With advances in precision agriculture, autonomous agricultural machines can reduce human labor, optimize workflow, and increase productivity. Accurate and reliable obstacle-detection and avoidance systems are essential for ensuring the safety of automated agricultural machines. Existing LiDAR-based obstacle detection methods for the farmland environment process the point clouds via manually designed features, which is time-consuming, labor-intensive, and weak in terms of generalization. In contrast, deep learning has a powerful ability to learn features autonomously. In this study, we attempted to apply deep learning in LiDAR-based 3D obstacle detection for the farmland environment. In terms of perception hardware, we established a data acquisition platform including LiDAR, a camera, and a GNSS/INS on the agricultural machine. In terms of perception method, considering the different agricultural conditions, we used our datasets to train an effective 3D obstacle detector, known as Focal Voxel R-CNN. We used focal sparse convolution to replace the original 3D sparse convolution because of its adaptable ability to extract effective features from sparse point cloud data. Specifically, a branch of submanifold sparse convolution was added to the upstream of the backbone convolution network; this adds weight to the foreground point and retains more valuable information. In comparison with Voxel R-CNN, the proposed Focal Voxel R-CNN significantly improves the detection performance for small objects, and the AP in the pedestrian class increased from 89.04% to 92.89%. The results show that our model obtains an mAP of 91.43%, which is 3.36% higher than the base model. The detection speed is 28.57 FPS, which is 4.18 FPS faster than the base model. The experiments show the effectiveness of our model, which can provide a more reliable obstacle detection model for autonomous agricultural machines.
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.