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 1–25 of 39 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | MMPedestron | mAP50 | 86.4 | — | Unverified |
| 2 | RGB-X Scene Adaptive CBAM | mAP50 | 86.16 | — | Unverified |
| 3 | CAFF-DINO | mAP50 | 85.5 | — | Unverified |
| 4 | RSDet | mAP50 | 83.9 | — | Unverified |
| 5 | CMX | mAP50 | 82.2 | — | Unverified |
| 6 | UniRGB-IR | mAP50 | 81.4 | — | Unverified |
| 7 | MiPa | mAP50 | 81.3 | — | Unverified |
| 8 | CSSA | mAP50 | 79.2 | — | Unverified |
| 9 | CFT | mAP50 | 77.7 | — | Unverified |
| 10 | ProbEn | mAP50 | 75.5 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | FusionRPN+BF | All Miss Rate | 51.7 | — | Unverified |
| 2 | Halfway Fusion | All Miss Rate | 49.18 | — | Unverified |
| 3 | IATDNN+IASS | All Miss Rate | 48.96 | — | Unverified |
| 4 | IAFR-CNN | All Miss Rate | 44.23 | — | Unverified |
| 5 | CIAN | All Miss Rate | 35.53 | — | Unverified |
| 6 | AR-CNN | All Miss Rate | 34.95 | — | Unverified |
| 7 | MSDS-R-CNN | All Miss Rate | 34.15 | — | Unverified |
| 8 | MBNet | All Miss Rate | 31.87 | — | Unverified |
| 9 | TSFADet | All Miss Rate | 30.74 | — | Unverified |
| 10 | CMPD | All Miss Rate | 28.98 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | YOLOv3-4‐channel | mAP@0.5:0.95 | 64.4 | — | Unverified |
| 2 | YOLOv3-Ensemble | mAP@0.5:0.95 | 53.4 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | CFT | mAP50 | 97.5 | — | Unverified |