arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.09412cs.CV
收藏

Det6D:一种用于提高地形鲁棒性的地面感知全姿态3D目标检测器

Det6D: A Ground-Aware Full-Pose 3D Object Detector for Improving Terrain Robustness

Harbin Institute of Technology Shenzhen(哈尔滨工业大学深圳)

Junyuan Ouyang, Haoyao Chen

摘要:

使用LiDAR进行精确的3D目标检测对于自动驾驶至关重要。现有的研究都是基于平世界假设。然而,实际的道路可能是复杂的陡峭路段,这打破了前提。目前的方法遭受性能下降,在这种情况下,由于难以正确地检测倾斜的地形上的对象。在这项工作中,我们提出了Det 6D,第一个没有空间和姿势限制的全自由度3D对象检测器,以提高地形鲁棒性。我们选择基于点的框架,通过建立他们的能力,在整个空间范围内检测对象。为了预测全角度姿态,包括俯仰和滚动,我们设计了一个地面感知方向分支,利用当地的地面约束。考虑到长尾非平坦场景数据汇集和6D姿态标注的困难,本文提出了一种利用平坦场景中记录的现有数据集合成非平坦地形的数据增强方法Slope-Aug。在不同数据集上的实验表明了该方法在不同地形条件下的有效性和鲁棒性。我们进一步进行了一个扩展实验,以探索网络如何预测两个额外的姿势。所提出的模块是现有的基于点的框架的即插即用。该代码可在https://github.com/HITSZ-NRSL/De6D上获得。

英文摘要:

Accurate 3D object detection with LiDAR is critical for autonomous driving. Existing research is all based on the flat-world assumption. However, the actual road can be complex with steep sections, which breaks the premise. Current methods suffer from performance degradation in this case due to difficulty correctly detecting objects on sloped terrain. In this work, we propose Det6D, the first full-degree-of-freedom 3D object detector without spatial and postural limitations, to improve terrain robustness. We choose the point-based framework by founding their capability of detecting objects in the entire spatial range. To predict full-degree poses, including pitch and roll, we design a ground-aware orientation branch that leverages the local ground constraints. Given the difficulty of long-tail non-flat scene data collection and 6D pose annotation, we present Slope-Aug, a data augmentation method for synthesizing non-flat terrain from existing datasets recorded in flat scenes. Experiments on various datasets demonstrate the effectiveness and robustness of our method in different terrains. We further conducted an extended experiment to explore how the network predicts the two extra poses. The proposed modules are plug-and-play for existing point-based frameworks. The code is available at https://github.com/HITSZ-NRSL/De6D.

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。

↑