arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.01802cs.CVcs.AI
收藏

MonoEdge:基于局部视角的单目3D目标检测

MonoEdge: Monocular 3D Object Detection Using Local Perspectives

TuSimple Inc(图森公司);University of Michigan(密歇根大学)

Minghan Zhu, Lingting Ge, Panqu Wang, Huei Peng

摘要:

我们提出了一种新的单目三维目标检测的方法,利用每个对象的局部透视效果。虽然显示为尺寸和位置变化的全局透视效应已被广泛用于单目3D检测,但局部透视一直被忽视。我们设计了一个局部透视模块,回归一个新定义的变量命名为keyedge-ratios作为局部形状失真的参数化,以考虑局部透视,并从中导出对象的深度和偏航角。理论上,该模块不依赖于像素的大小或位置的对象的图像,因此独立于相机的内部参数。通过将该模块插入到现有的单目3D目标检测框架中,我们将局部透视失真与全局透视效果结合起来进行单目3D推理,并在多个数据集上证明了强基线方法的有效性和优越性能。

英文摘要:

We propose a novel approach for monocular 3D object detection by leveraging local perspective effects of each object. While the global perspective effect shown as size and position variations has been exploited for monocular 3D detection extensively, the local perspectives has long been overlooked. We design a local perspective module to regress a newly defined variable named keyedge-ratios as the parameterization of the local shape distortion to account for the local perspective, and derive the object depth and yaw angle from it. Theoretically, this module does not rely on the pixel-wise size or position in the image of the objects, therefore independent of the camera intrinsic parameters. By plugging this module in existing monocular 3D object detection frameworks, we incorporate the local perspective distortion with global perspective effect for monocular 3D reasoning, and we demonstrate the effectiveness and superior performance over strong baseline methods in multiple datasets.

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。

↑