Object Tracking
Object tracking is the task of taking an initial set of object detections, creating a unique ID for each of the initial detections, and then tracking each of the objects as they move around frames in a video, maintaining the ID assignment. State-of-the-art methods involve fusing data from RGB and event-based cameras to produce more reliable object tracking. CNN-based models using only RGB images as input are also effective. The most popular benchmark is OTB. There are several evaluation metrics specific to object tracking, including HOTA, MOTA, IDF1, and Track-mAP.
( Image credit: Towards-Realtime-MOT )
Papers
Showing 26–50 of 1966 papers
All datasetsCOESOTFE108QuadTrackSeaDronesSeeBIRDSAI - ICVGIP 2020KITTIMMPTRACKPerception TestVisEvent
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | HR-CEUTrack-Large | Success Rate | 65 | — | Unverified |
| 2 | HR-CEUTrack-Base | Success Rate | 63.2 | — | Unverified |
| 3 | CEUTrack-Large | Success Rate | 62.8 | — | Unverified |
| 4 | CEUTrack-Base | Success Rate | 62 | — | Unverified |
| 5 | SiamR-CNN | Success Rate | 60.9 | — | Unverified |
| 6 | TransT | Success Rate | 60.5 | — | Unverified |
| 7 | SuperDiMP | Success Rate | 60.2 | — | Unverified |
| 8 | TrDiMP | Success Rate | 60.1 | — | Unverified |
| 9 | KeepTrack | Success Rate | 59.6 | — | Unverified |
| 10 | AiATrack | Success Rate | 59 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | HR-MonTrack-Base | Success Rate | 68.5 | — | Unverified |
| 2 | HR-MonTrack-Tiny | Success Rate | 66.3 | — | Unverified |
| 3 | Multi-modal | Success Rate | 63.4 | — | Unverified |
| 4 | PrDiMP | Success Rate | 59 | — | Unverified |
| 5 | DiMP | Success Rate | 57.1 | — | Unverified |
| 6 | MonTrack | Success Rate | 54.9 | — | Unverified |
| 7 | ATOM | Success Rate | 46.5 | — | Unverified |
| 8 | KYS | Success Rate | 26.6 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | OmniTrack | HOTA | 23.45 | — | Unverified |
| 2 | DeepSORT | HOTA | 21.16 | — | Unverified |
| 3 | OC-SORT | HOTA | 20.83 | — | Unverified |
| 4 | ByteTrack | HOTA | 20.66 | — | Unverified |
| 5 | TrackFormer | HOTA | 19.62 | — | Unverified |
| 6 | HybridSORT | HOTA | 16.64 | — | Unverified |
| 7 | DiffMOT | HOTA | 16.4 | — | Unverified |
| 8 | Bot-SORT | HOTA | 15.77 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | final | Humans | 0.14 | — | Unverified |
| 2 | night_fury | Humans | 0.05 | — | Unverified |
| 3 | Yolo based method | Humans | 0.02 | — | Unverified |
| 4 | final | Humans | 0 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Siam-FC | Average IOU | 0.66 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | RT-MDNet | Precision Plot | 0.63 | — | Unverified |