Intelligent monitoring method for smoky vehicles based on codebook and smooth transition autoregressive model

Abstract

The invention discloses an intelligent monitoring method for a smoky car based on a codebook and a smooth transition autoregressive model, comprising the following steps: (1) using the codebook model to detect a moving target in a video, and determining a key area behind the target; (2) Extract the Tamura feature of the key area, the central symmetric local binary pattern histogram feature and the gray histogram feature, and combine to form the three types of static features of the key area; (3) use the smooth transformation autoregressive model to analyze the time series of the three types of static features Modeling is carried out separately, and the solution of the model is used as the final feature vector to describe the dynamic characteristics of the key area; (4) Three types of feature training obtain three SVM classifiers, and the three classification results are weighted and fused to obtain the current key area Through the analysis of the recognition results of multiple key areas, it can judge whether there is a smoky car in the current video segment. The invention can improve the detection efficiency of the black smoke vehicle in the road monitoring video and reduce the false alarm rate.

Description

technical field [0001] The invention relates to the technical field of image feature extraction and timing analysis, and relates to an intelligent monitoring method for smoky vehicles based on a codebook and a smooth transition autoregressive model. Background technique [0002] The pollution of diesel trucks has always been the top priority of motor vehicle pollution. The smoky vehicles discussed in this invention are common diesel trucks. How to detect smoky vehicles driving on the road in time and implement elimination or mandatory maintenance according to the degree of pollution. It will be very helpful to reduce air pollution, fight the tough battle against pollution from diesel trucks, significantly reduce pollutant emissions, and win the battle to defend the blue sky. [0003] At present, vehicle exhaust analysis devices are used in some areas to detect smoky vehicles, but there are still many shortcomings. On the one hand, vehicle exhaust analysis devices are often e...

AI Technical Summary

Problems solved by technology

[0003] At present, vehicle exhaust analysis devices are used in some areas to detect smoky vehicles, but there are still many shortcomings. On the one hand, vehicle exhaust analysis devices are often expensive, and subsequent maintenance and maintenance need to consume a lot of money. Due to the increase in the number of vehicles, for each It is difficult to implement the configuration of all vehicles; on the other hand, for the analysis of vehicle exhaust installed on the roadside, the test results are often affected by many factors, such as multiple vehicles running in parallel, too close to the vehicle, bad weather (wind speed is too high) Heavy, rainy and snowy weather), road environment background, vehicle emissions nearby, exhaust pipe height, equipment status (light intensity, noise, etc.), professionalism of operators (installation and debugging), etc.

Images