downloads":0,"keywords":[],"search_terms":["multi","object","tracking","using","binary","masks","j"],"title":"Multi-object tracking using binary masks.","year":2008}