TY - GEN
T1 - A Continuous Occlusion Model for Road Scene Understanding
AU - Dhiman, Vikas
AU - Tran, Quoc Huy
AU - Corso, Jason J.
AU - Chandraker, Manmohan
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/12/9
Y1 - 2016/12/9
N2 - We present a physically interpretable, continuous threedimensional (3D) model for handling occlusions with applications to road scene understanding. We probabilistically assign each point in space to an object with a theoretical modeling of the reflection and transmission probabilities for the corresponding camera ray. Our modeling is unified in handling occlusions across a variety of scenarios, such as associating structure from motion (SFM) point tracks with potentially occluding objects or modeling object detection scores in applications such as 3D localization. For point track association, our model uniformly handles static and dynamic objects, which is an advantage over motion segmentation approaches traditionally used in multibody SFM. Detailed experiments on the KITTI raw dataset show the superiority of the proposed method over both state-of-the-art motion segmentation and a baseline that heuristically uses detection bounding boxes for resolving occlusions. We also demonstrate how our continuous occlusion model may be applied to the task of 3D localization in road scenes.
AB - We present a physically interpretable, continuous threedimensional (3D) model for handling occlusions with applications to road scene understanding. We probabilistically assign each point in space to an object with a theoretical modeling of the reflection and transmission probabilities for the corresponding camera ray. Our modeling is unified in handling occlusions across a variety of scenarios, such as associating structure from motion (SFM) point tracks with potentially occluding objects or modeling object detection scores in applications such as 3D localization. For point track association, our model uniformly handles static and dynamic objects, which is an advantage over motion segmentation approaches traditionally used in multibody SFM. Detailed experiments on the KITTI raw dataset show the superiority of the proposed method over both state-of-the-art motion segmentation and a baseline that heuristically uses detection bounding boxes for resolving occlusions. We also demonstrate how our continuous occlusion model may be applied to the task of 3D localization in road scenes.
UR - http://www.scopus.com/inward/record.url?scp=84986276567&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84986276567&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2016.469
DO - 10.1109/CVPR.2016.469
M3 - Conference contribution
AN - SCOPUS:84986276567
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 4331
EP - 4339
BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
T2 - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Y2 - 26 June 2016 through 1 July 2016
ER -