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

Re-recognition network training method, device and system, and re-recognition method, device and system

A training method and re-recognition technology, applied in the field of image recognition, can solve problems such as limiting the generalization ability of convolutional neural networks

Active Publication Date: 2018-06-01
MEGVII BEIJINGTECH CO LTD
View PDF10 Cites 35 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Metric learning is to extract the features of each pedestrian picture, calculate the distance between the features of the two pictures, and then randomly select positive sample pairs and negative sample pairs in the training samples. This method is for the sample pairs participating in the convolutional neural network. Most of them are simple and easily distinguishable sample pairs, which limits the generalization ability of convolutional neural networks

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
  • Re-recognition network training method, device and system, and re-recognition method, device and system
  • Re-recognition network training method, device and system, and re-recognition method, device and system
  • Re-recognition network training method, device and system, and re-recognition method, device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] figure 1 It is a schematic diagram of the electronic device provided by Embodiment 1 of the present invention.

[0073] refer to figure 1 , an example electronic device 100 for implementing the training of the re-identification network of the embodiment of the present invention, the re-identification method, device and system, including one or more processors 102, one or more storage devices 104, input devices 106, output Device 108 and image acquisition device 110, these components are interconnected by bus system 112 and / or other forms of connection mechanisms (not shown). It should be noted that figure 1 The components and structure of the electronic device 100 shown are only exemplary, not limiting, and the electronic device may also have other components and structures as required.

[0074] The processor 102 may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and m...

Embodiment 2

[0081] figure 2 It is a flow chart of the training method of the re-identification network provided by Embodiment 2 of the present invention.

[0082] refer to figure 2 , the method includes the following steps:

[0083] Step S101, obtaining batch processing training data, the batch processing training data includes N pictures, where N is a positive integer;

[0084] Optionally, for the batch training data for each training, the batch training data includes N pictures, N=P×K, where P is the number of different pedestrians, and K is the number of different photos corresponding to each pedestrian , where the different photos corresponding to each pedestrian are placed consecutively. In this way, the diagonal of the calculated distance matrix is ​​the positive sample distance, and the others are negative sample distances.

[0085] The convolutional neural network includes a custom convolutional neural network and a pre-trained convolutional neural network. If you use a cust...

Embodiment 3

[0129] Figure 6 It is a flowchart of a re-identification method for a re-identification network provided in Embodiment 3 of the present invention.

[0130] refer to Figure 6 , the method includes the following steps:

[0131] Step S501, obtaining a collection of pictures to be queried and pictures of pedestrians to be searched;

[0132] Step S502, pass the picture to be queried and at least one picture in the set of pictures of pedestrians to be searched through the trained convolutional neural network to obtain the feature vector of the picture to be queried and the feature vector of at least one picture in the set of pictures of pedestrians to be searched, wherein, training The convolutional neural network is obtained by the training method of the above-mentioned re-identification network;

[0133] Step S503, calculating the distance between the feature vector of the picture to be queried and the feature vector of at least one picture in the pedestrian picture set to be...

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 present invention provides a re-recognition network training method, device and system, and a re-recognition method, device and system. The re-recognition network training method comprises the steps of: obtaining batch processing training data; obtaining feature vectors corresponding to N images included in the batch processing training data, calculating the distance between two each feature vectors according to the feature vector corresponding to each image, and obtaining a distance matrix; and according to the distance matrix obtained through calculation, selecting a positive sample pairwith the maximum distance and a negative sample pair with the minimum distance, employing the two selected boundary samples to calculate loss of a convolutional neural network to train a model. Therefore, the most difficult positive sample pair and the negative sample pair are learned to calculate the loss of the convolutional neural network so that the generalization capability of the convolutional neural network model can be improved and the identification precision is improved.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a training and re-recognition method, device and system for a re-recognition network. Background technique [0002] Re-identification of pedestrians is a very important issue in security surveillance video applications. Pedestrian re-identification refers to detecting whether a pedestrian in a certain camera has appeared in other cameras. At present, re-identification is mainly carried out through two methods of representation learning and metric learning. Representation learning is to treat each pedestrian as a category and transform pedestrian re-identification into an image classification problem. Metric learning is to extract the features of each pedestrian picture, calculate the distance between the features of the two pictures, and then randomly select positive sample pairs and negative sample pairs in the training samples. This method is for the sample pairs pa...

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 Applications(China)
IPC IPC(8): G06K9/62G06N3/04
CPCG06N3/045G06F18/22
Inventor 罗浩张弛
Owner MEGVII BEIJINGTECH CO LTD
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