High Speed Road Boundary Detection with CNN-Based Dynamic Programming

Authors:
Hyongsuk Kim;Seungwan Hong;Taewan Oh;Junsu Lee
Affiliations:
-;-;-;-
Venue:
PCM '02 Proceedings of the Third IEEE Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Year:
2002

Citing 4
Cited 1

Rapidly Adapting Machine Vision for Automated Vehicle Steering

IEEE Expert: Intelligent Systems and Their Applications
Robust real-time lane and road detection in critical shadow conditions

ISCV '95 Proceedings of the International Symposium on Computer Vision
Dynamic Programming

Dynamic Programming
Optimal path finding with space- and time-variant metric weights via multi-layer CNN: Research Articles

International Journal of Circuit Theory and Applications - CNN Technology

Reverse Optical Flow for Self-Supervised Adaptive Autonomous Robot Navigation

International Journal of Computer Vision

Quantified Score

Hi-index	0.01

Visualization

Abstract

Analogic CNN-based road boundary detection algorithm for fast and optimal driving of autonomous vehicle is proposed. The CNN is a massively connected analog parallel array processor. In the previous study, the dynamic programming which is an efficient algorithm to find the optimal path is implemented with the CNN algorithm [1]. Due to the parallelism of the CNN structure, the processing speed of the CNN-based dynamic programming is expected to be very fast. The proposed study is an extension of previous optimal path finding algorithm for high speed road-boundary detection. If the road-edge images are utilized as the space variant weights and if the goal and the start lines are positioned at the top and the bottom of the image, respectively, the optimal path finding concept can be exploited for the road boundary detection. The proposed road boundary algorithm is described and simulation results are included.