An Improved RODNet for Object Detection Based on Radar and Camera Fusion
Open Access
Abstract
Deep learning-based radar detection often suffers from poor cross-device generalization due to hardware heterogeneity. To address this, we propose a unified framework that combines rigorous calibration with adaptive temporal modeling. The method integrates three coordinated steps: (1) ensuring precise spatial alignment via improved Perspective-n-Point (PnP) calibration with closed-loop verification; (2) unifying signal statistics through multi-range bin calibration and chirp-wise Z-score standardization; and (3) enhancing feature consistency using a lightweight global–temporal adapter (GTA) driven by global gating and three-point attention. By combining signal-level standardization with feature-level adaptation, our framework achieves 86.32% average precision (AP) on the ROD2021 dataset. It outperforms the E-RODNet baseline by 22.88 percentage points with a 0.96% parameter increase, showing strong generalization across diverse radar platforms.Keywords
Funding Information
- Hainan Province Science and Technology Special Fund (ZDYF2023GXJS159)
- Hainan Province Science and Technology Special Fund (ZDYF2023GXJS168)
This publication has 31 references indexed in Scilit:
- Radar-camera fusion for 3D object detection with aggregation transformerApplied Intelligence, 2024
- Perception and sensing for autonomous vehicles under adverse weather conditions: A surveyISPRS Journal of Photogrammetry and Remote Sensing, 2023
- CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection2022
- Domain Adaptive Object Detection via Asymmetric Tri-Way Faster-RCNN2020
- EfficientDet: Scalable and Efficient Object Detection2020
- CBAM: Convolutional Block Attention Module2018
- Squeeze-and-Excitation Networks2018
- Deep Residual Learning for Image Recognition2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- MIMO Radar Signal Processing2008