TY - GEN
T1 - Instance-level future motion estimation in a single image based on ordinal regression
AU - Kim, Kyung Rae
AU - Choi, Whan
AU - Koh, Yeong Jun
AU - Jeong, Seong Gyun
AU - Kim, Chang Su
N1 - Funding Information:
This work was supported by ‘The Cross-Ministry Giga KOREA Project’ grant funded by the Korea government (MSIT) (No. GK18P0200, Development of 4D reconstruction and dynamic deformable action model based hyperrealistic service technology), by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. NRF-2018R1A2B3003896), and by NAVER LABS.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - A novel algorithm to estimate instance-level future motion in a single image is proposed in this paper. We first represent the future motion of an instance with its direction, speed, and action classes. Then, we develop a deep neural network that exploits different levels of semantic information to perform the future motion estimation. For effective future motion classification, we adopt ordinal regression. Especially, we develop the cyclic ordinal regression scheme using binary classifiers. Experiments demonstrate that the proposed algorithm provides reliable performance and thus can be used effectively for vision applications, including single and multi object tracking. Furthermore, we release the future motion (FM) dataset, collected from diverse sources and annotated manually, as a benchmark for single-image future motion estimation.
AB - A novel algorithm to estimate instance-level future motion in a single image is proposed in this paper. We first represent the future motion of an instance with its direction, speed, and action classes. Then, we develop a deep neural network that exploits different levels of semantic information to perform the future motion estimation. For effective future motion classification, we adopt ordinal regression. Especially, we develop the cyclic ordinal regression scheme using binary classifiers. Experiments demonstrate that the proposed algorithm provides reliable performance and thus can be used effectively for vision applications, including single and multi object tracking. Furthermore, we release the future motion (FM) dataset, collected from diverse sources and annotated manually, as a benchmark for single-image future motion estimation.
UR - http://www.scopus.com/inward/record.url?scp=85081902603&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2019.00036
DO - 10.1109/ICCV.2019.00036
M3 - Conference contribution
AN - SCOPUS:85081902603
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 273
EP - 282
BT - Proceedings - 2019 International Conference on Computer Vision, ICCV 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 17th IEEE/CVF International Conference on Computer Vision, ICCV 2019
Y2 - 27 October 2019 through 2 November 2019
ER -