Multi-feature fusion cascaded classifier-based fire fighting access vehicle detection method

Abstract

The invention proposes a multi-feature fusion cascaded classifier-based fire fighting access vehicle detection method, and belongs to the field of image processing and machine learning. The method comprises the steps of extracting a road region in a fire fighting access image by utilizing a significance detection method so as to eliminate the influence of an object, in a non-lane region, on a detection result; extracting a vehicle bottom shadow region by adopting a vehicle bottom shadow adaptive threshold segmentation method based on a characteristic that a grayscale value of the road region obeys normal distribution; obtaining a lower edge of the vehicle bottom shadow by adopting a pixel change rate-based shadow edge extraction method, and constructing a region of interest of a vehicle according to the extracted lower edge of the vehicle bottom shadow; and extracting an Haar feature of the region of interest of the vehicle, training a feature value after fusion and an HOG feature value of ''integrogram'' calculation by utilizing an Adaboost algorithm to generate a strong classifier, and finally verifying whether the region of interest of the vehicle is the vehicle or not by using a cascaded classifier obtained by training.

Description

technical field [0001] The invention relates to a vehicle detection method, which belongs to the field of image processing and machine learning, in particular to a fire exit vehicle detection method based on a multi-feature fusion cascade classifier. Background technique [0002] With the improvement of people's living standards, the number of urban car ownership continues to increase. At the same time, the phenomenon of "chaotic parking" in cities is becoming more and more prominent, and the phenomenon of vehicles occupying and blocking fire exits is becoming more and more common. Research shows that more than 80% of the fire accidents with major casualties every year are caused by the occupation of fire exits by private vehicles, which prevents fire vehicles from arriving at the scene immediately for rescue. The main purpose of the fire exit vehicle detection system based on the Internet of Things is to effectively avoid the occurrence of major fire accidents caused by the...

AI Technical Summary

Problems solved by technology

[0003] At present, commonly used vehicle detection methods include background difference, template-based vehicle detection methods, etc., which are only suitable for detecting continuous vehicle video frames. There are problems of low detection rate and poor robustness, considering the impact of various interference factors (such as changes in weather conditions and the surrounding environment, etc.) Vehicle detection method based on multi-feature fusion cascade classifier

Images