Automatic extraction method for road vector mark lines in vehicle-mounted laser scanning point cloud

Abstract

The invention discloses an automatic extraction method for road vector mark lines in a vehicle-mounted laser scanning point cloud. According to the method, the framework of the road vector mark lines in the current image is extracted through self-adaptive threshold segmentation based on the road spatial form, direction constrained expansion and corrosion and refinement and other image processing methods according to intensity-based feature images generated by original road laser scanning point cloud data; the road vector mark lines are extracted by using an object-oriented method, and extraction of the road vector mark lines is performed through combination of the geometrical characteristics of the mark lines; and the shorter road vector mark lines are expressed by single line segments according to the principle of a ransac algorithm, and the long road vector mark lines are expressed by multiple continuous broken line segments so that the positions of the road vector mark lines are extracted. The mass laser scanning point cloud data of the roads and the two sides are rapidly acquired without influencing the traffic condition, information of the road vector mark lines is extracted and the three-dimensional space coordinates of the road vector mark lines are recorded so that operation is simple and feasibility is high.

Description

technical field [0001] The invention belongs to the technical field of vehicle-mounted laser scanning point cloud data processing, and in particular relates to a method for automatically extracting road vector marking lines in a vehicle-mounted laser scanning point cloud. Background technique [0002] The extraction of road vector marking lines is one of the key technologies in the fields of vehicle intelligent driving, traffic management and 3D modeling of road environment. Current research mainly focuses on detecting and tracking lane lines from video images, but the road vector marking lines detected from images mainly record the two-dimensional plane information of the marking lines instead of three-dimensional information, which has been unable to meet the needs of intelligent vehicles. The needs of assisted driving and traffic management. As an advanced measurement method, the vehicle-mounted mobile laser measurement system has the characteristics of fast, non-contact...

AI Technical Summary

Problems solved by technology

At present, the processing of vehicle-mounted laser scanning data mainly focuses on the extraction of building facade information, and the extraction of road traffic vector marking lines is mostly based on the overall intensity image segmentation technology of the road, without systematic analysis considering the space of road and road surface marking lines Morphological characteristics, there are few related studies, and a mature extraction method has not yet been formed

Images