Target feature detection method and device

Abstract

The invention belongs to the computer vision technical field and provides a target feature detection method and device. The method comprises the following steps that: a LBP (Local Binary Pattern) feature descriptors are extracted from a video frame; according to a preset simplification algorithm, a HOG (Histogram of Oriented Gradient) feature descriptors are extracted from the video frame; and a target can be identified through an SVM (Support Vector Machine) classifier according to the LBP feature descriptors and the HOG feature descriptors. According to the target feature detection method and device provided by the invention, the LBP feature descriptors and the HOG feature descriptors of the video frame are extracted according to the preset simplification algorithm so as to form HOG_LBP feature descriptors, and the HOG_LBP feature descriptors are inputted into the SVM classifier, so that a specific target in the video frame can be identified. The target feature detection method is suitable for FPGA (Field Programmable Gate Array) hardware circuits, and therefore, requirements for real-time detection can be satisfied, and computing speed of target feature detection can be improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a target feature detection method and device. Background technique [0002] In recent years, real-time monitoring has been more and more widely used in the fields of intelligent transportation and security. For example, the on-board video surveillance system can detect pedestrians in time and remind drivers to pay attention to reduce traffic accidents; install surveillance cameras in residential areas and traffic crossings to record passing pedestrians and vehicles, etc. These applications put forward high requirements on the real-time processing speed, storage capacity and accuracy of video data retrieval of video data. Therefore, target detection and tracking have become hot and difficult issues in the field of computer vision technology. [0003] The traditional target detection is to use the histogram of oriented gradient (HOG) to extract the features of ...

AI Technical Summary

Problems solved by technology

Combining HOG and LBP to extract features of the target can improve the detection accuracy, but due to the high computational complexity, it is difficult to meet the requirements of real-time detection

Images