Road condition image model training method and system based on auxiliary driving and intelligent terminal

Abstract

The invention discloses a road condition image model training method and system based on auxiliary driving, and an intelligent terminal. The method comprises the steps of obtaining a positive sample target image and a negative sample target image in an image area; performing feature extraction on each target image, obtaining n feature vectors, wherein n is a positive integer; splicing the obtained feature vectors, and carrying out feature normalization processing; extracting m items randomly from the n feature vectors, and forming a sample feature combination model, wherein m is a positive integer smaller than or equal to n; and carrying out model training and evaluation on the feature combination model. According to the invention, automatic feature screening can be achieved for the image classification problem, the extracted image features are screened and combined, the SVM classifier is trained to obtain different models, the model with the best performance is selected according to the model test result, and the technical problem that road surface information classification is difficult in the prior art is solved.

Description

technical field [0001] The present invention relates to the technical field of assisted driving, in particular to a road condition image model training method, system and intelligent terminal based on assisted driving. Background technique [0002] Over the past few years, deep learning has become the technique of choice for most AI-type problems, replacing classical machine learning. However, in vehicle assisted driving, when classifying road surface information, due to the small data set and limited hardware resources, under limited hardware resources, machine learning can be trained well with only CPU. It is not expensive and can iterate faster; and machine learning involves direct feature engineering, and the algorithm has better explainability and understandability. Therefore, in this specific scenario, adopting a machine learning approach is a better choice for solving the problem. [0003] Therefore, it becomes an urgent problem to be solved by those skilled in the ...

AI Technical Summary

Problems solved by technology

[0004] To this end, the embodiments of the present invention provide a road condition image model training method, system, and smart terminal based on assisted driving to at least partially solve the technical problem of difficult road surface information classification in the prior art

Images