Monocular 3D object detection plays a pivotal role in autonomous driving,presenting a formidable challenge by requiring the precise localization of 3D objects within a single image,devoid of depth information.Most exi...Monocular 3D object detection plays a pivotal role in autonomous driving,presenting a formidable challenge by requiring the precise localization of 3D objects within a single image,devoid of depth information.Most existing methods in this domain fall short of harnessing the limited information available in monocular 3D detection tasks.They typically provide only a single detection outcome,omitting essential uncertainty analysis and result post-processing during model inference,thus limiting overall model performance.In this paper,we propose a comprehensive framework that maximizes information extraction from monocular images while encompassing diverse depth estimation and incorporating uncertainty analysis.Specifically,we mine additional information intrinsic to the monocular 3D detection task to augment supervision,thereby addressing the information scarcity challenge.Moreover,our framework handles depth estimation by recovering multiple sets of depth values from calculated visual heights.The final depth estimate and 3D confidence are determined through an uncertainty fusion process,effectively reducing inference errors.Furthermore,to address task weight allocation in multi-task training,we present a versatile training strategy tailored to monocular 3D detection.This approach leverages measurement indicators to monitor task progress,adaptively adjusting loss weights for different tasks.Experimental results on the KITTI and Waymo dataset confirm the effectiveness of our approach.The proposed method consistently provides enhanced performance across various difficulty levels compared to the original framework while maintaining realtime efficiency.展开更多
基金supported by the Young Scientists Fund of the National Natural Science Foundation of China(No.62203289)Shanghai Sailing Program(No.22YF1413800)+1 种基金National Natural Science Foundation of China(No.52371371)Shanghai Municipal Natural Science Foundation(No.21ZR1423300).
文摘Monocular 3D object detection plays a pivotal role in autonomous driving,presenting a formidable challenge by requiring the precise localization of 3D objects within a single image,devoid of depth information.Most existing methods in this domain fall short of harnessing the limited information available in monocular 3D detection tasks.They typically provide only a single detection outcome,omitting essential uncertainty analysis and result post-processing during model inference,thus limiting overall model performance.In this paper,we propose a comprehensive framework that maximizes information extraction from monocular images while encompassing diverse depth estimation and incorporating uncertainty analysis.Specifically,we mine additional information intrinsic to the monocular 3D detection task to augment supervision,thereby addressing the information scarcity challenge.Moreover,our framework handles depth estimation by recovering multiple sets of depth values from calculated visual heights.The final depth estimate and 3D confidence are determined through an uncertainty fusion process,effectively reducing inference errors.Furthermore,to address task weight allocation in multi-task training,we present a versatile training strategy tailored to monocular 3D detection.This approach leverages measurement indicators to monitor task progress,adaptively adjusting loss weights for different tasks.Experimental results on the KITTI and Waymo dataset confirm the effectiveness of our approach.The proposed method consistently provides enhanced performance across various difficulty levels compared to the original framework while maintaining realtime efficiency.
