TY - JOUR
T1 - Multimodal Partial Estimates Fusion
AU - Xu, Jiang
AU - Yuan, Junsong
AU - Wu, Ying
N1 - Funding Information:
This work was supported in part by National Science Foundation grant IIS-0347877, US Army Research Laboratory and the US Army Research Office under grant ARO W911NF-08-1-0504, and NIH #5 R24 HD050821-03.
Publisher Copyright:
© 2009 IEEE.
PY - 2009
Y1 - 2009
N2 - Fusing partial estimates is a critical and common problem in many computer vision tasks such as part-based detection and tracking. It generally becomes complicated and intractable when there are a large number of multimodal partial estimates, and thus it is desirable to find an effective and scalable fusion method to integrate these partial estimates. This paper presents a novel and effective approach to fusing multimodal partial estimates in a principled way. In this new approach, fusion is related to a computational geometry problem of finding the minimumvolume orthotope, and an effective and scalable branch and bound search algorithm is designed to obtain the global optimal solution. Experiments on tracking articulated objects and occluded objects show the effectiveness of the proposed approach.
AB - Fusing partial estimates is a critical and common problem in many computer vision tasks such as part-based detection and tracking. It generally becomes complicated and intractable when there are a large number of multimodal partial estimates, and thus it is desirable to find an effective and scalable fusion method to integrate these partial estimates. This paper presents a novel and effective approach to fusing multimodal partial estimates in a principled way. In this new approach, fusion is related to a computational geometry problem of finding the minimumvolume orthotope, and an effective and scalable branch and bound search algorithm is designed to obtain the global optimal solution. Experiments on tracking articulated objects and occluded objects show the effectiveness of the proposed approach.
UR - http://www.scopus.com/inward/record.url?scp=85009915261&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85009915261&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2009.5459475
DO - 10.1109/ICCV.2009.5459475
M3 - Conference article
AN - SCOPUS:85009915261
SN - 1550-5499
SP - 2177
EP - 2184
JO - Proceedings of the IEEE International Conference on Computer Vision
JF - Proceedings of the IEEE International Conference on Computer Vision
T2 - 12th International Conference on Computer Vision, ICCV 2009
Y2 - 29 September 2009 through 2 October 2009
ER -