Lane line detection method based on improved SCNN network

Abstract

The invention discloses a lane line detection method based on an improved SCNN network, and the method comprises the steps: selecting a CULane lane line data set as a training data set for the training of the improved SCNN network; constructing an improved SCNN network, classifying different lane line features, and outputting lane line candidate points; classifying the lane lines by adopting a lane line seed point classification method; and based on the classified lane line candidate points obtained by the lane line seed point classification method, using a weighted least square method to carry out fitting on the lane line containers to obtain a lane line model of each lane line container so as to realize accurate positioning of the lane lines. According to the method, the processing speedof the network structure is improved on the premise that the accuracy of the SCNN network framework is not lost, and the method has good robustness and real-time performance, can be popularized and applied to systems such as a driving assistance system and has wide practicability.

Description

technical field [0001] The invention relates to the technical field of image recognition of road traffic, in particular to a lane line detection method based on an improved SCNN network. Background technique [0002] As automobiles become one of the main tools for people to travel, the increase in the number of automobiles is also accompanied by the occurrence of related social problems. The frequent occurrence of traffic accidents also makes people pay more and more attention to traffic safety issues. At present, relatively mature advanced driving assistance technologies include lane departure warning, adaptive cruise control, front collision warning, pedestrian detection, and lane keeping assistance. Among them, the lane detection system is an important basis for realizing the related functions of assisted driving. In a structured road environment, driving a vehicle in the lane can ensure the orderly driving of the vehicle, and whether the lane line can be detected quickl...

AI Technical Summary

Problems solved by technology

Due to the slender shape of the lane line, if the detection method is used, there are the following problems: the detection of the lane line needs to be accurately positioned, and the detected bounding box cannot meet the application requirements; The amount of information in the area is small, and the characteristics of the lane line cannot be fully learned

However, for slender objects like lane lines, the spatial shape features are obvious, but the appearance features are few, and the segmentation effect still needs to be improved.

Images