Pedestrian detection method based on resolution score change

一种行人检测、分辨率的技术,应用在仪器、计算、字符和模式识别等方向,能够解决低分辨率场景高误检、漏检等问题,达到好效果的效果

Inactive Publication Date: 2018-06-29
WUHAN UNIV
View PDF9 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] The purpose of the present invention is to propose a technical solution for pedestrian detection based on the change of resolution score. The problem of high false detection and missed detection in the scene, the pedestrian classifier trained by parameter features gets the best result

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The technical scheme of the present invention can adopt software technology to realize automatic process operation. The technical solution of the present invention will be further described in detail below with reference to the drawings and embodiments.

[0041] figure 1 It is the flow chart of the present invention. After the input picture passes the detector, the discriminant score can be obtained. When the resolution of the sample gradually decreases, the discriminant score will decrease accordingly. The resolution of the sample and the corresponding score form a curve, which we named The resolution score gradient line is composed of parameter features that can express the curve, and the picture is re-expressed with the parameter feature. Finally, the parameter feature is sent to the classifier to obtain the detection result.

[0042] The embodiment of the present invention is divided into a training phase and a testing phase, and the specific implementation is as follows...

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 present invention discloses a pedestrian detection method based on resolution score change. The method comprises the steps of: extracting sample features according to training data in a training phase, training a detector according to the obtained features, and obtaining discrimination scores after samples pass through the detector, wherein the discrimination scores are decreased with the gradual decreasing of the resolution of the samples, the resolution of the samples and corresponding scores form a gradual change line, and parameters for representing the gradual change line form parameter features to train a pedestrian classifier; and extracting corresponding parameter features in an area to be detected in a test phase, inputting the parameter features into a classifier obtained ina training phase to determine whether the area to be detected comprises pedestrians or not. The pedestrian detection method based on resolution score change is applied in the pedestrian detection field and can obtain a good effect.

Description

Technical field [0001] The invention belongs to the technical field of surveillance video detection, and relates to a pedestrian detection method, in particular to a pedestrian detection method based on changes in resolution scores. Background technique [0002] In recent years, surveillance networks have become more and more widely used in the fields of public safety, mobile investigation, and passenger flow statistics. Video surveillance is playing an increasingly important role in fighting crimes and maintaining social security. Video investigation has become the public security’s role in detecting cases. An effective means. In actual video investigations, investigators need to manually analyze the moving pictures in the video. It is difficult to quickly and effectively investigate, track and lock suspected targets. This requires a lot of manpower, material resources and time, which not only affects the efficiency of case detection, but also is extremely easy Miss the best ti...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/103G06F18/24G06F18/214
Inventor 胡瑞敏王晓丁贵广陈军梁超焦黎胡必成阮威健郑淇
Owner WUHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products