Pedestrian re-identification method based on kernelization features and random subspace integration

A technology of random subspace and identification method, which is applied in the field of pedestrian re-identification based on the integration of kernelized features and random subspaces, can solve the problems of difficult Mahalanobis distance calculation, performance degradation, insolvability, etc., and achieves accurate distance calculation and algorithm. Performance improvement, the effect of optimizing the process of sample distance calculation

Active Publication Date: 2017-09-01
TONGJI UNIV
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method is based on the theoretical assumption that the sample distribution obeys the Gaussian distribution, but in reality, the samples not only do not obey the Gaussian distribution perfectly, but may even deviate seriousl...

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
  • Pedestrian re-identification method based on kernelization features and random subspace integration
  • Pedestrian re-identification method based on kernelization features and random subspace integration
  • Pedestrian re-identification method based on kernelization features and random subspace integration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0042] A pedestrian re-identification method based on kernelized features and random subspace integration, comprising the following steps:

[0043] Step 1: Transform the original feature into a kernelized feature representation, as described below:

[0044] Obtain a training set X∈R of pedestrian images d×m and the test set Z ∈ R d×n , where the sample feature dimension is d, the number of samples in the training set is m, the number of samples in the test set is n, and x i Indicates the i-th training sample, with z i Denotes the i-th test sample. use the kernel function Convert the training set X to kernelized features Convert the test set Z to kernelized features where σ=1. The specific conversion process can be expressed as

[0045]

[0046]Step 2: In the kernelized feature space, randomly select L different subspaces. The specific description is as follows: After step 1 is completed, the dimension of the kernelized feature space is the same as the number of ...

Embodiment approach

[0064] Such as figure 1 Shown is the flowchart of the present embodiment, and the specific implementation is as follows:

[0065] 1) Determine the kernel function;

[0066] 2) Convert the original features of the training samples into kernelized features;

[0067] 3) Convert the original features of the test samples into kernelized features;

[0068] 4) In order to judge z i and z j Whether belong to the same pedestrian, use H 0 Indicates that they are not similar, that is, they do not belong to the same pedestrian, use H 1 Indicates that they are similar, that is, belong to the same pedestrian;

[0069] 5) Randomly select L subspaces D in the kernelized feature space k (k=1,2,...,L);

[0070] 6) In different subspaces, calculate the covariance matrix Σ of the feature difference between different pedestrian image pairs 0 , and find the inverse matrix

[0071] 7) In different subspaces, calculate the covariance matrix Σ of the feature difference between the same ped...

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 a pedestrian re-identification method based on kernelization features and random subspace integration. The method comprises the following steps that: S1, the training sample set and test sample set of pedestrian images are obtained, and the kernelization function between of the two sample sets is determined; S2, the original features of the two sample sets are transformed into kernelization features; S3, a plurality of subspaces are randomly selected from the kernelization feature space of the training sample set, the covariance matrixes and the inverse matrixes thereof of the kernelization feature difference values of different pedestrian image pairs and identical pedestrian image pairs are calculated, the distribution function of the kernelization feature difference values of the image pairs is obtained; S4, the probability of a sample pair being the same pedestrian and the probability of a sample pair being different pedestrians under each subspace are calculated, the ratio of the two probabilities is adopted as the distance between the samples; and S5, the distances are integrated, so that final distances between each sample pair are obtained. Compared with the prior art, the method of the invention has the advantages of excellent pedestrian re-identification ability, suitability for a variety of different features and high robustness.

Description

technical field [0001] The invention relates to a method for feature extraction and distance measurement learning in intelligent analysis of monitoring video, in particular to a pedestrian re-identification method based on kernelized features and random subspace integration. Background technique [0002] Pedestrian re-identification refers to the problem of matching pedestrian images from different camera perspectives in a multi-camera system. It provides critical assistance in the analysis of different aspects such as pedestrian identity and behavior, and has developed into a key component in the field of intelligent video surveillance. [0003] The main methods in the field of person re-ID can be divided into the following two categories: 1) person re-ID methods based on feature representation; 2) person re-ID methods based on metric learning. [0004] In the method of person re-identification based on feature representation, low-level visual features are the most commonl...

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): G06K9/62
CPCG06F18/24133
Inventor 赵才荣陈亦鹏王学宽卫志华苗夺谦田元
Owner TONGJI UNIV
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