A vehicle detection method based on multi-feature fusion

Abstract

The invention provides a vehicle detection method based on multi-feature fusion. The vehicle detection method based on the multi-feature fusion comprises the steps of step 1, establishing one or a plurality of monitoring areas (ROI (region of interest)) in an input image; step 2, extracting Harris angular points and longitudinal gradient information in the ROI on the basis of a grayscale map of an image to be detected; step 3, computing a geometry size of a detection window at a certain position inside the ROI according to a circumscribed trapezoid of an obtained monitoring area; step 4, counting an angular point number of the detection window and computing the distribution symmetry of the angular points; step 5, extracting structured horizontal line information on the basis of a longitudinal gradient in the detection window; step 6, utilizing a cascaded strong classifier to judge whether a current detection window is a vehicle area, if so, reserving the current detection window, and if not, dismissing the current detection window; step 7, moving the detection widow according to a certain step size, switching to the step 3, and repeating the steps from the step 3 to the step 7; and step 8, reducing the probability of the repeated detection of the same target through detection result combination.

Description

technical field [0001] The invention belongs to the field of intelligent transportation systems (ITS), relates to a method for detecting motor vehicles in traffic videos, in particular to a method for detecting vehicles based on multi-feature fusion. Background technique [0002] Vehicle detection technology is the primary research topic of intelligent transportation systems, and it is the prerequisite for important applications such as traffic parameter acquisition, event detection, and security deployment. [0003] Most of the current vehicle detection methods are based on video processing, such as traditional classifier methods, background modeling methods, and model methods. These methods are very sensitive to vehicle size, vehicle attitude, shadows, illumination changes, and scene changes. They are highly dependent on the accurate establishment of samples or models, and the false detection is serious. However, many emerging feature-based detection methods use features ...

AI Technical Summary

Problems solved by technology

These methods are very sensitive to vehicle size, vehicle attitude, shadows, illumination changes, and scene changes. They are highly dependent on the accurate establishment of samples or models, and the false detection is serious.

However, many emerging feature-based detection methods use features that are too complex or too simple, and the detection effect is heavily dependent on the quality of the collected images.

Most of the current methods have a large amount of calculation, which is difficult to meet the practical requirements

Images