Image detection method, device and computer readable storage medium

Abstract

The invention discloses an image detection method. The method comprises the steps of acquiring training samples, which are obtained by expanding marked image data containing vehicles and pedestrians;classifying first features extracted from the training samples and obtaining the coordinates of a first detection frame; calculating total loss through a preset algorithm according to the classification result, the coordinates of the first detection frame and the real classification information, updating the parameters of a convolution neural network model according to the total loss through a gradient descent algorithm, performing iterative training on the training data to obtain a trained convolutional neural network model, acquiring a to-be-detected image including vehicles and pedestrians,and obtaining the corresponding vehicle and pedestrian information by utilizing a trained convolutional neural network model. The invention further discloses an image detection device and a computerreadable storage medium. Vehicle and pedestrian information in an image can be detected based on a convolutional neural network model, and the accuracy of image detection can be improved.

Description

technical field [0001] The present invention relates to the technical field of image detection, in particular to an image detection method, device and computer-readable storage medium. Background technique [0002] With the frequent occurrence of traffic accidents and people's increasing attention to smart car technology, the research and application of automotive intelligent assisted driving systems are developing rapidly, and the vehicle environment perception system is the key to the automotive intelligent assisted driving system, in which the surrounding vehicles and pedestrians Recognition is one of the most important components of the environment perception system. Obtaining information about surrounding vehicles or pedestrians can provide powerful technology for active safety technologies such as adaptive cruise control systems and automatic emergency braking systems. [0003] At present, the recognition of surrounding vehicles and pedestrians is mainly to obtain ima...

AI Technical Summary

Problems solved by technology

However, the existing image detection methods are generally based on the detection model of manually designed features to detect the vehicle and pedestrian information in the image. This method requires complex preprocessing of the image in the early stage and artificially designed features, and its design is more complicated. , the versatility is not good, and the accuracy of image detection is poor

Images