A black smoke vehicle detection method based on single frame image

Abstract

The invention provides a black smoke vehicle detection method based on a single frame image. The black smoke vehicle detection method comprises the following steps: a single frame color image is converted into a gray scale image and is evenly divided into a plurality of small squares, for each small block region, discriminant complete local binary pattern features or discriminant non-redundant local binary pattern features are extracted, for each small block area, the gradient position direction histogram feature is extracted, for each small square area, the local partial shape feature is extracted, different types of features are normalized to be connected in series to form the final feature vector, the proposed feature vectors are classified by SVM classifier, the smoke squares are identified, and whether there are smoke vehicles in the current frame is judged. Various features are introduced into the invention, so that the information expression is sufficient and discriminative, which is more conducive to classification and identification, and has stronger robustness and discrimination. The recognition rate is further improved and the false alarm rate is reduced.

Description

technical field [0001] The invention belongs to the technical field of image processing and pyrotechnics detection, and relates to a method for detecting a smoky vehicle, more specifically, a method for detecting a smoky vehicle based on a single-frame image. Background technique [0002] Smoky vehicles are highly polluting motor vehicles, mainly powered by diesel fuel, and are commonly seen in large trucks and engineering vehicles. Their smoky exhaust seriously pollutes the air and endangers human health. [0003] At present, the methods of smoky vehicle detection can be roughly divided into two categories: traditional methods and intelligent methods. The first category of traditional methods is divided into public reporting, regular road inspections, night inspections, manual video surveillance, installation of vehicle exhaust analysis devices, sensor detection, etc. This type of method is inefficient and consumes a lot of manpower and financial resources. For example, th...

AI Technical Summary

Problems solved by technology

Such methods use computer vision technology to automatically detect smoky vehicles from massive road surveillance videos, and have many advantages, but such methods are still in the initial stage of research, and these methods cannot be applied to single-frame situations

Images