Intelligent identification method for urban violation

Abstract

The invention provides an intelligent identification method for urban violation, which comprises the following steps: step S1, obtaining a plurality of urban violation photos, and labeling the violation categories of the photos manually; step S2, creating an intelligent recognition model, and uploading the artificially labeled photos to the intelligent recognition model for in-depth learning training; step S3, obtaining a city monitoring video, intelligently identify the city monitoring video by using the optimized intelligent identification model, capturing a video frame which is judged to have illegal behavior, and creating a label; step S4, auditing the label of the screenshot manually, and if the label is incorrect, modifying the label, and entering the step S2; if the label is correct, sending the screenshot to the city management system for real-time alarm. The invention has the advantages of realizing the real-time monitoring and intelligent identification of the urban violationbehavior and reducing the cost of supervising the urban violation behavior.

Description

technical field [0001] The invention relates to the field of city management, in particular to an intelligent identification method for city violations. Background technique [0002] With the advancement of urbanization, a large number of people have flooded into cities to live, which has also resulted in a large number of urban violations, such as setting up stalls, operating outside stores, dumping muck, illegal parking, illegal construction, garbage dumping and Outdoor advertising, etc. [0003] For urban violations, the traditional method is to use manual on-site patrols to take photos and upload urban violations, or use video surveillance to conduct manual inspections in the command center. However, the traditional approach has the following problems: Due to the complex and diverse characteristics of urban violations and the complex management structure, there are untimely supervision of urban violations, difficulty in law enforcement and evidence collection, repeated ...

AI Technical Summary

Problems solved by technology

However, the traditional approach has the following problems: Due to the complex and diverse characteristics of urban violations and the complex management structure, there are untimely supervision of urban violations, difficulty in law enforcement and evidence collection, repeated problems, and consume a lot of human resources.

This invention has the following problems: firstly, no intelligent identification model has been established for violations, each time a photo of city violations needs to be uploaded to the analysis server for processing, and the identification reminder cannot be carried out immediately, resulting in delays in law enforcement; secondly, it is reported to the central server to stop video recording, and Real-time monitoring of city violations is not possible

Images