# Object Detection Tracking Evaluation on nuScenes (val) Source: [Object Detection Tracking Evaluation on nuScenes (val)]() Collection index: [llms.txt]() Data updated: 2026-03-31T10:43:34.858Z Evaluation of object detection results on the nuScenes validation set, focusing specifically on tracking performance metrics, including false positive/negative counts, critical event tracking errors, and effort-based metrics for tracking consistency. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Object Detection | | Dataset (including any stated split) | nuScenes (val) | | Metric | FN Count | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 6 of 6 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [FN Count](): Lower is better; unit: SCALAR. - [FP Count](): Lower is better; unit: SCALAR. - [Critical FN Count](): Lower is better; unit: SCALAR. - [Critical FP Count](): Lower is better; unit: SCALAR. - [TC](): Lower is better; unit: SCALAR. - [Mean Effort MDR](): Lower is better; unit: SCALAR. - [Mean Effort FSR](): Lower is better; unit: SCALAR. - [Mean Effort LEA](): Lower is better; unit: SCALAR. - [Cumulative Effort MDR](): Lower is better; unit: SCALAR. - [Cumulative Effort FSR](): Lower is better; unit: SCALAR. - [Cumulative Effort LEA](): Lower is better; unit: SCALAR. - [Worst Event MDR](): Lower is better; unit: SCALAR. - [Worst Event FSR](): Lower is better; unit: SCALAR. - [Worst Event LEA](): Lower is better; unit: SCALAR. - [Precision (Prec.)](): Higher is better; unit: PERCENT. - [Recall (Rec.)](): Higher is better; unit: PERCENT. ## Recorded results | Method | FN Count | Result date | Report paper | | --- | --- | --- | --- | | AB3DMOT | 644 | Not recorded | 69cb553b0636e5bf4afca0f9 | | CenterPoint | 654 | Not recorded | 69cb553b0636e5bf4afca0f9 | | BEVFusion | 687 | Not recorded | 69cb553b0636e5bf4afca0f9 | | AB3DMOT | 3252 | Not recorded | 69cb553b0636e5bf4afca0f9 | | CenterPoint | 3554 | Not recorded | 69cb553b0636e5bf4afca0f9 | | BEVFusion | 3865 | Not recorded | 69cb553b0636e5bf4afca0f9 | ### AB3DMOT FN Count: 644. Result ID: 69cba54347f34ce924b4a7b8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pipeline":"AB3DMOT","Modality":"LiDAR","Class":"Truck"}. This record does not assert independent reproduction. ### CenterPoint FN Count: 654. Result ID: 69cba54347f34ce924b4a7ba. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pipeline":"CenterPoint","Modality":"LiDAR","Class":"Truck"}. This record does not assert independent reproduction. ### BEVFusion FN Count: 687. Result ID: 69cba54347f34ce924b4a7bc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pipeline":"BEVFusion","Modality":"LiDAR + Camera","Class":"Truck"}. This record does not assert independent reproduction. ### AB3DMOT FN Count: 3252. Result ID: 69cba54347f34ce924b4a7b7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pipeline":"AB3DMOT","Modality":"LiDAR","Class":"Car"}. This record does not assert independent reproduction. ### CenterPoint FN Count: 3554. Result ID: 69cba54347f34ce924b4a7b9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pipeline":"CenterPoint","Modality":"LiDAR","Class":"Car"}. This record does not assert independent reproduction. ### BEVFusion FN Count: 3865. Result ID: 69cba54347f34ce924b4a7bb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pipeline":"BEVFusion","Modality":"LiDAR + Camera","Class":"Car"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.