In this paper, we investigate the problem of weakly supervised 3D vehicle detection. Conventional methods for 3D object detection need vast amounts of manually labelled 3D data as supervision signals. However, annotating large datasets requires huge human efforts, especially for 3D area. To tackle this problem, we propose frustum-aware geometric reasoning (FGR) to detect vehicles in point clouds without any 3D annotations. Our method consists of two stages: coarse 3D segmentation and 3D bounding box estimation. For the first stage, a context-aware adaptive region growing algorithm is designed to segment objects based on 2D bounding boxes. Leveraging predicted segmentation masks, we develop an anti-noise approach to estimate 3D bounding boxes in the second stage. Finally 3D pseudo labels generated by our method are utilized to train a 3D detector. Independent of any 3D groundtruth, FGR reaches comparable performance with fully supervised methods on the KITTI dataset. The findings indicate that it is able to accurately detect objects in 3D space with only 2D bounding boxes and sparse point clouds.
翻译:在本文中,我们调查三维对象探测的常规方法需要大量人工标记的三维数据作为监督信号。然而,指出大型数据集需要巨大的人力努力,特别是在三维区域。为了解决这个问题,我们提出了在无任何三维注解的情况下在点云中探测车辆的正方形测深推理(FGR)建议。我们的方法包括两个阶段:粗3D分解和3D捆绑框估计。在第一阶段,根据基于 2D 捆绑框的分块物体设计出一种符合环境的适应性区域增长算法。利用预测的分解遮罩,我们开发了一种反噪音方法来估计第二阶段的三维界限箱。最后,我们的方法产生的3D假标签被用于训练三维探测器。除了任何三维地心外,FGR都达到与KITTI数据集上完全受监督的方法相类似的性能。调查结果表明,它能够精确地探测三维空间的物体,只有2D 捆绑框和稀少的云层。