차선변이 함수 기반의 선행차량 인식 알고리즘 = Stereo Image Processing Algorithm for Preceding Vehicle Detection Based on DLI

다국어 초록 (Multilingual Abstract)

This paper proposes an image processing algorithm for detecting obstacles on road using DLI(disparity of lane-related information) that is generated by stereo images acquired from dual cameras mounted on a moving vehicle. The DLI is a disparity that is acquired using a single lane information from road lane detection. For the purpose to reduce processing time, we use small block of edge-histogram based blocking logic. This algorithm detects moving objects such as preceding vehicles and obstacles. The proposed algorithm has been implemented in a personal computer with the road image data of a typical highway. We successfully performed experiments under a wide variety of road conditions without changing parameter values or adding human intervention. Experimental results also showed that the proposed DLI is quite successful.

참고문헌 (Reference)

1 "도로의 구조 시설구조에 관한 규정 해설 및 지침" 건설부 건설부 1990.

2 J. Weber, "New results in stereo-based automatic vehicle guidance" Intelligent Vehicles '95 Symposium 530-535, 1995.

3 K. Saneyoshi, "Drive assist system using stereo image recognition" Intelligent Vehicles Symposium, Proceedings of the 1996 IEEE 230-235, 1996.

4 K. Hanawa, "Development of Stereo Image Recognition System for ADA" IVS2001 177-182, 2001.

5 Q.-T. Luong, "An integrated stereo-based approach to automatic ve- hicle guidance" Fifth International Conference on Computer Vision 52-57, 1995.

6 J. W. Lee, "A Cumulative Distribution Function of Edge Direction for Road-Lane Detection" e84-d (e84-d): 1206-1216, 2001.

7 K. Saneyoshi, "3-D Image Recognition System by Means of Stereoscope Combined with Ordinary Image Processing" 13-18, 1994.

8 K. Saneyoshi, "3-D Image Recognition System For Drive Assist" 60-65, 1993.