SOTAVerified

Multispectral Object Detection

Only using RGB cameras for automatic outdoor scene analysis is challenging when, for example, facing insufficient illumination or adverse weather. To improve the recognition reliability, multispectral systems add additional cameras (e.g. infra-red) and perform object detection from multispectral data. Although multispectral scene analysis with deep learning has be shown to have a great potential, there are still many open research questions and it has not been widely deployed in industrial contexts.

Papers

Showing 21–30 of 39 papers

TitleStatusHype
RGB-X Object Detection via Scene-Specific Fusion ModulesCode1
TFDet: Target-Aware Fusion for RGB-T Pedestrian DetectionCode1
Multispectral Detection Transformer with Infrared-Centric Sensor FusionCode0
Multispectral Pedestrian Detection via Simultaneous Detection and SegmentationCode0
CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic SegmentationCode0
Confidence-aware Fusion using Dempster-Shafer Theory for Multispectral Pedestrian DetectionCode0
Weakly Aligned Cross-Modal Learning for Multispectral Pedestrian DetectionCode0
Deep learning with RGB and thermal images onboard a drone for monitoring operations—0
Illumination-aware Faster R-CNN for Robust Multispectral Pedestrian Detection—0
RGB-T Object Detection via Group Shuffled Multi-receptive Attention and Multi-modal Supervision—0
Show:102550
← PrevPage 3 of 4Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MMPedestronmAP5086.4—Unverified
2RGB-X Scene Adaptive CBAMmAP5086.16—Unverified
3CAFF-DINOmAP5085.5—Unverified
4RSDetmAP5083.9—Unverified
5CMXmAP5082.2—Unverified
6UniRGB-IRmAP5081.4—Unverified
7MiPamAP5081.3—Unverified
8CSSAmAP5079.2—Unverified
9CFTmAP5077.7—Unverified
10ProbEnmAP5075.5—Unverified
#ModelMetricClaimedVerifiedStatus
1FusionRPN+BFAll Miss Rate51.7—Unverified
2Halfway FusionAll Miss Rate49.18—Unverified
3IATDNN+IASSAll Miss Rate48.96—Unverified
4IAFR-CNNAll Miss Rate44.23—Unverified
5CIANAll Miss Rate35.53—Unverified
6AR-CNNAll Miss Rate34.95—Unverified
7MSDS-R-CNNAll Miss Rate34.15—Unverified
8MBNetAll Miss Rate31.87—Unverified
9TSFADetAll Miss Rate30.74—Unverified
10CMPDAll Miss Rate28.98—Unverified
#ModelMetricClaimedVerifiedStatus
1YOLOv3-4‐channel[email protected]:0.9564.4—Unverified
2YOLOv3-Ensemble[email protected]:0.9553.4—Unverified
#ModelMetricClaimedVerifiedStatus
1CFTmAP5097.5—Unverified