Method for constructing pedestrian detection model

A pedestrian detection and model technology, applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as occlusion and inaccurate pedestrian detection results, and achieve the effect of solving pedestrian occlusion, ensuring accuracy, and small amount of calculation

Active Publication Date: 2019-07-30
ANHUI UNIVERSITY OF TECHNOLOGY
View PDF13 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

This patented technology allows create models that can help identify people or objects by analyzing their appearance on images captured from different angles. These models have been developed based upon previous data collected over time and improved at faster speeds than previously possible due to advancements made within this field. They also provide accurate results even when there were partial obstacles between them. Overall, these technical improvements improve the performance of Pedestrian Detection Modules (PMDM) used for various applications such as security systems monitoring footwear usage patterns or identifying individuals' faces.

Problems solved by technology

Technological Problem addressed in this patents relates to how to detect people without being too complex or expensive equipment while still maintaining accuracy due to factors like background noise, personality trauma, and environmental conditions (such as temperature). Current approaches involve manual identification processes but they may result in errors when used alone.

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
  • Method for constructing pedestrian detection model
  • Method for constructing pedestrian detection model
  • Method for constructing pedestrian detection model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] to combine figure 1As shown, a method for building a pedestrian detection model of the present invention, first randomly selects pedestrian images from the database and marks the head of the pedestrian image as a label file, and then divides the selected pedestrian images into training set, test set and Validation set; then perform cluster analysis on the training set to obtain a new prior frame, and then adjust the network structure of the YOLOv3 network; then use the YOLOv3 network to train the training set to obtain a pedestrian detection model, and then use the validation set to perform a pedestrian detection model Finally, the pedestrian detection model is tested on the test set.

[0044] The specific steps are as follows:

[0045] Step 1: Build the head model

[0046] Randomly select pedestrian images with illumination changes and scale changes in different scenes from the database, and mark the heads of pedestrians in the selected images as label files, that is, c

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 method for constructing a pedestrian detection model, and belongs to the technical field of graphic processing. The method for constructing the pedestrian detection model comprises the following steps: randomly selecting a pedestrian image from a database, marking the head of the pedestrian image as a label file, and dividing the selected pedestrian image into a trainingset, a test set and a verification set; performing clustering analysis on the training set to obtain a new prior frame, and performing network structure adjustment on the YOLOv3 network; and trainingthe training set by using a YOLOv3 network to obtain a pedestrian detection model, evaluating the pedestrian detection model by using a verification set, and finally testing the pedestrian detection model by using a test set. The invention aims to overcome the defect that in the prior art, when pedestrians in a monitoring scene are in a dense state, the pedestrian detection result is inaccurate, and provides the method for constructing the pedestrian detection model, so that the problem of pedestrian shielding during pedestrian detection can be solved, and the pedestrian detection accuracy isimproved.

Description

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

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
Owner ANHUI UNIVERSITY OF TECHNOLOGY
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap