arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.00871cs.CV
收藏

三维目标检测中的密集体素融合

Dense Voxel Fusion for 3D Object Detection

University of Toronto(多伦多大学)

Anas Mahmoud, Jordan S. K. Hu, Steven L. Waslander

摘要:

相机和LiDAR传感器模态提供了互补的外观和几何信息,可用于检测自动驾驶汽车应用中的3D物体。然而,当前的端到端融合方法在训练方面具有挑战性,并且性能低于最先进的仅有LiDAR的探测器。由于点云稀疏性,顺序融合方法遭受有限数量的像素和点对应,或者它们的性能被其中一种模态的检测严格限制。我们提出的解决方案,密集体素融合(DVF)是一种顺序融合方法,生成多尺度密集体素特征表示,提高低点密度区域的表现力。为了增强多模态学习,我们直接使用投影的地面实况3D限界框标签进行训练,避免了嘈杂的、特定于检测器的2D预测。DVF和多模态训练方法都可以应用于任何基于体素的LiDAR骨干。DVF在KITTI 3D汽车检测基准的已发布融合方法中排名第三,无需引入额外的可训练参数,也不需要立体图像或密集的深度标签。此外,DVF还显著提高了Waymo Open Dataset上基于体素方法的3D车辆检测性能。

英文摘要:

Camera and LiDAR sensor modalities provide complementary appearance and geometric information useful for detecting 3D objects for autonomous vehicle applications. However, current end-to-end fusion methods are challenging to train and underperform state-of-the-art LiDAR-only detectors. Sequential fusion methods suffer from a limited number of pixel and point correspondences due to point cloud sparsity, or their performance is strictly capped by the detections of one of the modalities. Our proposed solution, Dense Voxel Fusion (DVF) is a sequential fusion method that generates multi-scale dense voxel feature representations, improving expressiveness in low point density regions. To enhance multi-modal learning, we train directly with projected ground truth 3D bounding box labels, avoiding noisy, detector-specific 2D predictions. Both DVF and the multi-modal training approach can be applied to any voxel-based LiDAR backbone. DVF ranks 3rd among published fusion methods on KITTI 3D car detection benchmark without introducing additional trainable parameters, nor requiring stereo images or dense depth labels. In addition, DVF significantly improves 3D vehicle detection performance of voxel-based methods on the Waymo Open Dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑