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

Case activity track monitoring method based on pedestrian re-identification

A pedestrian re-identification and pedestrian technology, which is applied in character and pattern recognition, epidemic warning systems, instruments, etc., can solve the problem of unexplored application prospects of epidemic prevention and control, and achieve the effect of convenient prevention and control and improved accuracy.

Pending Publication Date: 2021-03-30
NANJING UNIV OF INFORMATION SCI & TECH
View PDF11 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

So far, no technology has attempted to apply pedestrian re-identification technology to activity trajectory monitoring, nor has it explored its application prospects for epidemic prevention and control

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
  • Case activity track monitoring method based on pedestrian re-identification
  • Case activity track monitoring method based on pedestrian re-identification
  • Case activity track monitoring method based on pedestrian re-identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0038] Such as figure 1 As shown, a case activity trajectory monitoring method based on pedestrian re-identification includes the following steps:

[0039] S1. Use the networked camera to obtain pedestrian video information and upload it to the cloud server, use the target detection algorithm to detect pedestrians, use the target tracking algorithm to obtain a series of pedestrian detection frames, preprocess the video, divide the video into continuous frames, and process all frames Uniform initialization, the size of each frame of image is cropped to contain 256*128 pixels, all images are converted into tensor (Tensor) data form, normalized using the channel mean and standard deviation, and then the tensor is normalized to (0 ,1) between.

[0040] S2, such as figure 2 As shown, a video sequence-based local alignment pedes...

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 case activity track monitoring method based on pedestrian re-identification. The method comprises the following steps: preprocessing a video, segmenting the video into continuous frames, and carrying out unified initialization; building a local alignment pedestrian re-identification framework based on a video sequence on the basis of PyTorch; dividing the MARS pedestrianre-identification data set into a training set and a test set, and loading the training set to train the neural network; adopting an MARS test set to test the model obtained through training, and searching for an optimal model; and acquiring pedestrian images / videos to be queried in different scenes, calculating a plurality of items closest to the features in the target video library as matching items, and acquiring pedestrian tracks according to the shooting position information. According to the invention, an existing pedestrian re-identification algorithm is improved and optimized, the problems that feature extraction is not robust and the accuracy is low are solved, the pedestrian re-identification technology is applied to track monitoring, and potential infected persons are conveniently and rapidly tracked, so that convenience is brought to prevention and control of epidemic situations.

Description

technical field [0001] The invention relates to the technical field of computer vision image retrieval, in particular to a method for monitoring case activity tracks based on pedestrian re-identification. Background technique [0002] As the new crown epidemic enters the stage of normalized prevention and control, the investigation and tracking of the activity trajectory of suspected or confirmed cases has become an essential step. Timely and effective acquisition of the recent activity areas of suspected or confirmed cases plays a vital role in screening close contacts of cases and controlling the further spread of the epidemic. However, there may be problems such as inaccurate locations, omissions, and low reliability in manual inquiry of cases to obtain activity trajectories; manual inspection of monitoring equipment for confirmation requires a lot of manpower and time, and is inefficient. Therefore, designing a case activity track monitoring method can bring great conve...

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): G06K9/00G06K9/32G06K9/62G16H50/80
CPCG16H50/80G06V20/49G06V20/41G06V10/25G06F18/214Y02T10/40
Inventor 张国庆陈裕豪
Owner NANJING UNIV OF INFORMATION SCI & 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