Helmet wearing state detection method and device, equipment and storage medium

Abstract

The invention relates to the field of artificial intelligence, and discloses a helmet wearing state detection method and device, equipment and a storage medium, which are used for improving the detection efficiency of the helmet wearing state. The helmet wearing state detection method comprises the steps of obtaining model training data, and training a preset initial convolutional neural network model based on a preset framework and the model training data to obtain a target convolutional neural network model; obtaining a target helmet wearing state picture set, wherein the target helmet wearing state picture set comprises a helmet wearing state picture set acquired in real time on the way from the starting place to the destination; calling a target convolutional neural network model, and performing separation, convolution and random mixing processing on the target helmet wearing state picture set in sequence to obtain an initial classification result; and performing regularization processing on the initial classification result to obtain a target classification result which is used for indicating related information of the helmet wearing state.

Description

technical field [0001] The present invention relates to the field of image detection, in particular to a method, device, equipment and storage medium for detecting a wearing state of a helmet. Background technique [0002] With the popularity of the e-commerce industry, people’s lives are increasingly inseparable from express delivery. In some end-of-the-box express delivery, it is still necessary for the courier to drive the express vehicle to deliver on-site delivery. In order to ensure the safety of the courier when delivering the express delivery, timely response The corresponding policy issued by the government requires couriers to wear helmets in the process of driving courier cars. In the past, most of them were manually inspected on site or watched surveillance videos. There were problems such as missed inspections and time-consuming and labor-intensive problems. [0003] In the existing technology, it is possible to detect the courier wearing a helmet based on machi...

AI Technical Summary

Problems solved by technology

[0002] With the popularity of the e-commerce industry, people’s lives are increasingly inseparable from express delivery. In some end-of-the-box express delivery, it is still necessary for the courier to drive the express vehicle to deliver on-site delivery. In order to ensure the safety of the courier when delivering the express delivery, timely response The corresponding policy issued by the government requires the courier to wear a helmet in the process of driving the courier car. In the past, most of them were manually inspected on the spot or checked the surveillance video, and there were problems such as missed inspection and time-consuming and labor-intensive problems

[0003] In the existing technology, it is possible to detect the courier wearing a helmet based on machine learning and deep learning technology. However, the existing detection is mostly focused on the departure and destination moments of the courier network, and it is impossible to detect the helmet worn by the courier during the journey. Real-time detection of wearing status, resulting in inefficient detection of helmet wearing status

Images