Towards Efficient Multiview Object Detection with Adaptive Action Prediction

Page view(s)
11
Checked on Dec 29, 2022
Towards Efficient Multiview Object Detection with Adaptive Action Prediction
Title:
Towards Efficient Multiview Object Detection with Adaptive Action Prediction
Other Titles:
2021 IEEE International Conference on Robotics and Automation (ICRA)
Keywords:
Publication Date:
18 October 2021
Citation:
Xu, Q., Fang, F., Gauthier, N., Liang, W., Wu, Y., Li, L., & Lim, J.-H. (2021). Towards Efficient Multiview Object Detection with Adaptive Action Prediction. 2021 IEEE International Conference on Robotics and Automation (ICRA). doi:10.1109/icra48506.2021.9561388
Abstract:
Active vision is a desirable perceptual feature for robots. Existing approaches usually make strong assumptions about the task and environment, thus are less robust and efficient. This study proposes an adaptive view planning approach to boost the efficiency and robustness of active object detection. We formulate the multi-object detection task as an active multiview object detection problem given the initial location of the objects. Next, we propose a novel adaptive action prediction (A2P) method built on a deep Q-learning network with a dueling architecture. The A2P method is able to perform view planning based on visual information of multiple objects; and adjust action ranges according to the task status. Evaluated on the AVD dataset, A2P leads to 21.9% increase in detection accuracy in unfamiliar environments, while improving efficiency by 22.7%. On the T-LESS dataset, multi-object detection boosts efficiency by more than 30% while achieving equivalent detection accuracy.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - AME Programmatic Funding Scheme
Grant Reference no. : #A18A2b0046
Description:
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
2577-087X
1050-4729
ISBN:
978-1-7281-9077-8
978-1-7281-9078-5
Files uploaded:

File Size Format Action
2021-icra.pdf 3.47 MB PDF Request a copy