An Improved Seat Belt Detection Method

Abstract

The invention provides an improved safety belt detection method, which uses a convolutional neural network as a training model to solve the problem of low detection accuracy of the existing deep learning safety belt detection method. The present invention improves the detection accuracy of the convolutional neural network by using a novel feedback incremental convolutional neural network training method and a novel multi-branch final evaluation value acquisition method. The selection rate of the seat belt area is improved, and finally the flexibility of the detection operation is improved by using the method of setting the fault tolerance threshold by the user. The invention is a successful application of the CNN structure in seat belt detection, and improves the detection accuracy compared with existing algorithms.

Description

technical field [0001] The invention belongs to the subfield of machine learning theory and application in the field of computer application technology, focuses on the problem of seat belt detection in intelligent transportation technology, and is specifically an improved seat belt detection method. Background technique [0002] After an in-depth investigation of the existing seat belt detection technology, it is found that the most popular seat belt detection method is the seat belt detection algorithm based on Canny edge detection and cascaded adaboost. The whole algorithm realizes seat belt detection by first locating the driver's area . In order to realize the positioning part of the driver area, the algorithm mainly converts the image to be detected into HSV space, and then uses two linear filters in the horizontal direction and vertical direction to calculate the projection of the image in the horizontal and vertical directions, and compares the projection modes compre...

AI Technical Summary

Problems solved by technology

Then use the adaboost algorithm to build a classifier for seat belt detection. The problem with this method is that it is greatly affected by the noise of a single image. Image noise not only has a great impact on contour acquisition but also on license plate positioning. In addition, this method is not suitable for poor lighting. The judgment error rate of the image acquired under the condition is high, because the feature acquisition method used to construct the classifier is easily affected by external factors, the robustness of this method is not high

However, the inventive method has deficiencies in detection accuracy and time efficiency. This method uses an 8-layer CNN model, which takes a long time to train and has low algorithm efficiency.

Images