HIVE-ECIA: Identity-Aware Historical Evidence Acquisition for Bandwidth-Efficient Multi-Object Tracking
Organizations: Ruhr-Universität Bochum · Posts & Telecommunications Institute of Technology
Abstract
Panoramic multi-object tracking (MOT) requires reliable identity association across a 360° field of view, yet bandwidth-constrained operation forces a trade-off between low-resolution (LR) identity ambiguity and costly high-resolution (HR) transmission. We propose HIVE-ECIA, an identity-aware framework that selectively retrieves historical HR evidence to recover fragmented identities without modifying detection boxes or the underlying tracker. An ECIA Base-Guided query policy determines when additional HR evidence is warranted; HIVE ranks historical LR observations to select an informative retrieval timestamp; and ECIA Full integrates the retrieved HR crop through learned gated fusion and conservative identity safeguards. We further introduce DualPano-MOT, a real-world dual-fisheye panoramic evaluation dataset featuring controlled pedestrian interactions, panorama-seam challenges, and occlusions, with model-assisted, manually verified tracking annotations. On held-out QuadTrack sequences and zero-shot DualPano-MOT, HIVE-ECIA improves identity association across four MOT trackers without tracker-specific retraining. Across these trackers, identity switches decrease by up to 21.8% and 23.4%, while the largest IDF1 gains reach 3.81 and 6.74 percentage points, respectively. Under an offline JPEG-based acquisition model, our framework reduces encoded data volume by 89.2% and 79.3% relative to continuous Full-HR acquisition.
Figures & tables
| Dataset | Pano. | MOT | Staged | Border | Trace |
| MOT17 [ 7 ] | ✗ | ✓ | – | – | – |
| 360VOT [ 11 ] | ✓ | ✗ | – | ✓ | – |
| JRDB [ 19 ] | ✓ | ✓ | – | – | ✓ |
| QuadTrack [ 17 ] | ✓ | ✓ | – | – | – |
| DualPano-MOT (Ours) | ✓ | ✓ | ✓ | ✓ | ✓ |
| Tracker | Identity Recovery | HOTA | IDF1 | AssA | MOTA | IDSW |
| QuadTrack (held-out, ) | ||||||
| SORT [ 3 ] | Raw tracker | 26.78 | 32.20 | 26.57 | 31.40 | 135 |
| HIVE–ECIA (Ours) † | 28.79 (+2.01) | 36.01 (+3.81) | 30.68 (+4.11) | 31.54 (+0.14) | 113 (-22) | |
| ByteTrack [ 27 ] | Raw tracker | 30.55 | 36.23 | 31.93 | 34.65 | 101 |
| HIVE–ECIA (Ours) † | 30.89 (+0.34) | 36.78 (+0.55) | 32.64 (+0.71) | 34.78 (+0.13) | 79 (-22) | |
| OC-SORT [ 6 ] | Raw tracker | 26.99 | 32.99 | 28.15 | 30.23 | 95 |
| Dataset | Variant | HOTA | IDF1 | IDSW | HR |
| A0 | 36.18 | 44.76 | 92 | 0 | |
| A1 | 36.32 | 44.85 | 86 | 0 | |
| A2 | 37.22 | 46.56 | 82 | 120 | |
| QuadTrack | A3 (Ours) | 37.25 | 46.63 | 78 | 29 |
| A0 | 34.22 | 35.20 | 94 | 0 | |
| A1 | 34.68 | 35.20 | 91 | 0 |
| Dataset | Selection | IDF1 | IDSW |
| Nearest | 44.92 | 84 | |
| LR heuristic | 46.26 | 81 | |
| QuadTrack | HIVE (Ours) | 46.63 | 78 |
| Nearest | 36.60 | 91 | |
| LR heuristic | 37.22 | 90 | |
| DualPano | HIVE (Ours) | 37.22 | 89 |
| Acquisition | IDF1 | IDSW | MB | Saving | FPS | Speedup |
| QuadTrack | ||||||
| LR-only | 44.76 | 92 | 51.31 | 89.26% | ||
| Full-HR | 48.30 | 376 | 477.64 | 0.00% | ||
| Periodic-HR ( ) | 43.00 | 198 | 136.63 | 71.39% | ||
| HIVE–ECIA (Ours) | 46.63 | 78 | 51.47 | 89.22% | ||
| DualPano-MOT | ||||||
| Parameter | HIVE | ECIA Full |
| Random seed | 42 | 42 |
| Max. epochs | 100 | 50 |
| Batch size | 8 | 128 |
| Learning rate | ||
| Weight decay | ||
| Gradient clipping | 5.0 | 1.0 |
| Dataset | Variant | HOTA | IDF1 | AssA | IDSW |
| QuadTrack | Base-only | 36.32 | 44.85 | 43.96 | 86 |
| Ungated ( ) | 37.29 | 46.67 | 46.37 | 75 | |
| Learned gate | 37.25 | 46.63 | 46.28 | 78 | |
| DualPano | Base-only | 34.68 | 35.20 | 23.32 | 91 |
| Ungated ( ) | 35.36 | 36.61 | 24.23 | 87 | |
| Learned gate | 35.25 | 37.22 | 24.08 | 89 |
| Detector | Tracker | HOTA | IDF1 | AssA | IDSW |
| YOLOv10-L | SORT | 24.79 24.84 +0.05 | 30.69 30.36 -0.33 | 29.76 29.87 +0.12 | 81 71 -10 |
| ByteTrack | 27.45 28.39 +0.94 | 31.85 33.29 +1.44 | 34.05 36.43 +2.38 | 84 63 -21 | |
| OC-SORT | 25.66 25.84 +0.18 | 30.47 30.62 +0.16 | 35.07 35.57 +0.50 | 65 58 -7 | |
| BoT-SORT | 30.24 30.32 +0.08 | 34.56 35.13 +0.57 | 39.97 40.22 +0.25 | 91 69 -22 | |
| YOLO11-L | SORT | 26.78 28.79 +2.01 | 32.20 36.01 +3.81 | 26.57 30.68 +4.11 | 135 113 -22 |
| ByteTrack | 30.55 30.89 +0.34 | 36.23 36.78 +0.55 | 31.93 32.64 +0.71 | 101 79 -22 |
| Detector | Tracker | HOTA | IDF1 | AssA | IDSW |
| YOLOv10-L | SORT | 36.87 41.13 +4.26 | 39.87 44.72 +4.84 | 24.96 30.99 +6.03 | 86 71 -15 |
| ByteTrack | 38.98 42.98 +4.00 | 40.09 44.50 +4.41 | 26.80 32.54 +5.74 | 79 73 -6 | |
| OC-SORT | 36.79 43.17 +6.38 | 40.11 47.42 +7.31 | 25.57 35.11 +9.54 | 78 61 -17 | |
| BoT-SORT | 37.32 40.89 +3.57 | 39.55 44.37 +4.81 | 25.45 30.48 +5.03 | 101 94 -7 | |
| YOLO11-L | SORT | 33.58 40.27 +6.69 | 35.08 41.82 +6.74 | 22.25 31.89 +9.64 | 103 88 -15 |
| ByteTrack | 34.04 35.56 +1.52 | 32.25 35.44 +3.19 | 21.88 23.85 +1.97 | 85 76 -9 |
Multi-Object Tracking
Multi-object tracking (MOT) links detections across video frames to maintain object identities through motion, occlusion, and changing viewpoints.
See all 203 papers