Multi-surface mark fusion-based lane level locating method

Abstract

The invention discloses a multi-surface mark fusion-based lane level locating method. The method comprises the steps of 1, obtaining a vehicle road image; 2, performing grayscale processing and filtering processing on the road image; 3, performing lane line detection on the processed road image in the step 2; 4, performing stop line detection on the road image; 5, performing zebra crossing detection on the road image; and 6, locating the position of a vehicle in a lane in real time according to a lane line, a zebra crossing and a stop line. According to the method, information of multiple mark lines of a road is fused for performing accurate road lane line locating; and the method not only can be suitable for a driving safety pre-warning function of the vehicle but also can be fused in a pure vision system in unmanned driving to perform lane line patrol and turning at the intersection.

Description

technical field [0001] The invention belongs to the field of intelligent assisted driving technology and automatic driving technology, and in particular relates to a lane-level positioning method based on fusion of multiple ground signs. Background technique [0002] In recent years, advancements in autonomous driving technology have attracted the attention and interest of researchers, the media, and the general public. In 2015, Google's self-driving car officially drove on the roads of California, USA for testing. Other major automakers and companies have generally acknowledged that it is only a matter of time before self-driving cars enter people's lives and profoundly affect people's living conditions. Vehicle localization plays a fundamental and critical role in intelligent transportation systems as it is a higher level pre-mission operation. Previously, most positioning methods relied on GNSS and inertial navigation systems, but when GPS loses signal under certain cir...

AI Technical Summary

Problems solved by technology

Previously, most positioning methods relied on GNSS and INS, but when GPS loses signal under certain circumstances, they cannot continue to estimate the position of the vehicle

Images