Driving area detection method, device and equipment

Abstract

The invention provides a drivable area detection method, device and equipment, and the method comprises the steps: obtaining a three-dimensional point cloud of a target detection area through a laser radar, determining the type label of each point in the three-dimensional point cloud through a semantic segmentation network, and enabling the type labels to comprise the ground and a ground object; determining the position of the laser radar as a coordinate origin, dividing the three-dimensional point cloud into different fan-shaped regions, and dividing each fan-shaped region into different grids according to the distance from the point to the origin; performing grid traversal on each fan-shaped region, and determining boundary points of a drivable region of each fan-shaped region based on type labels of points contained in grids; performing segmentation fitting on each boundary point, performing resampling on boundary lines after segmentation fitting according to a preset interval, and determining an envelope point set of a drivable area; according to the method, the problems of unstable road edge shielding identification, poor rugged road robustness, insufficient detection precision and the like in the prior art are effectively solved.

Description

technical field [0001] The present application relates to the technical field of automatic driving perception, and in particular, to a method, device and device for detecting a drivable area. Background technique [0002] Autonomous driving technology is a complex engineering system, which requires the cooperation of various modules to ensure the safety of driving in an all-round way. Among them, the free space detection technology is one of the key technologies of the autonomous driving system, which can provide a basis for back-end modules such as path planning and behavior decision-making. Camera images and LiDAR point clouds are currently the main data input sources used to detect drivable areas. In the method of extracting drivable areas based on images, the color or texture features used are easily disturbed by light and weather, and the lack of three-dimensional information also limits the adaptability of such algorithms in different scenarios. Lidar can provide ric...

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present application provides a drivable area detection method, device and equipment, which are used to solve the problems existing in the prior art such as unstable roadside occlusion recognition, poor robustness of undulating roads, and insufficient detection accuracy.

Images