RDNet: Rotate-Groundtruth Augmentation and Decoupled Attention HEAD for 3D Object Detection
- 23 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. 12 (2) , 389-402
Abstract
LiDAR is one of the most important sensors in the field of autonomous driving and allows for better and more accurate perception of the changes in the surrounding environment. Most of the existing 3D object detection methods use data augmentation and feature fusion enhancement to improve the performance of detection, but the majority of the methods ignore the handling of sample imbalance problems during data augmentation. Also, the designed feature fusion and enhancement methods were not well suited to work with the enhancement methods. To this end, we developed a combined method involving data augmentation and feature enhancement. The designed approach has two main objectives: 1) to address the problem of unbalanced sample distribution in detection scenes through data augmentation, and 2) to enhance feature perception using a special feature enhancement module. Our proposed method solves the problem of class imbalance by directly increasing the number of pedestrian samples in the scene through mixed data augmentation, i.e., RG-Aug. In addition, we introduce the Decoupling and Attention Fusion module (DAF), which combines classification headers with high-level features and prediction branches with low-level features. Leverage data features between different layers of features to get a more robust feature representation. Finally, the multi-scale pyramid attention enhancement module is designed to achieve feature enhancement of multi-scale features by means of attention to improve the detection ability of small objects in the scene, especially the detection ability of pedestrians. Our method can achieve 1.57%, 2.16%, and 2.05% performance improvement on the KITTI dataset for Easy, Mod, and Hard samples, respectively. Furthermore, for the detection of pedestrians, our method has a significant competitive advantage over other state-of-the-art techniques with a mAP of 73.42%.Keywords
Funding Information
- Hubei Provincial Natural Science Foundation of China (2023AFB697)
- National Natural Science Foundation of China (62202348)
- National Natural Science Foundation of China (62272189)
- National Natural Science Foundation of China (62372206)
- Foundation of State Key Laboratory of Public Big Data (PBD2024-0503)
- Fundamental Research Funds for the Central Universities, JLU
This publication has 27 references indexed in Scilit:
- Multi-task feature-aligned head in one-stage object detectionSignal, Image and Video Processing, 2022
- VoteNet: A Deep Learning Label Fusion Method for Multi-atlas Segmentation2019
- LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving2019
- PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud2019
- Multi-Task Multi-Sensor Fusion for 3D Object Detection2019
- PointPillars: Fast Encoders for Object Detection From Point Clouds2019
- YOLO3D: End-to-End Real-Time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud2019
- Frustum PointNets for 3D Object Detection from RGB-D Data2018
- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection2018
- Multi-view 3D Object Detection Network for Autonomous Driving2017