Pedestrian re-identification model training method and device based on active learning
A pedestrian re-identification and active learning technology, applied in the computer field, can solve the problems of low accuracy of recognition results, large errors in actual model effects, and high cost of data labeling, and achieve the effect of improving the accuracy of recognition results and saving labeling costs
Active Publication Date: 2020-11-20
TSINGHUA UNIV
View PDF5 Cites 10 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] Embodiments of the present disclosure provide a pedestrian re-identification model training method, device, equipment, and storage medium based on active learning to solve the problem of using deep learning for pedestrian re-identification. In different scenarios, the actual effect of the model has a large error. The high cost of data labeling during training leads to a technical problem of low accuracy in the recognition results of pedestrian re-identification
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0053] In order to understand the characteristics and technical content of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure will be described in detail below in conjunction with the accompanying drawings. The attached drawings are only for reference and description, and are not intended to limit the embodiments of the present disclosure. In the following technical description, for purposes of explanation, numerous details are set forth in order to provide a thorough understanding of the disclosed embodiments. However, at least one embodiment can be practiced without these details. In other instances, well-known structures and devices may be shown simplified in order to simplify the drawings.
[0054] see figure 1 , in some embodiments, an embodiment of the present disclosure provides a method for training a pedestrian re-identification model based on active learning, including:
[0055] S101. Acquire un...
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 relates to the technical field of computers, and discloses a pedestrian re-identification model training method based on active learning. The methhod comprises the following steps: acquiring unlabeled video data acquired by a plurality of image acquisition units in a monitoring area to obtain an original video data set; performing pedestrian detection and tracking on the unlabeled video data acquired by each image acquisition unit to obtain a pedestrian image data set; inputting the pedestrian image data set as a training sample into an initial pedestrian re-identification model,and training the initial pedestrian re-identification model by using an active learning strategy until parameters of the initial pedestrian re-identification model meet training stop conditions. Thepedestrian re-identification model based on active learning training can be suitable for more pedestrian identification scenes, the accuracy of the identification result of pedestrian re-identification can be improved, and the data annotation cost is saved. The invention further discloses a pedestrian re-identification model training device based on active learning, electronic equipment and a storage medium.
Description
technical field [0001] The present application relates to the field of computer technology, for example, to a method and device for training a pedestrian re-identification model based on active learning. Background technique [0002] Pedestrian re-identification is a technology that uses computer vision technology to identify whether a specific pedestrian exists in an image or video sequence. Pedestrian re-identification is mainly used in the fields of intelligent video surveillance and intelligent security. [0003] In the process of implementing the embodiments of the present disclosure, it is found that at least the following problems exist in related technologies: [0004] Related technologies usually use deep learning for pedestrian re-identification. In different scenarios, the actual effect of the model has large errors, and the cost of data labeling during model training is high, resulting in low accuracy of pedestrian re-identification results. Contents of the inv...
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
Login to View More IPC IPC(8): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V40/10G06V20/42G06N3/045
Inventor 丁贵广何涛
Owner TSINGHUA UNIV