Pedestrian image preprocessing method and device based on pedestrian re-identification
An image preprocessing, pedestrian re-identification technology, applied in the field of neural networks, can solve the problem of failing to obtain high-quality pedestrian images, and achieve the goal of improving portability, reducing complexity, enhancing robustness and generalization ability. Effect
Pending Publication Date: 2022-06-28
WINNER TECH CO INC
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide a pedestrian image preprocessing method and device based on pedestrian re-identification, which is used to solve the problem of failing to obtain high-quality images before pedestrian re-identification processing in the prior art. Problems with Pedestrian Images
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
[0031] The embodiments of the present invention are described below through specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments may be combined with each other under the condition of no conflict.
[0032] It should be noted that the drawings provided in the following embodiments are only used to illustrate the basic concept of the present invention in a schematic way, so the drawings only show the components related to the present invention rather than the number, shape and number of compo...
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 provides a pedestrian image preprocessing method and device based on pedestrian re-identification, and the method comprises the steps: determining an image feature corresponding to a pedestrian image based on the to-be-processed pedestrian image through a first feature extraction module of a neural network model; based on the image features, applying an interpolation scaling algorithm to determine the image features after interpolation scaling; based on the image features after interpolation scaling, a second feature extraction module and a third feature extraction module of a neural network model are applied to determine a scaled image; based on the image features after interpolation scaling, a perspective matrix corresponding to the image features is determined by applying a fourth feature extraction module and a perspective transformation module of a neural network model; and determining a processed pedestrian image by applying a perspective transformation method based on the scaled image and the perspective matrix. According to the pedestrian image preprocessing method, the style influence caused by image preprocessing can be reduced.
Description
technical field [0001] The invention relates to the field of neural networks, in particular to a pedestrian image preprocessing method and device based on pedestrian re-identification. Background technique [0002] Pedestrian re-identification (Re-ID) technology is a popular direction in computer vision research. retrieve. However, the type of camera, the capture angle, and the actual environment of the scene will directly affect the quality of the captured pedestrian image, so the quality of the pedestrian image is very important. [0003] In the prior art, different cameras have different imaging sensors, and in addition to the adjustment of parameters, imaging conditions, and imaging angles, the pedestrian images obtained by the same camera are often prone to different degrees of perspective distortion and picture distortion at different positions on the screen; and After obtaining the pedestrian image through the camera, it is necessary to accurately locate the image p...
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): G06V40/10G06V10/82G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 游浩泉袁德胜陈宏锐王海涛成西峰崔龙党毅飞刘耀文
Owner WINNER TECH CO INC