Personnel reidentification method based on deep learning and distance metric learning

A distance measurement and deep learning technology, applied in the field of recognition, can solve the problems of poor generalization ability of similarity measurement model and poor pedestrian re-identification performance.

Pending Publication Date: 2018-07-31
江苏测联空间大数据应用研究中心有限公司
View PDF4 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is: in order to solve the problem that the generalization ability of the existing similarity measurement model is not strong, and the pedestrian re-identification performance is poor, the present invention provides a method based on deep learning and distanc...

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
  • Personnel reidentification method based on deep learning and distance metric learning
  • Personnel reidentification method based on deep learning and distance metric learning
  • Personnel reidentification method based on deep learning and distance metric learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0099] Embodiment 1: The pedestrian re-identification method based on deep learning and distance metric learning in this embodiment

[0100] First of all, in view of the serious occlusion of video targets, a pedestrian target detection method based on convolutional neural network is used to process massive video data and detect pedestrian targets in the video. Secondly, the unsupervised RBM network is used to encode the initial features of the pedestrian target in a bottom-up manner to obtain a visual dictionary with both sparsity and selected rows; then, the initial visual dictionary is supervised and fine-tuned by error back propagation to obtain A new image expression method for video images, that is, image deep learning representation vectors; finally, the distance metric learning method of feature grouping and feature value optimization is used to obtain a metric space closer to the real semantics, and a linear SVM classifier is used to classify pedestrians target identif...

Embodiment 2

[0102] Embodiment 2: Due to the poor quality of the monitoring video, the uncontrollable environment, the wide range of shooting angles of view and the partial occlusion between pedestrians, it is difficult for the traditional target detection method to achieve good results in this open environment. This embodiment adopts a method based on The pedestrian target detection method of the convolutional neural network is mainly divided into the model training stage and the target detection stage. The specific process and results are as follows: figure 1 As shown, the specific process can be described as:

[0103] (1) In the model training stage, the focus of work is the selection and preprocessing of samples, as well as experimenting with CNN network parameters to select the optimal parameter combination. First, increase the diversity of samples by selecting samples from different angles and appearance colors, and then readjust these samples to a uniform resolution, and then enhanc...

Embodiment 3

[0105] Embodiment three: see figure 2 , image 3 , Figure 4 The pedestrian re-identification method based on the deep learning coding model of the present embodiment adopts the following steps to generate a visual dictionary with both sparseness and selectivity:

[0106] Figure 4 Among them, the visual dictionary represented by (a) is both sparse and selective, the visual dictionary represented by (b) is only selective, and the visual dictionary represented by (c) is only sparse.

[0107] First, extract the SIFT features of the training image library; extract the SIFT features; secondly, combine the spatial information of the SIFT features, use the adjacent SIFT features as the input of the RBM, train the RBM through the CD fast algorithm, and obtain the hidden layer features; then the adjacent hidden layer The features are used as the input of the next layer of RBM to get the output dictionary. Among them, ω 1 and ω 2 is the connection weight of RBM. RBM has an obvio...

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 relates to the field of the identification method, and particularly relates to a personnel reidentification method based on deep learning and distance metric learning. The identificationmethod comprises the steps that (1) a pedestrian target detection method based on the convolutional neural network is adopted to process the video data so as to detect the pedestrian target in the video; (2) the initial characteristics of the pedestrian target are coded by using an unsupervised RBM network through the bottom-up mode so as to obtain a visual dictionary having sparsity and selectivity; (3) supervised fine adjustment is performed on the initial visual dictionary by using error back propagation so as to obtain the new image expression mode of the video image, i.e. the image deeplearning representation vector; and (4) the metric space closer to the real semantics is acquired by using the distance metric learning method of characteristic grouping and characteristic value optimization, and the pedestrian target is identified by using a linear SVM classifier. The essential attributes of the image can be more accurately expressed so as to greatly enhance the accuracy of pedestrian reidentification.

Description

technical field [0001] The invention relates to the field of identification methods, in particular to a person re-identification method based on deep learning and distance metric learning. Background technique [0002] In recent years, with the extensive construction and application of video surveillance systems, it has played an increasingly important role in combating crime and maintaining stability. Most of the current monitoring systems use real-time shooting and manual monitoring, which requires the monitoring personnel to always pay attention to the monitoring screen and carefully distinguish the events in the video, which is obviously unrealistic, not to mention that there are a lot of omissions and subjective errors in the way of manual viewing . Considering the increasing scale of surveillance video, the labor cost required by this method will also be unbearable and inefficient. Therefore, there is an urgent need for a convenient and quick method to replace the ex...

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): G06K9/00G06K9/62G06N3/08
CPCG06N3/084G06V40/103G06F18/28G06F18/2411G06F18/22G06F18/214
Inventor 李弼程赵永威朱彩英陈良浩
Owner 江苏测联空间大数据应用研究中心有限公司
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