Method of object detection and training method of classifier in hierarchical object detector

Abstract

The present invention discloses a method and a system of object detection, as well as a training method and a system of the classifier in a hierarchical object detector. Wherein, the method of object detection comprises: preprocessing an input image into S images to be detected in different scales, wherein S is greater than or equal to 1; determining the every position of the images to be detected by employing a hierarchical object detector, and if the current position passes the current layer, a going to the determination of next layer; otherwise, considering the current position not to be the candidate position of the images to be detected. Wherein, the determination process of the classifier in each layer comprises the following steps: extracting texture characteristics of the specific subarea corresponding to the images to be detected; calculating the output characteristics of a local sub-classifier respectively corresponding to each specific subarea according to the texture characteristics; and determining whether the current position passes the current layer according to the output characteristics. The invention can increase the speed of object detection and obtain a better effect of object detection.

Description

technical field [0001] The invention relates to the technical field of pattern recognition, in particular to an object detection method and system, and a classifier training method and system in a hierarchical object detector. Background technique [0002] With the rapid development of computer technology, computer processing capacity has been greatly improved, and many emerging technical means such as pattern recognition and motion detection have emerged. Among them, object detection, as a kind of pattern recognition technology, is used in more and more field has been widely used. Object detection refers to obtaining the number, position and size of objects existing in a certain area from static or video images. Object detection technology has important practical value in various fields such as intelligent video surveillance, intelligent traffic management, video analysis and image retrieval. [0003] Currently, object detection technologies are mainly divided into two ca...

AI Technical Summary

Problems solved by technology

There has been a proposal to use the method based on microstructural features and Adaboost, which has been successfully used in the field of human detection, for object detection. Although the detection speed of the described scheme is fast, the detection effect is not ideal enough to meet practical requirements.

[0009] In addition, support vector machine (SVM) is another widely used classifier, which has better generalization ability compared to Adaboost, and some people have also tried to use the object detection algorithm based on SVM classifier, and obtained good results. detection effect, but this method has the problem of extremely slow detection speed, which makes this scheme unable to be applied to real-time running systems, thus greatly limiting the application scenarios of this scheme

Images