Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

SVM object detection method based on Adaboost Haar-Like features

A target detection and strong feature technology, applied in the field of image recognition, can solve problems such as wrong judgment results, and achieve the effect of improving accuracy and good application prospects.

Active Publication Date: 2016-03-30
ANHUI TSINGLINK INFORMATION TECH
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the problem with the above method is: due to the cascaded structure, once the previous strong feature classifier makes a wrong judgment, it is useless even if all the subsequent strong feature classifiers are correct, and the final judgment result is still wrong.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • SVM object detection method based on Adaboost Haar-Like features
  • SVM object detection method based on Adaboost Haar-Like features
  • SVM object detection method based on Adaboost Haar-Like features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0022] The invention belongs to a classification method with supervised learning, so it is divided into two main processes of training and detection. Before understanding the implementation of the present invention, one should first fully understand the classic AdaboostHaar-like method mentioned in the background technology, and fully understand the SVM training and detection process.

[0023] A SVM target detection method based on AdaboostHaar-Like features, including a training step and a detection step.

[0024] Such as figure 1 As shown, the training steps specifically include the following steps:

[0025] Step S101, start the training process; before this, similar to all supervised learning classification methods, it is necessary to collect and mark positive and negative samples of the target of interest.

[0026] Step S102, traverse al...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides an SVM object detection method based on Adaboost Haar-Like features. According to the method, Haar-Like features are adopted, a plurality of features of the type constitute a strong feature classifier through an Adaboost method, and multiple strong feature classifiers are selected through the method; and then, the feature values of the strong feature classifiers constitute a feature vector according to a certain sequence, and the feature vector is trained and detected by an SVM method. Although the method of the invention is of lower speed than an object detection algorithm based on cascaded Adaboost Haar-Like features, the accuracy rate is increased obviously.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to an SVM target detection method based on AdaboostHaar-Like features. Background technique [0002] With the development of video surveillance technology, video surveillance products continue to develop in the direction of high-definition and intelligence. At present, one of the main contents of intelligent research in the industry is to enable the computer to automatically recognize the target behavior in the screen. The premise of recognizing target behavior is to accurately detect the target of interest. In 2001, Paul Viola and Michael Jones proposed a method based on AdaboostHaar-Like features and a cascaded structure for object detection (Rapid object detection using a boosted cascade of simple features, CVPR2001, hereinafter referred to as the classic AdaboostHaar-like method), and applied this method to face detection, obtaining better effect. [0003] This me...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/62G06K9/66
CPCG06V30/194G06V2201/07G06F18/2411
Inventor 何佳张卡尼秀明
Owner ANHUI TSINGLINK INFORMATION TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com