Research map / Detection and segmentation / 3D detection and driving
Robust Small Object Detection on the Water Surface Through Fusion of Camera and Millimeter Wave Radar
Yuwei Cheng, Hu Xu, Yimin Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| fuse radar with image instead of image only | YOLOv4 · Floating bottle dataset | AP35: 78.46 -> 90.05 | Improved |
| use radar point density map (range, velocity, energy) instead of only density map (ablation) | RISFNet · Floating bottle dataset | AP35: 82.48 -> 90.05 | Improved |
| use radar point density map instead of binary radar sparse image (ablation) | RISFNet · Floating bottle dataset | AP50: 69.58 -> 75.09 | Improved |
| add velocity and energy channels to range density map (ablation) | RISFNet · Floating bottle dataset | AP50: 72.20 -> 75.09 | Improved |
| use separate image and radar backbones instead of one backbone (ablation) | RISFNet · Floating bottle dataset | AP35: 82.81 -> 90.05 | Improved |
| add multi-frame radar input instead of a single frame (ablation) | RISFNet · Floating bottle dataset | AP50: 68.83 -> 75.09 | Improved |
| add temporal position encoding (ablation) | RISFNet · Floating bottle dataset | AP50: 72.24 -> 75.09 | Improved |
| add self-attention block on radar features (ablation) | RISFNet · Floating bottle dataset | AP50: 71.38 -> 75.09 | Improved |
| add global attention fusion module (ablation) | RISFNet · Floating bottle dataset | AP35: 88.95 -> 90.05 | Improved |
| add global attention fusion module under degraded sensor data (ablation) | RISFNet · Floating bottle dataset | AP35: 87.34 -> 90.05 | Improved |
| use RISFNet instead of Li et al. radar-vision fusion on nuScenes mini | RISFNet · nuScenes mini | mAP: 24.3 -> 28.25 | Improved |
| use RISFNet instead of Li et al. radar-vision fusion on floating bottle data | RISFNet · Floating bottle dataset | AP50: 64.64 -> 75.09 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FCOS — FCOS: Fully Convolutional One-Stage Object Detection (ICCV 2019) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- HGSFusion: Radar-Camera Fusion with Hybrid Generation and Synchronization for 3D Object Detection (AAAI 2025 · similarity 0.86)
- RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detection (CVPR 2024 · similarity 0.85)
- CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for 3D Object Detection (NeurIPS 2024 · similarity 0.84)
- RobuRCDet: Enhancing Robustness of Radar-Camera Fusion in Bird's Eye View for 3D Object Detection (ICLR 2025 · similarity 0.83)
- TransLoc4D: Transformer-based 4D Radar Place Recognition (CVPR 2024 · similarity 0.83)
- RaCFormer: Towards High-Quality 3D Object Detection via Query-based Radar-Camera Fusion (CVPR 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
