AI Paper Atlas

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

ICCV 2021 · Detection and segmentation › 3D detection and driving · approach: Camera-radar fusion detection · 110 citations (OpenAlex)

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 changedWhereMeasuredEffect
fuse radar with image instead of image onlyYOLOv4 · Floating bottle datasetAP35: 78.46 -> 90.05Improved
use radar point density map (range, velocity, energy) instead of only density map (ablation)RISFNet · Floating bottle datasetAP35: 82.48 -> 90.05Improved
use radar point density map instead of binary radar sparse image (ablation)RISFNet · Floating bottle datasetAP50: 69.58 -> 75.09Improved
add velocity and energy channels to range density map (ablation)RISFNet · Floating bottle datasetAP50: 72.20 -> 75.09Improved
use separate image and radar backbones instead of one backbone (ablation)RISFNet · Floating bottle datasetAP35: 82.81 -> 90.05Improved
add multi-frame radar input instead of a single frame (ablation)RISFNet · Floating bottle datasetAP50: 68.83 -> 75.09Improved
add temporal position encoding (ablation)RISFNet · Floating bottle datasetAP50: 72.24 -> 75.09Improved
add self-attention block on radar features (ablation)RISFNet · Floating bottle datasetAP50: 71.38 -> 75.09Improved
add global attention fusion module (ablation)RISFNet · Floating bottle datasetAP35: 88.95 -> 90.05Improved
add global attention fusion module under degraded sensor data (ablation)RISFNet · Floating bottle datasetAP35: 87.34 -> 90.05Improved
use RISFNet instead of Li et al. radar-vision fusion on nuScenes miniRISFNet · nuScenes minimAP: 24.3 -> 28.25Improved
use RISFNet instead of Li et al. radar-vision fusion on floating bottle dataRISFNet · Floating bottle datasetAP50: 64.64 -> 75.09Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy