Smoky vehicle detection method based on self-organized background difference model and multi-feature fusion

Abstract

The invention discloses a black smoke vehicle detection method based on a self-organized background difference model and multi-feature fusion, including: using the self-organized background difference model to detect a moving target from video surveillance, and determine a key area; transforming the image of the key area into a YCrCb color space , to extract the color moment feature; convert the key area to the gray space, and extract the local three-valued pattern histogram feature and the edge direction histogram feature respectively; according to the position of the key area of ​​the current frame, extract the images of several frames before and after it in the entire frame sequence Corresponding to the area, the same type of features extracted from all time series areas are connected in series to form the feature vector of each type, and the feature vectors of each type are normalized and connected in series to form the final feature vector; using the pruned radial basis neural network classifier Classify the proposed final feature vectors, identify key areas of black smoke, and further identify black smoke vehicles. The invention can further improve the recognition rate, reduce the false alarm rate, and have a better recognition effect on the smoky cars with relatively light black smoke.

Description

technical field [0001] The invention belongs to the technical field of moving target detection in computer vision, and relates to a smoky car detection method based on a self-organized background difference model and multi-feature fusion. Background technique [0002] In recent years, more and more cities have suffered from smog. There are many factors that cause smog, among which exhaust emissions from motor vehicles using diesel engines are one of the main sources. Air pollution is harmful to human health, and the World Health Organization has confirmed and announced that the particulate matter emitted by diesel vehicles is a strong carcinogen. [0003] At this stage, the phenomenon of diesel vehicles emitting black smoke is still very serious, and it is commonplace during the stages of starting, accelerating, going uphill, and overloading. Some diesel vehicles pass through the city, which is like poisoning along the way. Taking Beijing as an example, the "Notice on Adop...

AI Technical Summary

Problems solved by technology

However, the current artificial intelligence implementation scheme has a low recognition rate and the effect is not ideal.

Images