Boosting Online 3D Multi-Object Tracking through Camera-Radar Cross Check
Not on the map. Why?
Abstract (arXiv)
In the domain of autonomous driving, the integration of multi-modal perception techniques based on data from diverse sensors has demonstrated substantial progress. Effectively surpassing the capabilities of state-of-the-art single-modality detectors through sensor fusion remains an active challenge. This work leverages the respective advantages of cameras in perspective view and radars in Bird's Eye View (BEV) to greatly enhance overall detection and tracking performance. Our approach, Camera-Radar Associated Fusion Tracking Booster (CRAFTBooster), represents a pioneering effort to enhance radar-camera fusion in the tracking stage, contributing to improved 3D MOT accuracy. The superior experimental results on the K-Radaar dataset, which exhibit 5-6% on IDF1 tracking performance gain, validate the potential of effective sensor fusion in advancing autonomous driving.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 30 of its 39 references that are in the map. First posted on arXiv 18 Jul 2024.
Builds on
30 of 39 references.
References · 30
- 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
- 2020Center-based 3D Object Detection and Trackingcited by 1,144
- 2022Planning-oriented Autonomous Drivingcited by 1,087
- 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
- 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 850
- 2023MovieChat: From Dense Token to Sparse Memory for Long Video Understandingcited by 542
- 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 466
- 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 459
- 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
- 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 439
- 2017Deep Layer Aggregationcited by 436
- 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 346
18 more
- 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 249
- 2022StrongSORT: Make DeepSORT Great Againcited by 213
- 2020EPNet: Enhancing Point Features with Image Semantics for 3D Object Detectioncited by 164
- 2020CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detectioncited by 147
- 2022Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?cited by 128
- 2022MeMOT: Multi-Object Tracking with Memorycited by 114
- 2023Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Drivingcited by 114
- 2022K-Radar: 4D Radar Object Detection for Autonomous Driving in Various Weather Conditionscited by 108
- 2020RADIATE: A Radar Dataset for Automotive Perception in Bad Weathercited by 100
- 2022TJ4DRadSet: A 4D Radar Dataset for Autonomous Drivingcited by 75
- 2021RadarScenes: A Real-World Radar Point Cloud Data Set for Automotive Applicationscited by 61
- 2022Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detectioncited by 50
- 2021RODNet: A Real-Time Radar Object Detection Network Cross-Supervised by Camera-Radar Fused Object 3D Localizationcited by 49
- 2022Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detectioncited by 48
- 2020CNN based Road User Detection using the 3D Radar Cubecited by 47
- 2023Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous Drivingcited by 37
- 2024MambaMOT: State-Space Model as Motion Predictor for Multi-Object Trackingcited by 8
- 2023Vision meets mmWave Radar: 3D Object Perception Benchmark for Autonomous Drivingcited by 4
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.