Method and equipment for generating vehicle re-identification model
A re-identification and vehicle technology, applied in the computer field, can solve problems such as disappearance and difficulty in solving, and achieve the effect of promoting training and accelerating convergence
Pending Publication Date: 2020-02-28
上海眼控科技股份有限公司
View PDF7 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In this problem, due to the position offset of the same car under different shooting conditions, some features used for discrimination may disappear; at the same time, there may be little difference between different vehicles
These phenomena make it very difficult to solve the problem
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
[0055] The present invention will be described in further detail below in conjunction with the accompanying drawings.
[0056] In a typical configuration of the present application, the terminal, the device serving the network and the trusted party all include one or more processors (CPUs), input / output interfaces, network interfaces and memory.
[0057] Memory may include non-permanent storage in computer readable media, in the form of random access memory (RAM) and / or nonvolatile memory such as read only memory (ROM) or flash RAM. Memory is an example of computer readable media.
[0058] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can be implemented by any method or technology for storage of information. Information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static rando...
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 aims to provide a method and equipment for generating a vehicle re-identification model. The basic network is trained based on the corresponding comparison loss value and classificationloss value of each picture pair so as to obtain the final vehicle re-identification neural network model, and the distance loss is used as the auxiliary loss of the model in the training stage so thatbetter training of the model can be further facilitated and convergence of the model can be accelerated. Besides, the distance loss is used as the auxiliary loss of the model in the training stage, in a subsequent test phase, whether the two vehicles are the same vehicle or not can be judged based on the classification value, namely, in the test stage, the classification value output by the modelis finally used as an evaluation mechanism for judging whether the two vehicle pictures belong to the same vehicle or not, so that the situation that a threshold value needs to be manually set in thetest stage is avoided, and whether the two vehicle pictures belong to the same vehicle or not can be judged without setting the threshold value in the test stage.
Description
technical field [0001] The invention relates to the field of computers, in particular to a method and device for generating a vehicle re-identification model. Background technique [0002] Vehicle Re-ID (Re-identification) refers to judging whether two vehicles belong to the same vehicle under different cameras. In this problem, due to the position shift of the same car under different shooting conditions, some features used for discrimination may disappear; at the same time, there may be little difference between different cars. These phenomena make solving the problem very difficult. [0003] As an important means to solve image problems, neural network has achieved great success in image recognition, object detection and other fields in recent years. In terms of vehicle Re-ID, the structure of the twin network is mainly used. In this method, a basic network needs to be used to extract the features of the image, and then based on the loss function, the distance between t...
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 Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/08
CPCG06N3/08G06V20/00G06V2201/08G06F18/22G06F18/2415G06F18/253G06F18/214
Inventor 周康明戚风亮
Owner 上海眼控科技股份有限公司