Zebra crossing correction method, electronic device and storage medium

Abstract

The invention discloses an electronic device, a zebra crossing correction method and a storage medium, and the method comprises the steps: obtaining crowdsourcing track data which comprises the trackdata of a plurality of vehicles, wherein the track data of each vehicle comprise a plurality of track points; preprocessing the trajectory data of each vehicle to obtain preprocessed crowdsourcing trajectory data; removing a U-turn track from the preprocessed crowdsourcing track data to obtain removed crowdsourcing track data; acquiring acquired zebra crossing data; according to the zebra crossingdata and the removed crowdsourcing trajectory data, adjusting the zebra crossing data to obtain an adjusted zebra crossing; obtaining a central point set of the adjusted zebra crossing; clustering the adjusted center point set of the zebra crossing, and determining a clustering center point; and determining a new zebra crossing according to the clustering center point, the adjusted zebra crossingand the removed crowdsourcing trajectory data. The zebra crossing drawing method can improve zebra crossing drawing precision.

Description

technical field [0001] The invention relates to the field of automatic driving, in particular to a zebra crossing correction method, an electronic device and a storage medium. Background technique [0002] In the field of autonomous driving, in order to accurately control the driving of vehicles, the drawing of high-precision maps is often involved. In the process of drawing high-precision maps, the zebra crossing data of high-precision maps are needed to provide data support for the driving behavior decision-making of autonomous vehicles. The drawing cost of the crowdsourcing collection vehicle is low, and the collected traffic facility data is usually of poor accuracy, and the data collected through the same traffic facility multiple times will also have a certain offset due to factors such as GPS signals or vehicle speeds each time. The zebra crossing results after class processing often deviate greatly from the actual position. Therefore, it is necessary to integrate th...

AI Technical Summary

Problems solved by technology

The drawing cost of the crowdsourcing collection vehicle is low, and the collected traffic facility data is usually of poor accuracy, and the data collected through the same traffic facility multiple times will also have a certain offset due to factors such as GPS signals or vehicle speeds each time. The results of the zebra crossing after class processing often deviate greatly from the actual position

Images