Paper Info
Title
3D Autonomous Navigation Line Extraction for Field Roads Based on Binocular Vision.
Abstract
This paper proposes a 3D autonomous navigation line extraction method for field roads in hilly regions based on a low-cost binocular vision system. Accurate guide path detection of field roads is a prerequisite for the automatic driving of agricultural machines. First, considering the lack of lane lines, blurred boundaries, and complex surroundings of field roads in hilly regions, a modified image processing method was established to strengthen shadow identification and information fusion to better distinguish the road area from its surroundings. Second, based on nonobvious shape characteristics and small differences in the gray values of the field roads inside the image, the centroid points of the road area as its statistical feature was extracted and smoothed and then used as the geometric primitives of stereo matching. Finally, an epipolar constraint and a homography matrix were applied for accurate matching and 3D reconstruction to obtain the autonomous navigation line of the field roads. Experiments on the automatic driving of a carrier on field roads showed that on straight roads, multicurvature complex roads and undulating roads, the mean deviations between the actual midline of the road and the automatically traveled trajectory were 0.031m, 0.069m, and 0.105m, respectively, with maximum deviations of 0.133, 0.195m, and 0.216m, respectively. These test results demonstrate that the proposed method is feasible for road identification and 3D navigation line acquisition.
Year
DOI
Venue
2019
10.1155/2019/6832109
JOURNAL OF SENSORS
Field
DocType
Volume
Computer vision,Binocular vision,Epipolar geometry,Image processing,Geometric primitive,Homography,Artificial intelligence,Engineering,Trajectory,Centroid,3D reconstruction
Journal
2019
ISSN
Citations 
PageRank 
1687-725X
1
0.37
References 
Authors
14
3
Name
Order
Citations
PageRank
Yunwu Li110.37
Xiao-Juan Wang2228.34
Dexiong Liu310.70