Efficient Lane Detection Based on Spatiotemporal Images

• Published in: IEEE transactions on intelligent transportation systems Vol. 17; no. 1; pp. 289 - 295
• Main Authors: Jung, Soonhong, Youn, Junsic, Sull, Sanghoon
• Format: Journal Article
• Language: English
• Published: IEEE 01.01.2016
• Subjects: alignment; binarization; cubic model; Hough transform; Image edge detection; lane detection; lane tracking; Lenses; Reliability; Roads; scanline; Spatiotemporal image; Spatiotemporal phenomena; temporal consistency; Transforms; Vehicles; binarization; temporal consistency; cubic model; Spatiotemporal image; scanline; lane tracking; Hough transform; alignment; lane detection
• ISSN: 1524-9050; 1558-0016
• DOI: 10.1109/TITS.2015.2464253

In this paper, we propose an efficient method for reliably detecting road lanes based on spatiotemporal images. In an aligned spatiotemporal image generated by accumulating the pixels on a scanline along the time axis and aligning consecutive scanlines, the trajectory of the lane points appears smooth and forms a straight line. The aligned spatiotemporal image is binarized, and two dominant parallel straight lines resulting from the temporal consistency of lane width on a given scanline are detected using a Hough transform, reducing alignment errors. The left and right lane points are then detected near the intersections of the straight lines and the current scanline. Our spatiotemporal domain approach is more robust missing or occluded lanes than existing frame-based approaches. Furthermore, the experimental results show not only computation times reduced to as little as one-third but also a slightly improved rate of detection.