Goods stacking detection method, device, equipment and system

Abstract

The invention relates to a cargo stacking detection method, device, equipment and system. The method comprises the following steps: acquiring a monitoring video of goods, and intercepting images from the monitoring video every preset time; converting the intercepted image from a color image into a grayscale image, and then converting the grayscale image into an image matrix; inputting the image matrix into a preset preprocessing network to obtain a shared feature map; inputting the shared feature map into a pre-trained goods quantity classification network to obtain a goods quantity magnitude classification feature map; inputting the shared feature map and the classification feature map into a pre-trained cargo density evaluation network to obtain a cargo density evaluation map with the same size as the image matrix; and based on the cargo density evaluation diagram, calculating the cargo quantity and outputting the cargo quantity. According to the method, the neural network is adopted to realize cargo stacking detection, so that an express company can be helped to reasonably dispatch resources, and the situation of warehouse explosion of express cargoes is prevented.

Description

technical field [0001] The present application relates to the technical field of network video surveillance, and in particular, to a method, device, device and system for detecting cargo accumulation. Background technique [0002] With the rapid development of Internet technology and information technology technology, it has driven the popularization of big data, artificial intelligence, the Internet of Things, and 5G networks, and also promoted the development of image transmission and processing, video terminal receiving technology, and network video surveillance technology. With the emergence of innovation, the network video surveillance system has been widely used and popularized in different fields and different occasions due to its advantages and characteristics such as rich image information, high-definition pixels, advanced technology, convenience and intuitiveness. [0003] At present, the field of network video surveillance mainly relies on manual operations. For e...

AI Technical Summary

Problems solved by technology

[0005] This application provides a cargo accumulation detection method, device, equipment and system to solve the problems of high labor cost and untimely in the method of manually checking the monitoring video to judge the accumulation of goods

Images