Lidar-Based 3D Obstacle Detection Using Focal Voxel R-CNN for Farmland Environment
Open Access
Abstract
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.Keywords
Funding Information
- Beijing Municipal Science and Technology Project (Z201100008020008, 2021YFB3901302)
- National Key Research and Development Project (Z201100008020008, 2021YFB3901302)
This publication has 18 references indexed in Scilit:
- SECOND: Sparsely Embedded Convolutional DetectionSensors, 2018
- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection2018
- Focal Loss for Dense Object Detection2017
- DeepAnomaly: Combining Background Subtraction and Deep Learning for Detecting Obstacles and Anomalies in an Agricultural FieldSensors, 2016
- The obstacle detection and obstacle avoidance algorithm based on 2-D lidar2015
- Object Detection and Terrain Classification in Agricultural Fields Using 3D Lidar Data2015
- Development of prediction based emergency obstacle avoidance module by using LIDAR for mobile robot2014
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012
- Precision Agriculture and Food SecurityScience, 2010