Extraction of straight field roads between farmlands based on agricultural vehicle-mounted LiDAR

Abstract

The application of autonomous agricultural vehicles is gaining popularity as a way to increase production efficiency and lower operational costs. To achieve high performance, perception tasks (such as obstacle detection, road extraction, and drivable area extraction) are of great importance. Compared with structured roads, field roads between farmlands, including unstructured roads and semi-structured roads, are unfavorable for autonomous agricultural vehicle driving due to their bumpiness and unstructured nature. This study proposed an extraction method for the straight field roads between farmlands. The proposed method was based on the point cloud data acquired by LiDAR (Velodyne VLP-16) mounted on a John Deere 1204 6B-1204 tractor. The proposed method has three aspects: Euclidean Clustering-based extraction, boundary-based extraction, and road point cloud curve segment modification. Firstly, Euclidean Clustering with K-Dimensional (KD)-Tree data structure was adopted to extract the road curve segments close to the LiDAR composed of road points. Secondly, the boundary lines constraint was constructed to extract the distant road curve segments. Thirdly, the local distance ratio was used to modify the extracted road curve segments. The average extraction accuracy for both semi-structured and unstructured roads exceeded 98%, and the false positive rate (FPR) was less than 0.5%. These experimental findings demonstrated that the proposed road extraction method was precise and effective. The proposed method of this study can be applied to enhance the perception ability of autonomous agricultural vehicles thereby increasing the efficiency and safety of field road driving.

Novel real-time safety algorithm for predicting multi-targets in the farmland road

“…In 2018, there were 244 937 traffic accidents in China and a direct property loss was 1384.56 million RMB yuan [1] . The accident death rate on agricultural vehicles was 45%, and the death accident rate on farmland roads reached 54.5% [2] . It is very important to predict the targets in the farmland roads and remind the driver in time to reduce accidents and improve safety [3][4][5][6][7] .…”

Dynamic Analysis of Street Trees in Vehicle-mounted LiDAR Point Clouds

“…However, this method is limited by image resolution and has poor general applicability, making it unsuitable for widespread application. In 2014, Yang Shasha [6] analyzed different features of various objects and performed feature segmentation based on vehiclemounted LiDAR data. By projecting 3D graphics onto a 2D plane for processing and using Matable programming, tree information was extracted.…”