High-altitude parabolic object detection method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a high-altitude parabolic object detection method and device, electronic equipment and a storage medium, and relates to the technical field of image processing. The detection method comprises the following steps: acquiring a monitoring video of a high-altitude parabolic object; analyzing the monitoring video to obtain a plurality of frames of images; obtaining an inter-frame difference graph according to the multiple frames of images; compressing the inter-frame difference graph to obtain a compressed inter-frame difference graph; synthesizing a feature matrix according to the monitoring video and the compressed inter-frame difference graph; and inputting the feature matrix into a binary-classification convolutional neural network classifier to obtain a detection result of the high-altitude parabolic object. The high-altitude parabolic object detection method is low in memory requirement and low in equipment cost, and the technical effect of greatly reducing the calculation amount can be achieved.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular, to a detection method, device, electronic equipment and storage medium of a high-altitude parabola. Background technique [0002] At present, high-altitude throwing objects is a relatively common uncivilized phenomenon in cities. This kind of behavior of throwing debris from windows or rooftops of buildings can pollute the environment and sanitation in the slightest, and cause serious injuries or even fatal consequences in severe cases. Therefore, the high-altitude parabolic phenomenon was once called "the pain hanging over the city". It used to be as famous as "littering" and ranked second. Parabolic throwing at high altitude is an uncivilized behavior and will bring great social harm. [0003] In the prior art, the traditional high-altitude parabolic supervision method is mainly to retrieve the surveillance video of the time period after the parabolic event o...

AI Technical Summary

Problems solved by technology

However, such monitoring methods based on technologies such as millimeter-wave mines, sensors, and radio signals have problems such as time-consuming calculations, large computing resources, low accuracy, poor generalization, and expensive equipment maintenance.

Images