Road Lane Detection Robust to Shadows Based on a Fuzzy System Using a Visible Light Camera Sensor

Abstract

Recently, autonomous vehicles, particularly self-driving cars, have received significant attention owing to rapid advancements in sensor and computation technologies. In addition to traffic sign recognition, road lane detection is one of the most important factors used in lane departure warning systems and autonomous vehicles for maintaining the safety of semi-autonomous and fully autonomous systems. Unlike traffic signs, road lanes are easily damaged by both internal and external factors such as road quality, occlusion (traffic on the road), weather conditions, and illumination (shadows from objects such as cars, trees, and buildings). Obtaining clear road lane markings for recognition processing is a difficult challenge. Therefore, we propose a method to overcome various illumination problems, particularly severe shadows, by using fuzzy system and line segment detector algorithms to obtain better results for detecting road lanes by a visible light camera sensor. Experimental results from three open databases, Caltech dataset, Santiago Lanes dataset (SLD), and Road Marking dataset, showed that our method outperformed conventional lane detection methods.

Shadow Detection in Still Road Images Using Chrominance Properties of Shadows and Spectral Power Distribution of the Illumination

“…Since the method addresses the detection of shadow edges on the road, in order to simplify a captured road scene, as well as reduce the number of false positive detections outside the road surface, an ROI in the incoming color images is defined on the road by using knowledge of the scene perspective and assuming flat road surface as in References [4,59]. The camera is installed beside the rear-view mirror of the ego-vehicle, and the ROI is a rectangular area covering the road region ahead, excluding most of the image areas which do not correspond with the ground (see Figure 8).…”

“…There are several factors that make onboard systems based on computer vision challenging. Changing scenarios, cluttered backgrounds, variable illumination, and the presence of objects of different class in the scene contribute to making the design of driver assistance tasks such as the detection of roads [1,2] and lanes [3,4] difficult. One of the most challenging factors encountered by a vision-based ADAS system is cast shadows [1,5] (see Figure 1).…”

“…Instead, two alternative strategies are applicable to onboard systems. One strategy focuses on comparing pixel properties between the candidate shadow region and a selected region located at the bottom of the image, which is assumed a free road region in front of the ego-vehicle [1,4,20]. However, depending on the distance to the camera, the varying reflection angles of the illumination may cause color variation of the road; thus, even a well-laid asphalted road can show zones in the image where the pixel properties are significantly different.…”

Lane Detection Method with Impulse Radio Ultra-Wideband Radar and Metal Lane Reflectors

“…Currently, the most widely used sensor for lane detection is a camera. Lane detection technology using cameras has been mainly studied to increase its recognition rate in complex environments [1][2][3][4] and to reduce the complexity for real-time lane recognition [5][6][7][8]. However, when cameras are affected by factors, such as lighting conditions, fog, and obstacles, the lane recognition rate is degraded.…”

Lane Marking Detection and Reconstruction with Line-Scan Imaging Data

“…However, unexpected challenges always appear in lane marking detection and localization due to various interferences such as illumination conditions (occlusion, night time…), camera location and orientation, environmental factors (i.e., foggy days, cloudy and rainy days…), the appearance of the lane markings, the type of road, and so on [ 2 ]. To deal with the abovementioned problems, numerous vision-based lane marking detection and localization algorithms have been proposed, which for structured roads can be roughly grouped into two categories: feature-based methods and model-based techniques [ 6 , 15 , 16 , 17 , 18 ].…”