Unlock instant, AI-driven research and patent intelligence for your innovation.

A Pedestrian Retrieval Method Based on Multiple Models and Fuzzy Colors

A fuzzy color and multi-model technology, applied in character and pattern recognition, special data processing applications, instruments, etc., can solve the problems of pedestrian retrieval that cannot achieve comprehensive features, low detection rate, high false alarm rate, etc., and achieve high comprehensive retrieval Efficient calculation of accuracy, feature calculation and feature distance

Active Publication Date: 2017-11-21
ROPEOK TECHNOLOGY GROUP CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] In order to overcome the technical problems of low detection rate and high false alarm rate of current pedestrian detection methods for static images, and the inability to achieve pedestrian retrieval based on comprehensive features, the present invention provides a method for achieving efficient foreground extraction for static images with high detection rate and high detection rate. Low false alarm rate, multi-model and fuzzy color pedestrian retrieval method that can realize comprehensive feature retrieval

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
  • A Pedestrian Retrieval Method Based on Multiple Models and Fuzzy Colors
  • A Pedestrian Retrieval Method Based on Multiple Models and Fuzzy Colors
  • A Pedestrian Retrieval Method Based on Multiple Models and Fuzzy Colors

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The abbreviations mentioned in the present invention include:

[0052] HOG: Histograms of Oriented Gradients;

[0053] FHOG: Felzenszwalb's HOG;

[0054] DPM: Deformable Part Model; deformable part model; open source software;

[0055] ICF: Integral Channel Features; integrated channel model; open source software;

[0056] FCTH: FUZZY COLOR AND TEXTURE HISTOGRAM; fuzzy color and texture histogram; open source software;

[0057] CEDD: Color and Edge Directivity Descriptor; color and edge direction descriptor; open source software;

[0058] ROI: Region Of Interest; Interest area;

[0059] CBIR: Content-based image retrieval; content-based image retrieval;

[0060] lire: Lucene Image REtrieval; an open-source cbir engine that integrates a variety of image features;

[0061] Foreground extraction mentioned in the present invention can be described in the following published documents:

[0062] [a] Level-Set Person Segmentation and Tracking with Multi-RegionAppearance...

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 discloses a pedestrian retrieval method with multiple models and fuzzy colors. Step 1: Define the input pedestrian detection results to obtain a preliminary foreground, and then calculate the preliminary foreground to obtain and save the final foreground; Step 2: Synthesize Calculate the CEDD feature and fuzzy color feature of each pedestrian from the foreground obtained in step 1 and the position information in the input pedestrian detection result; step 3: retrieve the objects stored in the database according to the given search feature , if given as pedestrian and foreground features, calculate the CEDD feature of the given pedestrian, and compare it with each record in the CEDD feature database to get the feature distance, and sort the records according to the feature distance to get the retrieval result; if given is a color feature, calculate the fuzzy color histogram of the given color, and compare it with each record in the fuzzy color feature database to get the feature distance, and sort the records according to the feature distance to get the retrieval result.

Description

technical field [0001] The invention relates to a pedestrian retrieval method with multiple models and fuzzy colors. Background technique [0002] At present, pedestrian detection and foreground extraction for static images are technical difficulties. Although there are many pedestrian detection methods, there are few detection methods that are easy to foreground extraction, mainly DPM, namely: [0003] Deformable Part Model (DPM: Deformable Part Model) [0004] Object Detection with Discriminatively Trained Part Based Models, P. Felzenszwalb, R. Girshick, 2010; [0005] Cascade Object Detection with Deformable Part Models, P. Felzenszwalb, R. Girshick, 2010. [0006] At present, many pedestrian detection and foreground extraction are based on video. The reason is that the motion information in it is used to achieve better detection results. [0007] The result of most pedestrian detection is a pedestrian's peripheral box, and it is difficult to extract the pedestrian fo...

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 Patents(China)
IPC IPC(8): G06F17/30G06K9/00
CPCG06F16/5838G06V40/162
Inventor 张翔
Owner ROPEOK TECHNOLOGY GROUP CO LTD
PatSnap Eureka logo

PatSnap Eureka turns technology decisions into work you can execute. Powered by our Innovation Knowledge Graph, it runs expert workflows across engineering, life sciences, materials and intellectual property. Get your review-ready output in minutes.

X (Twitter)LinkedInYouTubeSubstack

© 2026 PatSnap. All rights reserved. 

Terms of Service

 | 

Privacy policy

 | 

Modern Slavery Act Transparency Statement