Lane line detection method, device and system based on semantic segmentation and storage medium

The invention relates to the field of lane line detection, in particular to a lane line detection method and system based on semantic segmentation and a storage medium, and the method comprises the steps: carrying out the image binarization semantic segmentation of the feature data of an input image, obtaining the pixels of a lane line, predicting the output type of the lane line through combining with a data set, and calculating the classification probability; and dynamically adjusting a weight coefficient and a sphere radius of a clustering algorithm according to the classification probability and the change of the lane line direction, classifying the pixel points through the clustering algorithm, and parameterizing each lane line by adopting a curve fitting algorithm. According to the embodiment, for a complex traffic environment, semantic segmentation and an adaptive clustering method are combined, pixel-level recognition of lane lines is achieved, urgent needs of automatic driving can be met, and a high-