Cited 0 time in
Cited 0 time in
Methodology for Improving Detection Speed of Pedestrians in Autonomous Vehicle by Image Class Classification
- Methodology for Improving Detection Speed of Pedestrians in Autonomous Vehicle by Image Class Classification
- Kim, Junkwang; Jung, Woo Young; Jung, Heechul; Han, Dong Seog
- DGIST Authors
- Kim, Junkwang; Jung, Woo Young
- Issue Date
- 2018 IEEE International Conference on Consumer Electronics, ICCE 2018, 1-2
- We propose a pedestrian detection method to minimize the amount of computation for classifying and candidate region detection in autonomous vehicles. The minimization of the computational complexity is a crucial factor for commercial products with a limited computational power. In conventional pedestrian detection methods, the number of candidate regions is 300 to 2,000 even if there is no pedestrian in an image. Therefore, the unnecessary computation is significant to classify each falsely decided candidate region. Moreover, it leads to false detection. In this paper, we propose a new methodology for solving this problem, and show through experiments that the processing speed can be improved by the proposed methodology. © 2018 IEEE.
- Institute of Electrical and Electronics Engineers Inc.
- Related Researcher
Artificial Intelligence, Machine Learning, Autonomous Driving
There are no files associated with this item.
- Division of Automotive Technology2. Conference Papers
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.