Lifting Multi-View Detection and Tracking to the Bird's Eye View
Taking advantage of multi-view aggregation presents a promising solution to tackle challenges such as occlusion and missed detection in multi-object tracking and detection. Recent advancements in multi-view detection and 3D object recognition have significantly improved performance by strategically projecting all views onto the ground plane and conducting detection analysis from a Bird's Eye View. In this paper, we compare modern lifting methods, both parameter-free and parameterized, to multi-view aggregation. Additionally, we present an architecture that aggregates the features of multiple times steps to learn robust detection and combines appearance- and motion-based cues for tracking. Most current tracking approaches either focus on pedestrians or vehicles. In our work, we combine both branches and add new challenges to multi-view detection with cross-scene setups. Our method generalizes to three public datasets across two domains: (1) pedestrian: Wildtrack and MultiviewX, and (2) roadside perception: Synthehicle, achieving state-of-the-art performance in detection and tracking. https://github.com/tteepe/TrackTacular
PDF AbstractCode
Datasets
Wildtrack
MultiviewX
Synthehicle
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Multiview Detection | MultiviewX | TrackTacular (Bilinear Sampling) | MODA | 96.5 | # 1 | |
| MODP | 75.0 | # 7 | ||||
| Recall | 97.1 | # 2 | ||||
| Multi-Object Tracking | MultiviewX | TrackTacular (Bilinear Sampling) | IDF1 | 85.6 | # 1 | |
| MOTA | 92.4 | # 1 | ||||
| Multiview Detection | Wildtrack | TrackTacular (Depth Splatting) | MODA | 93.2 | # 3 | |
| MODP | 77.5 | # 4 | ||||
| Recall | 95.8 | # 3 | ||||
| Multi-Object Tracking | Wildtrack | TrackTacular (Bilinear Sampling) | IDF1 | 95.3 | # 1 | |
| MOTA | 91.8 | # 1 |
