Object Re-Identification Method and System Based on Unsupervised Pyramid Similarity Learning
What is AI technical title?
AI technical title is built by Patsnap AI team. It summarizes the technical point description of the patent document.
A similarity and re-identification technology, applied in the field of target re-identification, can solve the problems that the target model is not suitable for unlabeled sample characteristics, the target model is inaccurate, and the performance is not as good as it is, which is conducive to migration and self-adaptation, and the feature block is simple General Purpose, Good Performance Effects
Active Publication Date: 2022-04-12
DEZHOU UNIV
View PDF4 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
This problem has always been challenging in complex monitoring environments (such as lighting changes, objects occluded by other things, different monitoring perspectives, etc.)
The performance of these methods is still not as good as the corresponding supervisory method. There are still problems in building models and migration algorithms. Most of them use the overall feature model. When the target is blocked or the monitoring perspective changes, the performance will drop significantly.
[0005] In summary, the inventors found that the target model constructed by the current target re-identification method is inaccurate, and the target model is not suitable for unlabeled sample characteristics
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0042] Such as figure 1 As shown, the target re-identification method based on non-supervised pyramid similarity learning of this embodiment includes:
[0043] Step 1: Obtain the sample image to be queried and the image of the target scene domain;
[0044] Step 2: Output the target image in the target scene domain that matches the sample image to be queried through the target re-identification model;
[0045] Among them, the training and updating process of the target re-identification model is:
[0046] Unsupervised multi-scale horizontal pyramid similarity learning for source and target scene domain images;
[0047] According to the similarity, the sample images of the target scene domain are automatically marked and the training samples are selected to train and update the initial model to obtain the target re-identification model.
[0048] The labeled and filtered samples are used to continue training the model. After several iterations of training, the updated model wi...
Embodiment 2
[0095]The target re-identification system based on non-supervised pyramid similarity learning of the present embodiment includes:
[0096] An image acquisition module, which is used to acquire sample images to be queried and target scene domain images;
[0097] A target re-identification module, which is used to output a target image matching the sample image to be queried in the target scene domain through the target re-identification model;
[0098] Among them, the training and updating process of the target re-identification model is:
[0099] Unsupervised multi-scale horizontal pyramid similarity learning for source and target scene domain images;
[0100] According to the similarity, the sample images of the target scene domain are automatically marked and the training samples are selected to train and update the initial model to obtain the target re-identification model.
[0101] Each module of the target re-identification system based on non-supervised pyramid similar...
Embodiment 3
[0103] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the target re-identification method based on non-supervised pyramid similarity learning as described in the first embodiment above is implemented. step.
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
Login to View More
Abstract
The invention belongs to the field of target re-identification and provides a target re-identification method and system based on non-supervised pyramidsimilarity learning. Among them, the target re-identification method based on non-supervised pyramidsimilarity learning includes obtaining the sample image to be queried and the image of the target scene domain; outputting the target image in the target scene domain that matches the sample image to be queried through the target re-identification model; wherein, the target re-identification The training and update process of the recognition model is as follows: unsupervised multi-scale horizontal pyramidsimilarity learning for source scene domain and target scene domain images; automatic labeling of target scene domain sample images according to similarity and screening of training samples to update the initial model Perform training and updating to obtain the target re-identification model. Through continuous iterative training and updating, the model is more and more adapted to the sample data in the target scene domain, which can improve the accuracy of pedestrian target re-identification.
Description
technical field [0001] The invention belongs to the field of target re-identification, in particular to a target re-identification method and system based on non-supervised pyramid similarity learning. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] The purpose of target re-identification is to compare and match the pedestrian target image to be found with the pedestrian images obtained under different cameras, and find out whether the target pedestrian appears in different camera monitoring scenes. This technology plays an important role in intelligent surveillance and public safety. This problem has always been challenging in complex surveillance environments (such as lighting changes, objects occluded by other things, different surveillance perspectives, etc.). [0004] Recently, object re-identification methods based on deep learning...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More