YOLO V5-based unmanned aerial vehicle aerial image river sewage draining exit detection method and system

Abstract

The invention provides a YOLO V5-based unmanned aerial vehicle aerial image river sewage draining exit detection method and system. The method comprises the steps of establishing an unmanned aerial vehicle aerial image river sewage draining exit image data set; preprocessing the established data set, and establishing a training set and a test set; and building a YOLO V5 model, testing the performance of the trained YOLO V5 model by using the test set, and then using the model for unmanned aerial vehicle aerial sewage draining exit image identification. The problem that in a traditional targetdetection method, the detection precision of small targets such as a sewage draining exit of an aerial image of an unmanned aerial vehicle is low is solved. The invention assists in manually detectingthe river sewage draining exit of the aerial image, and improves the detection precision of the sewage draining exit.

Description

technical field [0001] The present disclosure belongs to the field of target detection of drone aerial images, and in particular relates to a method and system for detecting river sewage outlets of drone aerial images based on YOLO V5. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Domestic sewage treatment plants, industrial wastewater treatment plants and mixed waste water treatment plants are an important part of modern sewage outlets. Among them, domestic sewage and industrial wastewater are important causes of river pollution. The number of sewage outlets entering the river is large, widely distributed, changing rapidly, and highly concealed. It is difficult to use traditional methods to check sewage outlets, with high costs, many omissions, and long cycles. UAVs are low in construction and use costs, strong in mobility, easy to t...

AI Technical Summary

Problems solved by technology

However, compared with ordinary images, UAV aerial images have a resolution as high as 7952×5304, and the comparison between sewage outlets and the whole image accounts for less than 0.01%, and there are many types and forms of sewage outlets, and the semantic information of the background is very rich , more interference information

Human judgment depends on the technical level of professionals, which is likely to cause problems such as missed detection and false detection, and will increase the verification workload of on-site staff

At the same time, the number of images taken by drones is tens of thousands. It is time-consuming and laborious to manually detect the sewage outlets in the images.

Images