Pre-Segmented Down-Sampling Accelerates Graph Neural Network-Based 3D Object Detection in Autonomous Driving
Graph neural networks (GNNs) have been proven to be an ideal approach to deal with irregular point clouds, but involve massive computations for searching neighboring points in the graph, which limits their application in large-scale LiDAR point cloud processing. Down-sampling is a straightforward an...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/5/1458 |
| _version_ | 1797263892072628224 |
|---|---|
| author | Zhenming Liang Yingping Huang Yanbiao Bai |
| author_facet | Zhenming Liang Yingping Huang Yanbiao Bai |
| author_sort | Zhenming Liang |
| collection | DOAJ |
| description | Graph neural networks (GNNs) have been proven to be an ideal approach to deal with irregular point clouds, but involve massive computations for searching neighboring points in the graph, which limits their application in large-scale LiDAR point cloud processing. Down-sampling is a straightforward and indispensable step in current GNN-based 3D detectors to reduce the computational burden of the model, but the commonly used down-sampling methods cannot distinguish the categories of the LiDAR points, which leads to an inability to effectively improve the computational efficiency of the GNN models without affecting their detection accuracy. In this paper, we propose (1) a LiDAR point cloud pre-segmented down-sampling (PSD) method that can selectively reduce background points while preserving the foreground object points during the process, greatly improving the computational efficiency of the model without affecting its 3D detection accuracy. (2) A lightweight GNN-based 3D detector that can extract point features and detect objects from the raw down-sampled LiDAR point cloud directly without any pre-transformation. We test the proposed model on the KITTI 3D Object Detection Benchmark, and the results demonstrate its effectiveness and efficiency for autonomous driving 3D object detection. |
| first_indexed | 2024-04-25T00:20:13Z |
| format | Article |
| id | doaj.art-8b86a6e781424ddb9a3465caae77a2ee |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-25T00:20:13Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-8b86a6e781424ddb9a3465caae77a2ee2024-03-12T16:54:50ZengMDPI AGSensors1424-82202024-02-01245145810.3390/s24051458Pre-Segmented Down-Sampling Accelerates Graph Neural Network-Based 3D Object Detection in Autonomous DrivingZhenming Liang0Yingping Huang1Yanbiao Bai2School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, ChinaSchool of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, ChinaSchool of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, ChinaGraph neural networks (GNNs) have been proven to be an ideal approach to deal with irregular point clouds, but involve massive computations for searching neighboring points in the graph, which limits their application in large-scale LiDAR point cloud processing. Down-sampling is a straightforward and indispensable step in current GNN-based 3D detectors to reduce the computational burden of the model, but the commonly used down-sampling methods cannot distinguish the categories of the LiDAR points, which leads to an inability to effectively improve the computational efficiency of the GNN models without affecting their detection accuracy. In this paper, we propose (1) a LiDAR point cloud pre-segmented down-sampling (PSD) method that can selectively reduce background points while preserving the foreground object points during the process, greatly improving the computational efficiency of the model without affecting its 3D detection accuracy. (2) A lightweight GNN-based 3D detector that can extract point features and detect objects from the raw down-sampled LiDAR point cloud directly without any pre-transformation. We test the proposed model on the KITTI 3D Object Detection Benchmark, and the results demonstrate its effectiveness and efficiency for autonomous driving 3D object detection.https://www.mdpi.com/1424-8220/24/5/14583D object detectionautonomous drivingLiDAR point cloud down-samplinggraph neural network |
| spellingShingle | Zhenming Liang Yingping Huang Yanbiao Bai Pre-Segmented Down-Sampling Accelerates Graph Neural Network-Based 3D Object Detection in Autonomous Driving Sensors 3D object detection autonomous driving LiDAR point cloud down-sampling graph neural network |
| title | Pre-Segmented Down-Sampling Accelerates Graph Neural Network-Based 3D Object Detection in Autonomous Driving |
| title_full | Pre-Segmented Down-Sampling Accelerates Graph Neural Network-Based 3D Object Detection in Autonomous Driving |
| title_fullStr | Pre-Segmented Down-Sampling Accelerates Graph Neural Network-Based 3D Object Detection in Autonomous Driving |
| title_full_unstemmed | Pre-Segmented Down-Sampling Accelerates Graph Neural Network-Based 3D Object Detection in Autonomous Driving |
| title_short | Pre-Segmented Down-Sampling Accelerates Graph Neural Network-Based 3D Object Detection in Autonomous Driving |
| title_sort | pre segmented down sampling accelerates graph neural network based 3d object detection in autonomous driving |
| topic | 3D object detection autonomous driving LiDAR point cloud down-sampling graph neural network |
| url | https://www.mdpi.com/1424-8220/24/5/1458 |
| work_keys_str_mv | AT zhenmingliang presegmenteddownsamplingacceleratesgraphneuralnetworkbased3dobjectdetectioninautonomousdriving AT yingpinghuang presegmenteddownsamplingacceleratesgraphneuralnetworkbased3dobjectdetectioninautonomousdriving AT yanbiaobai presegmenteddownsamplingacceleratesgraphneuralnetworkbased3dobjectdetectioninautonomousdriving |