Publications
Detailed Information
자율주행 인지 모듈의 실시간 성능을 위한 적응형 관심 영역 판단 : An Adaptive ROI Decision for Real-time Performance in an Autonomous Driving Perception Module
Cited 0 time in
Web of Science
Cited 0 time in Scopus
- Authors
- Issue Date
- 2022-06
- Publisher
- 사단법인 한국자동차안전학회
- Citation
- 자동차안전학회지, Vol.14 No.2, pp.20-25
- Abstract
- This paper represents an adaptive Region of Interest (ROI) decision for real-time performance in an autonomous driving perception module. Since the whole automated driving system consists of numerous modules and subdivisions of module occur, it is necessary to consider the characteristics, complexity, and limitations of each module. Furthermore, Light Detection And Ranging (Lidar) sensors require a considerable amount of time. In view of these limitations, division of submodule is inevitable to represent high real-time performance for stable system. This paper proposes ROI to reduce the number of data respect to computation time. ROI is set by a roads design speed and the corresponding ROI is applied differently to each vehicle considering its speed. The simulation model is constructed by ROS, and overall data analysis is conducted by Matlab. The algorithm is validated using real-time driving data in urban environment, and the result shows that ROI provides low computational costs.
- ISSN
- 2005-9396
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.