Multiscale Region-Based Convolutional Neural Networks for 3D Object Detection with LiDAR Sensors
Open Access
Abstract
LiDAR-based 3D object detection is essential for autonomous driving vehicles under poor lighting conditions. With LiDAR data, point cloud technologies have become increasingly important, as LiDAR sensors are largely cost down. However, the sparsity of point cloud poses a challenge for 3D object detection, requiring advancements in sparse convolutional networks. Given that the multiscale feature fusion mechanism can improve object detection performance using rich information across scale features, we added a refinement fusion network with cross-attention modules to existing 3D voxel-based object detection networks. We also employed a realistic strategy to refine existing point cloud data augmentation techniques to enable the trained detection networks to achieve substantially improved results. The experimental results demonstrate the effectiveness of our proposed detection system across three categories on the KITTI dataset. These enhancements address the limitations of current approaches and highlight the superior performance of the proposed system.Keywords
All Related Versions
Funding Information
- National Science and Technology Council, Taiwan (NSTC 114-2221-E-006-105)
- National Science and Technology Council, Taiwan (NSTC 114-2221-E-017-009)
This publication has 10 references indexed in Scilit:
- IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection2024
- Efficient Detection and Tracking of Human Using 3D LiDAR SensorSensors, 2023
- CasA: A Cascade Attention Network for 3-D Object Detection From LiDAR Point CloudsIEEE Transactions on Geoscience and Remote Sensing, 2022
- TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers2022
- DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution2021
- Voxel R-CNN: Towards High Performance Voxel-based 3D Object DetectionProceedings of the AAAI Conference on Artificial Intelligence, 2021
- 3DSSD: Point-Based 3D Single Stage Object Detector2020
- PointPillars: Fast Encoders for Object Detection From Point Clouds2019
- Dynamic Multi-LiDAR Based Multiple Object Detection and TrackingSensors, 2019
- SECOND: Sparsely Embedded Convolutional DetectionSensors, 2018