Disentangling and Vectorization: A 3D Visual Perception Approach for Autonomous Driving Based on Surround-View Fisheye Cameras
This addresses the problem of low-cost urban autonomous driving by improving 3D object detection on fisheye images, though it appears incremental as it builds on existing monocular methods.
The paper tackled 3D visual perception for autonomous driving using surround-view fisheye cameras by breaking down the task into sub-tasks like contact point detection and proposing a Multidimensional Vector concept, achieving state-of-the-art accuracy with real-time performance.
The 3D visual perception for vehicles with the surround-view fisheye camera system is a critical and challenging task for low-cost urban autonomous driving. While existing monocular 3D object detection methods perform not well enough on the fisheye images for mass production, partly due to the lack of 3D datasets of such images. In this paper, we manage to overcome and avoid the difficulty of acquiring the large scale of accurate 3D labeled truth data, by breaking down the 3D object detection task into some sub-tasks, such as vehicle's contact point detection, type classification, re-identification and unit assembling, etc. Particularly, we propose the concept of Multidimensional Vector to include the utilizable information generated in different dimensions and stages, instead of the descriptive approach for the bird's eye view (BEV) or a cube of eight points. The experiments of real fisheye images demonstrate that our solution achieves state-of-the-art accuracy while being real-time in practice.