Station degradation face recognition library allocation method based on roulette
A technology of face recognition and roulette, which is applied in character and pattern recognition, instruments, still image data indexing, etc., can solve the problem of loss of usability of face-passing service and achieve good practical adaptability
Inactive Publication Date: 2022-08-02
NANJING PANDA ELECTRONICS +1
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In practical applications, face recognition is realized by relying on network communication between the terminal device and the cloud platform that usually passes through the network, but when there is a network communication failure or a failure of the face recognition cloud platform, the face recognition service will be lost. availability
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
[0038] The technical solutions of the present invention will be further described below with reference to the accompanying drawings.
[0039] like figure 1 As shown, a roulette-based station downgraded face recognition library distribution method includes the following steps:
[0040] S1. Statistical preprocessing is performed based on the big data OD of passengers brushing their faces and going through the gate;
[0041] common n passengers, m sites, in the statistical interval t , the number of times the passengers are swiping in and out of the station can be calculated using the matrix C express:
[0042]
[0043] Assemble over a continuous statistical interval , it is possible to obtain the C ( t k ) whose matrix elements are .
[0044] in c ij represented in the statistical interval t The number of face-swiping entry and exit times of passenger i at station j. for different statistical intervals t , you can get different statistical results C ( t )....
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 discloses a station degraded face recognition library distribution method based on a roulette. The method comprises the following steps: performing statistical preprocessing based on big data OD of passenger face-swiping lockage travel; based on the statistical matrix on the statistical interval set, calculating a probability matrix of all passengers at all stations through multiple linear regression; carrying out normalization processing on the frequent rate matrix; and selecting a given number of degraded face libraries from all passengers on the normalized matrix based on a roulette method, and allocating the degraded face libraries to each station. The degraded face database allocated to each station has the advantages of small scale and high coverage rate, can dynamically roll according to the travel rule of passengers, and can effectively support the station to autonomously realize face recognition calculation under the condition that a network platform is available.
Description
technical field [0001] The invention relates to urban rail transit, in particular to a roulette-based station downgraded face recognition library distribution method. Background technique [0002] With the continuous development of urban rail, more and more urban people choose the subway as their daily commuting tool. At the same time, with the continuous development of machine vision technology, biometric recognition technology represented by face recognition has entered our daily life. The typical face recognition architecture includes terminal services and cloud services, in which the terminal can not only collect face images, but also extract face image features. The cloud platform is responsible for the preservation of the face database and the comparison of face features, that is, to the terminal The device provides face recognition service. The face recognition system used in rail transit to pass through the gate can reach the payment level by configuring a high-conc...
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): G06V40/16G06V40/50G06V10/74G06K9/62G06F16/51G06F17/18G07C9/00G07C9/37
CPCG06V40/16G06V40/50G06V10/74G06F16/51G06F17/18G07C9/00G07C9/37
Inventor 焦科杰陆斌刘光杰张鹏高申吴娟熊伟顾伟王松松胡天澍潘辉桂大发徐亮李熙源张建闫震
Owner NANJING PANDA ELECTRONICS