Detection of Damaged Stop Lines on Public Roads by Focusing on Piece Distribution of Paired Edges

Abstract

In this study, a system for detecting stop lines on roads with damaged paint is developed to enhance a digital map localization system. Existing methods to detect stop lines focus on features such as straight edges and adequate size; however, these methods are not suitable to be used in rural areas because the paint of stop lines on the roads is damaged sometimes. In addition, lane marks, which are focused on by other existing methods, are often not present on actual roads in rural areas. Thus, to enable the detection of stop lines in the absence of conditions necessary for using the abovementioned features, we focus on pieces of faint features of damaged stop lines. First, we extract the positive and negative edges from an inverse perspective mapped image of the camera input by using a Sobel filter. Next, we verify the pairs of positive and negative edges from the trinarized edge image by confirming the width between both edges. Subsequently, we detect the candidates of stop lines by analyzing the distribution of the line segments extracted by the Hough transformation. In addition, we combine the data of the estimated driving distance and the result of detection of the preceding vehicles with the proposed system to prevent false detections in terms of bicycle crossing lanes and preceding vehicles. The damaged stop lines are detected eventually using these processes. To evaluate the performance of the proposed method, we collect driving data on actual public roads. The results of offline evaluations confirm that the proposed system can detect all target stop lines without any false detections, at a reasonable speed. The findings of this study are expected to contribute to the realization of intelligent vehicles on community roads.

From Pedestrian Detection to Crosswalk Estimation: An EM Algorithm and Analysis on Diverse Datasets

“…Camera-based approaches are the most popular for such detections, and for good reason: (Song et al, 2022) shows that in urban point cloud maps, crosswalks and other road surface markings (RSMs) are the most challenging class in point cloud semantic segmentation. But even in camerabased approaches, cracks and other damage to painted lines can provide significant challenges, with remedies proposed in (Ito et al, 2021).…”

Holistic Grid Fusion Based Stop Line Estimation

“…To track stop lines robustly over time, [14] uses a spatial filter to find stop line candidates and then applies a Kalman Filter to track and stabilize the position estimate. To eliminate the prior assumptions about ideal shapes or positional relations, [4] developed a system for detecting stop lines on roads with damaged paint. Although their proposed method achieves good results, it still is constrained by the requirement of partial visibility of the ground markings, and hence is not robust to occlusion.…”

“…Most approaches to stop line detection rely only on camera images [4] and explicitly try to detect the stop line that is painted onto the road. A few difficult scenarios for camerabased stop line detection are depicted in Figure 1.…”

Identification and location method of strip ingot for autonomous robot system using kmeans clustering and color segmentation

“…W Winterhalter [29] proposed a pipeline for reliable plant segmentation at any stage of crop growth, as well as a new algorithm for robust crop row detection, which uses the HT for line detection to detect patterns of parallel isometric lines. Besides, in order to improve the positioning accuracy of HT algorithm and accurately identify the location of damaged stop lines for driverless vehicles, Takuma Ito [23] and others proposed a method to detect stop line based on HT to extract the distribution characteristics of line segments, and finally realized the accurate detection of damaged stop lines. Considering that this method can only detect a single line segment, it is difficult to apply it to the positioning of multiple edge lines in ingots.…”