Supercharge Your Innovation With Domain-Expert AI Agents!

Footprint identification and gait detection method based on depth learning and device thereof

A deep learning and gait detection technology, applied in the field of image recognition, can solve the problems of time-consuming and labor-intensive cultivation of footprint identification experts, few experts, and unpopular footprint identification, so as to facilitate promotion and application, reduce dependence, and improve recognition accuracy rate effect

Active Publication Date: 2019-02-19
FUJIAN INST OF RES ON THE STRUCTURE OF MATTER CHINESE ACAD OF SCI
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, most public security organs need to hire experts with many years of experience in footprint identification to conduct manual identification with the naked eye, but there are few experts in this area nationwide, and the training of footprint identification experts is time-consuming and labor-intensive.
For these reasons, footprint identification is not popular across the country.

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
  • Footprint identification and gait detection method based on depth learning and device thereof
  • Footprint identification and gait detection method based on depth learning and device thereof
  • Footprint identification and gait detection method based on depth learning and device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0093] Embodiment 1 Footprint identification and gait detection method based on deep learning

[0094] see figure 2 and 4 , the footprint identification and gait detection method based on deep learning in the present embodiment, comprises the following steps:

[0095] 1. Collection of effective image datasets of human footprints is used to filter and process the collected images of human footprints to retain image datasets that meet the requirements of network training, which are called effective image datasets.

[0096] 2. The construction and training of the first neural network adopt the offline construction and training mode, which can ensure the timeliness of system application.

[0097] 3. The final output of the footprint identification method is the basic identity information of the owner of the provided human footprint image.

[0098] 4. Collection of effective human gait video data sets is used to filter and process the collected effective human gait videos to re...

Embodiment 2

[0101] Embodiment 2 Footprint identification and gait detection method based on deep learning

[0102] see image 3 and 5 , the footprint identification and gait detection method based on deep learning in the present embodiment, comprises the following steps:

[0103] 1. First, collect human footprint image datasets by collecting data from public security organs, web crawlers, and annotations on video screenshots.

[0104] 2. Eliminate the data in the data set that does not meet the network training requirements, and sort out effective images.

[0105] 3. Make one-to-one correspondence between the features of the valid data and the tags. The identity feature information includes but is not limited to height, weight, age, gender, type of shoes worn, whether there is any disease in the legs, whether the soles of the feet are special, etc.

[0106] 4. Save the processed effective data as the effective data set of human footprint images, and divide the effective data set of hum...

Embodiment 3

[0118] Embodiment 3 Footprint identification and gait detection method based on deep learning

[0119] see figure 1 , the footprint identification and gait detection method based on deep learning in the present embodiment, comprises the following steps:

[0120] 1. The construction and training of the network are consistent with those in Examples 1-2.

[0121] 2. The input of the second neural network is the external input of the human footprint image that needs to be identified, and the output of the second neural network is the basic identity information of the footprint owner (including but not limited to height, weight, age, gender, type of shoes worn, Whether there is a disease in the leg, whether there is a particularity in the sole of the foot, etc.), and at the same time, input the basic identity feature information into the fourth neural network.

[0122] 3. The input of the fourth neural network is the basic identity information of the footprint owner output by the...

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 footprint identification and gait detection method based on depth learning and a device thereof. The method comprises the following steps: step S100: identifying the basic identity characteristic information of an output footprint owner of a human footprint image to be identified; Step S200: inputting the basic identity characteristic information of the footprint owner into the fourth neural network trained with the effective video data set of human gait, and outputting the gait information of the basic identity characteristic of the human body; S300: detecting a human body image coinciding with the gait information according to the gait information of the basic human body identity feature in the video to be detected. The present application improves efficiency and accuracy by constructing a footprint identification and gait detection neural network and completing the training process of the network offline instead of artificial naked eye identification.

Description

technical field [0001] This application relates to a method and device for footprint identification and gait detection based on deep learning, belonging to the field of image recognition. Background technique [0002] In today's society, the public security organs first extract the fingerprint information of the crime scene during the investigation of criminal cases, but if the criminal suspect wears gloves and other coverings to commit the crime, it will lead to the inability to extract valuable fingerprint information at the crime scene. [0003] Due to long-term habits or leg diseases, the human footprint information carries the identity information of the human body. As an identity feature of the human body, footprints play an important role in the detection of criminal cases in today's society. [0004] At present, most public security organs need to hire experts with many years of experience in footprint identification to conduct manual identification with the naked e...

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): G06K9/00G06K9/62G06N3/04
CPCG06V40/25G06N3/045G06F18/214
Inventor 董秋杰周盛宗韩爱福
Owner FUJIAN INST OF RES ON THE STRUCTURE OF MATTER CHINESE ACAD OF SCI
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com