Method and system for detecting and judging smoky vehicles based on spatio-temporal background comparison

Abstract

The invention belongs to the technical field of monitoring, analysis and statistics of illegal vehicles, and discloses a black-smoky vehicle detection and determination system based on space-time background comparison, which acquires a video stream carrying traffic road condition images from an externally connected industrial camera; from the acquired video stream Extract key frames; use deep learning algorithm to detect common vehicles and smoky vehicles on key frames, save detection screenshots and 5-second videos containing smoky vehicles respectively; perform license plate recognition and Ringelman smoky coefficient on smoky vehicles Judgment and judgment of the number of illegal roads; complete the storage and analysis of the detection results, and output and save the results of the smoky car video, screenshots, information and other data with the detection results for later analysis and inspection. The invention effectively solves the problem that black smoke vehicles are difficult to detect, and at the same time proposes a key frame extraction method to accelerate the problem of slow real-time detection speed, and the accuracy and real-time performance are significantly improved.

Description

technical field [0001] The invention belongs to the technical field of monitoring, analysis and statistics of illegal vehicles, and in particular relates to a detection and judgment system for black-smoky vehicles based on space-time background comparison. Background technique [0002] In recent years, with the continuous development of the national economy and the continuous improvement of residents' living standards, automobiles have become an indispensable means of transportation in human life and production. However, with the popularization of automobiles, automobile exhaust pollution is also becoming more and more serious. According to the "China Motor Vehicle Environmental Management Annual Report" released by the environmental protection department in 2017, the number of motor vehicles in the country reached 295 million in 2016, an increase of 8.1% over 2015, and cars have taken the dominant position. In 2016, the preliminary calculation of motor vehicle emissions na...

AI Technical Summary

Problems solved by technology

[0008] The significance of solving the above problems and defects is: the missed detection of smoky vehicles will seriously affect urban traffic and pollute urban air

Images