Robust BEV 3D Object Detection for Vehicles with Tire Blow-Out

• Published in: Sensors (Basel, Switzerland) Vol. 24; no. 14; p. 4446
• Main Authors: Yang, Dongsheng, Fan, Xiaojie, Dong, Wei, Huang, Chaosheng, Li, Jun
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 09.07.2024
• Subjects: 3D object detection; bird’s-eye view; Calibration; Cameras; Geometry; Methods; tire blow-out; transformer; Vehicles; transformer; bird’s-eye view; tire blow-out; 3D object detection
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s24144446

The bird's-eye view (BEV) method, which is a vision-centric representation-based perception task, is essential and promising for future Autonomous Vehicle perception. It has advantages of fusion-friendly, intuitive, end-to-end optimization and is cheaper than LiDAR. The performance of existing BEV methods, however, would be deteriorated under the situation of a tire blow-out. This is because they quite rely on accurate camera calibration which may be disabled by noisy camera parameters during blow-out. Therefore, it is extremely unsafe to use existing BEV methods in the tire blow-out situation. In this paper, we propose a geometry-guided auto-resizable kernel transformer (GARKT) method, which is designed especially for vehicles with tire blow-out. Specifically, we establish a camera deviation model for vehicles with tire blow-out. Then we use the geometric priors to attain the prior position in perspective view with auto-resizable kernels. The resizable perception areas are encoded and flattened to generate BEV representation. GARKT predicts the nuScenes detection score (NDS) with a value of 0.439 on a newly created blow-out dataset based on nuScenes. NDS can still obtain 0.431 when the tire is completely flat, which is much more robust compared to other transformer-based BEV methods. Moreover, the GARKT method has almost real-time computing speed, with about 20.5 fps on one GPU.