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

Pedestrian detection method

A pedestrian detection and normalization technology, applied in the field of detection, can solve the problems of difficult to deal with occlusion, poor real-time performance, etc., and achieve the effect of enhancing the scale without deformation, improving the robustness and improving the real-time performance.

Pending Publication Date: 2018-09-18
CHINA UNIV OF MINING & TECH
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above analysis, the embodiment of the present invention aims to provide a pedestrian detection method to solve the problems of poor real-time performance, difficult to deal with occlusion, unsuitable for occasions with obvious changes in illumination and strong noise in the prior art

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
  • Pedestrian detection method
  • Pedestrian detection method
  • Pedestrian detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] Such as figure 1 As shown, a specific embodiment of the present invention discloses a pedestrian detection method, comprising the following steps:

[0064] 1. Input an image and obtain its pixel gray value;

[0065] 2. Obtain three kinds of CRLBP operators according to the gray value of the pixel, and obtain the CRLBP texture feature spectrum;

[0066] 3. Calculate the HOG feature of the input image; calculate the HOG feature of the CRLBP texture feature spectrum; calculate the CRLBP histogram feature;

[0067] 4. merging the HOG feature of the input image, the HOG feature of the CRLBP texture feature spectrum, and the CRLBP histogram feature to obtain an image descriptor;

[0068] 5. Using principal component analysis to reduce the dimensionality of the image descriptor, and using a classifier to realize pedestrian detection and recognition on the dimensionality reduction result.

[0069] During implementation, first, the average local gray level (ALG) is defined as...

Embodiment 2

[0099] Optimizing on the basis of the above examples, such as figure 2 As shown, the flow of the pedestrian detection method of this embodiment is described. Firstly, the CRLBP histogram feature of the original image is extracted, and the directional gradient histogram feature based on the CRLBP texture feature spectrum is extracted at the same time, and the directional gradient histogram of the original image is calculated. Then, after obtaining the CRLBP histogram feature of the original image, the HOG feature based on the CRLBP texture feature spectrum and the HOG feature of the original image in a serial fusion manner, the final image descriptor can be obtained, and the principal component analysis method is used Dimensionality reduction for this image descriptor. Finally, the HIKSVM classifier is used to realize the detection and recognition of the input image.

[0100] Such as image 3 As shown, the steps to calculate the image HOG features include:

[0101] 1. Norm...

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 relates to a pedestrian detection, belongs to the technical field of detection, and solves problems in the prior art that the real-time performance is poor, the shielding is difficult toprocess and a method is not suitable for occasions with the apparent illumination changes and strong noise. The method comprises the following steps: inputting an image, and obtaining gray scale values of the pixels; obtaining three CRLBP operators according to the gray scale values of the pixels, and obtaining a CRLBP texture feature spectrum; calculating HOG features of the input image, CRLBP histogram features, and HOG features of a CRLBP texture feature spectrum; carrying out the fusion of the HOG features of the input image, the CRLBP histogram features, and the HOG features of the CRLBPtexture feature spectrum to obtain an image descriptor; reducing the dimensions of the image descriptor through a principal component analysis method, and employing a classifier for a dimension reduction result to achieve pedestrian detection and recognition. The method is high in detection efficiency, is good in real-time performances, and is good in robustness for illumination and noise.

Description

technical field [0001] The invention relates to the technical field of detection, in particular to a pedestrian detection method. Background technique [0002] Pedestrian detection, as a kind of detection technology, has been widely used in the fields of automobile driving assistance, video surveillance system and content-based video retrieval. Pedestrian detection can be seen as a process of combining feature extraction and classifier, the purpose is to automatically analyze and detect pedestrians in an unknown video or image. [0003] At present, the more classic pedestrian detection methods include: the pedestrian detection method combining the Histogram of Oriented Gradient (HOG) descriptor and the Support Vector Machine (SVM) classifier, and the combination of the variable part model (DPM) and the HOG descriptor. A method for pedestrians with severe adhesion, and a pedestrian detection method based on HOG-LBP features. [0004] The above three methods all use the HOG ...

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): G06K9/00G06K9/46G06K9/62
CPCG06V40/10G06V10/507G06F18/2411G06F18/253
Inventor 程德强唐世轩李岩赵凯高蕊李腾腾赖伟
Owner CHINA UNIV OF MINING & 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