CN114783038A - Automatic identification method and system for unregistered passenger and electronic equipment - Google Patents
Automatic identification method and system for unregistered passenger and electronic equipment Download PDFInfo
- Publication number
- CN114783038A CN114783038A CN202210694267.XA CN202210694267A CN114783038A CN 114783038 A CN114783038 A CN 114783038A CN 202210694267 A CN202210694267 A CN 202210694267A CN 114783038 A CN114783038 A CN 114783038A
- Authority
- CN
- China
- Prior art keywords
- data set
- candidate data
- unregistered
- registration
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012216 screening Methods 0.000 claims description 15
- 238000010276 construction Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 12
- 239000013598 vector Substances 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000005286 illumination Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000013024 troubleshooting Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/14—Travel agencies
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an automatic identification method, a system and electronic equipment for unregistered passengers, wherein the method comprises the following steps: acquiring an image data set of an unregistered passenger; constructing a candidate data set of the unregistered passenger according to the registration quality and the identification score of the image data set; carrying out hierarchical clustering on the candidate data set to obtain a structured candidate data set; determining a registration template of the unregistered passenger according to the number of clustering centers in the structured candidate data set; and identifying the unregistered passenger according to the registration template. The invention obtains the structured candidate data set by carrying out hierarchical clustering on the candidate data set, and identifies the unregistered passenger by determining the registration template of the unregistered passenger based on the structured candidate data set, so that the accuracy of identification can be greatly improved.
Description
Technical Field
The invention belongs to the technical field of urban rail transit, and particularly relates to an automatic identification method and system for unregistered passengers and electronic equipment.
Background
Subway is one of the traffic ways commonly used in modern times, and the use frequency is higher and higher in recent years. Because compare with public transit, the problem that blocks up has been solved to the subway, has greatly shortened the trip time. However, the following problems occur, and because the number of people who take the subway is very large, the subway security check queuing also becomes a problem, and the conventional security check method generally checks pedestrians one by subway staff, so that the working efficiency is very low.
Disclosure of Invention
The invention aims to provide an automatic identification method, system and electronic equipment for unregistered passengers, and aims to solve the problem of low efficiency of manual pedestrian troubleshooting.
In order to achieve the purpose, the invention adopts the technical scheme that:
an automatic identification method for unregistered passengers, comprising the following steps:
step 1: acquiring an image data set of an unregistered passenger;
and 2, step: constructing a candidate data set of the unregistered passenger according to the registration quality and the identification score of the image data set;
and step 3: carrying out hierarchical clustering on the candidate data set to obtain a structured candidate data set;
and 4, step 4: determining a registration template of the unregistered passenger according to the number of the clustering centers in the structured candidate data set;
and 5: and identifying the unregistered passenger according to the registration template.
Preferably, the step 2: constructing a candidate data set of unregistered passengers according to the registration quality and the identification score of the image data set, wherein the candidate data set comprises:
step 2.1: inputting the image data set into a registered image quality model to obtain the registered quality of each image;
step 2.2: removing the corresponding images with the registration quality smaller than a preset threshold value to obtain images meeting the registration quality requirement;
step 2.3: inputting the image which meets the registration quality requirement into a face recognition model to obtain a recognition score;
step 2.4: and removing the images with the identification scores smaller than the identification threshold value to obtain a candidate data set of the unregistered passenger.
Preferably, the step 3: performing hierarchical clustering on the candidate data set to obtain a structured candidate data set, including:
step 3.1: clustering the images in the candidate data set according to the tracking chain information of each image to obtain a subclass center;
step 3.2: and clustering the subclass centers according to the matching distance to obtain a structured candidate data set.
Preferably, the step 4: determining a registration template for an unregistered traveler according to the number of cluster centers in the structured candidate data set, comprising:
and screening the representative image of each clustering center as a registration template of the unregistered passenger according to the acquisition time information and the registration quality information of each image in the structured candidate data set.
The invention also provides an automatic identification system for unregistered passengers, which comprises:
the image data set acquisition module is used for acquiring an image data set of the unregistered passenger;
the candidate data set construction module is used for constructing a candidate data set of the unregistered passenger according to the registration quality and the identification score of the image data set;
the hierarchical clustering module is used for carrying out hierarchical clustering on the candidate data sets to obtain structured candidate data sets;
the registration template determining module is used for determining the registration template of the unregistered passenger according to the number of the clustering centers in the structured candidate data set;
and the automatic identification module is used for identifying the unregistered passenger according to the registration template.
Preferably, the candidate data set construction module comprises:
a registration quality obtaining unit, configured to input the image data set into a registration image quality model to obtain registration quality of each image;
the registration quality screening unit is used for removing the corresponding images with the registration quality smaller than a preset threshold value to obtain images meeting the registration quality requirement;
the identification score acquisition unit is used for inputting the image which meets the registration quality requirement into a face identification model to obtain an identification score;
and the candidate data set construction module is used for removing the images with the identification scores smaller than the identification threshold value to obtain a candidate data set of the unregistered passenger.
Preferably, the hierarchical clustering module comprises:
the screening unit is used for screening the images in the candidate data set according to the tracking chain information, the acquisition time information and the registration quality information of each image to obtain screened images;
the clustering unit is used for clustering the screened images according to meta information to obtain subclass centers;
and the subclass center clustering unit is used for clustering the subclass centers according to the matching distance to obtain a structured candidate data set.
Preferably, the enrollment template determination module includes:
and the registration template construction unit is used for screening the representative image of each clustering center as the registration template of the unregistered passenger according to the acquisition time information and the registration quality information of each image in the structured candidate data set.
The invention also provides an electronic device comprising a bus, a transceiver, a memory, a processor and a computer program stored in the memory and operable on the processor, wherein the transceiver, the memory and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of the above method for automatically identifying an unregistered passenger.
The invention also provides a computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of a method for automatic identification of an unregistered passenger as described above.
The method, the system and the electronic equipment for automatically identifying the unregistered passenger have the advantages that: compared with the prior art, the automatic identification method for the unregistered passenger comprises the following steps: acquiring an image data set of an unregistered passenger; constructing a candidate data set of the unregistered passenger according to the registration quality and the identification score of the image data set; carrying out hierarchical clustering on the candidate data set to obtain a structured candidate data set; determining a registration template of the unregistered passenger according to the number of clustering centers in the structured candidate data set; and identifying the unregistered passenger according to the registration template. According to the invention, the structured candidate data set is obtained by carrying out hierarchical clustering on the candidate data set, and the unregistered passenger is identified by determining the registration template of the unregistered passenger based on the structured candidate data set, so that the identification accuracy can be greatly improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed for the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a flow chart of a method for automatically identifying an unregistered traveler according to the present invention;
FIG. 2 is a schematic diagram of an automatic identification method for unregistered passengers according to the present invention;
FIG. 3 is a schematic diagram of candidate data set construction provided by the present invention;
fig. 4 is a schematic diagram of hierarchical clustering provided by the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
The invention aims to provide an automatic identification method, system and electronic equipment for unregistered passengers, and aims to solve the problem of low efficiency of manual pedestrian troubleshooting.
Referring to fig. 1-4, an automatic identification method for unregistered passengers includes the following steps:
s1: acquiring an image data set of an unregistered passenger;
the invention can take the unrecognized face image data set in a period of time as the original image data set of the unregistered passenger.
S2: constructing a candidate data set of the unregistered passenger according to the registration quality and the identification score of the image data set;
further, S2 includes:
s2.1: inputting the image data set into a registered image quality model to obtain the registered quality of each image; the quality model of the registered image can predict the corresponding conditions of illumination, posture, shielding and the like of the input image simultaneously in one feedforward operation by using the same deep learning network architecture through the CNN model and a multi-task combined training strategy, and the quality score of the registered quality of the image is predicted by synthesizing various conditions. Furthermore, the method can respectively design optimization loss functions for different optimization targets (illumination, posture, shielding and the like) in a multi-task joint training mode to construct a deep learning model; during reasoning, network reasoning results (registration quality) corresponding to illumination, posture, shielding and the like can be respectively obtained, wherein cross-entropy loss functions can be adopted for training illumination tasks; the training of the posture task can adopt cross-entropy + MSE loss function; the loss function of the key point (occlusion) task is the sum of the distances between the predicted point and the real mark point.
S2.2: removing the corresponding images with the registration quality smaller than a preset threshold value to obtain images meeting the registration quality requirement;
s2.3: inputting the image which meets the registration quality requirement into a face recognition model to obtain a recognition score; it should be noted that the face recognition model of the present invention can quickly find the approximately optimal vector of the distance input vector in the mega-high dimensional vector data set by using an indexing technique, and obtain the distance score (recognition score) between the two vectors. Furthermore, the invention can extract the high-dimensional characteristic vectors of the face image through a deep learning network, and then traverse and calculate the distance between the two high-dimensional characteristic vectors (various distance calculation formulas such as Euclidean distance and cosine distance can be used), wherein the obtained minimum distance is the distance score.
S2.4: removing images with identification scores less than the identification threshold results in a candidate data set for unregistered passengers. In practical applications, the judgment condition identified here needs to guarantee a certain score value space with the identification threshold of the image to guarantee that the face data is determined as an unregistered passenger, for example, for the face identification model a, if the identification threshold is 0.85 (when the distance score between the input image and an ID image in the template set is greater than 0.85, the image can be identified as the ID), in order to guarantee that the input image does not belong to any ID in the image template library, an identified gray area needs to be considered, and if the area score span is set to be 0.1, the judgment condition for identification needs to be less than 0.75 (0.85-0.1 = 0.75).
S3: carrying out hierarchical clustering on the candidate data set to obtain a structured candidate data set;
further, S3 includes:
s3.1: clustering the images in the candidate data set according to the tracking chain information of each image to obtain a subclass center;
s3.2: and clustering the subclass centers according to the matching distance to obtain a structured candidate data set.
In this embodiment, a cluster subset of images is first constructed according to tracking chain information of the images, and for the cluster subset, a representative image of the cluster subset needs to be jointly screened according to acquisition time information and registration quality information of each image and by combining with cluster center information. Further, firstly, clustering images for the first time according to the ID of the tracking chain; for the images with the same tracking chain ID, image filtering is carried out according to the acquisition time (namely the acquisition time is used for approximately estimating the distance between the face and an acquisition camera, for example, the sequence time length is 1 minute, data in the range from 20 seconds to 55 seconds can be selected, the distance between the face and the acquisition camera is considered to be too far before 20 seconds, the distance between the face and the acquisition camera is considered to be too close after 55 seconds, the time range selection can be statistically acquired through camera historical data), and then the image with the highest registration quality score is selected for the filtered image subset as the representative image of the cluster subset.
After meta information, namely tracking chain information, acquisition time information and registration quality information, is clustered, the sub-class centers are clustered according to the matching distance of the templates (such as K-Means or a clustering algorithm such as hierarchical clustering), face data of different tracking chains and different time are further unified into the same cluster data, and data structuring of a candidate data set can be realized.
S4: determining a registration template of the unregistered passenger according to the number of clustering centers in the structured candidate data set; in the embodiment of the present invention, S4 may be:
and screening the representative image of each clustering center as a registration template of the unregistered passenger according to the acquisition time information and the registration quality information of each image in the structured candidate data set. Wherein, the more dispersed the acquisition time of the representative image, the better the registration quality information).
S5: and identifying the unregistered passenger according to the registration template.
The registration template selection is based on a structured candidate data set, for each cluster category, the number of images (cluster center number) to be registered is selected according to the number of images in the category, and the representative images of the cluster category are jointly selected by combining the time information and the quality information of the images and are used as the registration template of the unregistered passenger for face registration, so that the automatic identification of the unregistered passenger can be realized when the passenger next approaches the station. In addition, in order to ensure accuracy, the invention needs to comprehensively consider various information to realize the automatic identification of the off-line unregistered passenger after certain data is accumulated; the invention can also adopt on-line registration, for example, when the unrecognized face image is selected, the image can be directly considered as an unregistered passenger, and then the image is directly marked to enter the system in real time.
The invention discloses an automatic identification method for unregistered passengers, which comprises the steps of inputting an unidentified face image data set in a period of time as an original data set of the unregistered passengers; starting a data selection strategy, comprehensively considering two dimensions of registration quality of the images and identification scores of the images, and constructing a candidate data set of the unregistered passenger; according to the candidate data set, making full use of multidimensional data Meta information and an accelerated hierarchical clustering strategy to perform data structuring on the candidate data set; based on the cluster data distribution, the final template data is selected as the registration template of the unregistered passenger, so that automatic identification is realized. The invention comprehensively considers the multidimensional Meta information, and can greatly improve the accuracy of identification while improving the clustering efficiency.
The invention also provides an automatic identification system for unregistered passengers, which comprises:
the image data set acquisition module is used for acquiring an image data set of the unregistered passenger;
the candidate data set construction module is used for constructing a candidate data set of the unregistered passenger according to the registration quality and the identification score of the image data set;
the hierarchical clustering module is used for carrying out hierarchical clustering on the candidate data sets to obtain structured candidate data sets;
the registration template determining module is used for determining the registration template of the unregistered passenger according to the number of the clustering centers in the structured candidate data set;
and the automatic identification module is used for identifying the unregistered passenger according to the registration template.
Preferably, the candidate data set construction module comprises:
a registration quality acquisition unit for inputting the image data set into a registration image quality model to obtain the registration quality of each image;
the registration quality screening unit is used for removing the corresponding images with the registration quality smaller than a preset threshold value to obtain images meeting the registration quality requirement;
the identification score acquisition unit is used for inputting the image meeting the registration quality requirement into the face identification model to obtain an identification score;
and the candidate data set construction module is used for removing the images with the identification scores smaller than the identification threshold value to obtain a candidate data set of the unregistered passenger.
Preferably, the hierarchical clustering module comprises:
the screening unit is used for screening the images in the candidate data set according to the tracking chain information, the acquisition time information and the registration quality information of each image to obtain screened images;
the clustering unit is used for clustering the screened images according to the meta information to obtain subclass centers;
and the subclass center clustering unit is used for clustering the subclass centers according to the matching distance to obtain a structured candidate data set.
Preferably, the enrollment template determination module includes:
and the registration template construction unit is used for screening the representative image of each clustering center according to the acquisition time information and the registration quality information of each image in the structured candidate data set, and taking the representative image as the registration template of the unregistered passenger.
The invention discloses an automatic identification method and system for unregistered passengers, wherein the method comprises the following steps: acquiring an image data set of an unregistered passenger; constructing a candidate data set of the unregistered passenger according to the registration quality and the identification score of the image data set; carrying out hierarchical clustering on the candidate data set to obtain a structured candidate data set; determining a registration template of the unregistered passenger according to the number of clustering centers in the structured candidate data set; and identifying the unregistered passenger according to the registration template. According to the invention, the structured candidate data set is obtained by carrying out hierarchical clustering on the candidate data set, and the unregistered passenger is identified by determining the registration template of the unregistered passenger based on the structured candidate data set, so that the identification accuracy can be greatly improved.
The invention also provides an electronic device, which comprises a bus, a transceiver, a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the transceiver, the memory and the processor are connected through the bus, and when the computer program is executed by the processor, each process of the embodiment of the automatic identification method for the unregistered passenger is realized, the same technical effect can be achieved, and the details are not repeated here to avoid repetition.
The invention also provides a computer-readable storage medium, on which a computer program is stored, wherein the computer program is executed by a processor to implement the steps in the above-mentioned method for automatically identifying an unregistered passenger, and the computer program is executed by the processor to implement the processes of the above-mentioned embodiment of the method for automatically identifying an unregistered passenger, and can achieve the same technical effects, and in order to avoid repetition, the description is omitted here.
The above description is intended to be illustrative of the preferred embodiment of the present invention and should not be taken as limiting the invention, but rather, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.
Claims (10)
1. An automatic identification method for unregistered passengers, which is characterized by comprising the following steps:
step 1: acquiring an image data set of an unregistered passenger;
and 2, step: constructing a candidate data set of the unregistered passenger according to the registration quality and the identification score of the image data set;
and 3, step 3: carrying out hierarchical clustering on the candidate data set to obtain a structured candidate data set;
and 4, step 4: determining a registration template of the unregistered passenger according to the number of the clustering centers in the structured candidate data set;
and 5: and identifying the unregistered passenger according to the registration template.
2. A method for automatic identification of an unregistered passenger as claimed in claim 1, wherein said step 2: constructing a candidate data set of unregistered passengers according to the registration quality and the identification score of the image data set, wherein the candidate data set comprises:
step 2.1: inputting the image data set into a registered image quality model to obtain the registered quality of each image;
step 2.2: removing the corresponding images with the registration quality smaller than a preset threshold value to obtain images meeting the registration quality requirement;
step 2.3: inputting the image which meets the registration quality requirement into a face recognition model to obtain a recognition score;
step 2.4: and removing the images with the identification scores smaller than the identification threshold value to obtain a candidate data set of the unregistered passenger.
3. A method for automatic identification of an unregistered passenger as claimed in claim 1, wherein said step 3: performing hierarchical clustering on the candidate data set to obtain a structured candidate data set, including:
step 3.1: clustering the images in the candidate data set according to the tracking chain information of each image to obtain a subclass center;
step 3.2: and clustering the subclass centers according to the matching distance to obtain a structured candidate data set.
4. A method for automatic identification of an unregistered passenger as claimed in claim 1, wherein said step 4: determining a registration template for an unregistered traveler according to the number of cluster centers in the structured candidate data set, comprising:
and screening the representative image of each clustering center as a registration template of the unregistered passenger according to the acquisition time information and the registration quality information of each image in the structured candidate data set.
5. An automatic identification system for an unregistered traveler, comprising:
the image data set acquisition module is used for acquiring an image data set of the unregistered passenger;
the candidate data set construction module is used for constructing a candidate data set of the unregistered passenger according to the registration quality and the identification score of the image data set;
the hierarchical clustering module is used for carrying out hierarchical clustering on the candidate data sets to obtain structured candidate data sets;
the registration template determining module is used for determining the registration template of the unregistered passenger according to the number of the clustering centers in the structured candidate data set;
and the automatic identification module is used for identifying the unregistered passenger according to the registration template.
6. The system of claim 5, wherein the candidate data set construction module comprises:
a registration quality obtaining unit, configured to input the image data set into a registration image quality model to obtain registration quality of each image;
the registration quality screening unit is used for removing the corresponding images with the registration quality smaller than a preset threshold value to obtain images meeting the registration quality requirement;
the identification score acquisition unit is used for inputting the image which meets the registration quality requirement into a face identification model to obtain an identification score;
and the candidate data set construction module is used for removing the images with the identification scores smaller than the identification threshold value to obtain a candidate data set of the unregistered passenger.
7. The system for automatically identifying unregistered passengers of claim 5, wherein the hierarchical clustering module comprises:
the screening unit is used for screening the images in the candidate data set according to the tracking chain information, the acquisition time information and the registration quality information of each image to obtain screened images;
the clustering unit is used for clustering the screened images according to meta information to obtain subclass centers;
and the subclass center clustering unit is used for clustering the subclass centers according to the matching distance to obtain a structured candidate data set.
8. The system of claim 5, wherein the registration template determination module comprises:
and the registration template construction unit is used for screening out the representative image of each clustering center as a registration template of the unregistered passenger according to the acquisition time information and the registration quality information of each image in the structured candidate data set.
9. An electronic device comprising a bus, a transceiver, a memory, a processor and a computer program stored on said memory and executable on said processor, said transceiver, said memory and said processor being connected via said bus, characterized in that said computer program, when executed by said processor, implements the steps of a method for automatic identification of an unregistered passenger as claimed in any one of claims 1 to 4.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of a method for automatic identification of an unregistered passenger according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210694267.XA CN114783038A (en) | 2022-06-20 | 2022-06-20 | Automatic identification method and system for unregistered passenger and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210694267.XA CN114783038A (en) | 2022-06-20 | 2022-06-20 | Automatic identification method and system for unregistered passenger and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114783038A true CN114783038A (en) | 2022-07-22 |
Family
ID=82421127
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210694267.XA Pending CN114783038A (en) | 2022-06-20 | 2022-06-20 | Automatic identification method and system for unregistered passenger and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114783038A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115512427A (en) * | 2022-11-04 | 2022-12-23 | 北京城建设计发展集团股份有限公司 | User face registration method and system combined with matched biopsy |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080304755A1 (en) * | 2007-06-08 | 2008-12-11 | Microsoft Corporation | Face Annotation Framework With Partial Clustering And Interactive Labeling |
| CN102067128A (en) * | 2009-04-27 | 2011-05-18 | 松下电器产业株式会社 | Data processing device, data processing method, program, and integrated circuit |
| CN106446797A (en) * | 2016-08-31 | 2017-02-22 | 腾讯科技（深圳）有限公司 | Image clustering method and device |
| CN107292252A (en) * | 2017-06-09 | 2017-10-24 | 南京华捷艾米软件科技有限公司 | A kind of personal identification method of autonomous learning |
| CN109086720A (en) * | 2018-08-03 | 2018-12-25 | 腾讯科技（深圳）有限公司 | A kind of face cluster method, apparatus and storage medium |
| CN109684913A (en) * | 2018-11-09 | 2019-04-26 | 长沙小钴科技有限公司 | A kind of video human face mask method and system based on community discovery cluster |
| CN114299435A (en) * | 2021-12-30 | 2022-04-08 | 北京爱奇艺科技有限公司 | Scene clustering method and device in video and related equipment |
| CN114332716A (en) * | 2021-12-30 | 2022-04-12 | 北京爱奇艺科技有限公司 | Method and device for clustering scenes in video, electronic equipment and storage medium |
-
2022
- 2022-06-20 CN CN202210694267.XA patent/CN114783038A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080304755A1 (en) * | 2007-06-08 | 2008-12-11 | Microsoft Corporation | Face Annotation Framework With Partial Clustering And Interactive Labeling |
| CN102067128A (en) * | 2009-04-27 | 2011-05-18 | 松下电器产业株式会社 | Data processing device, data processing method, program, and integrated circuit |
| CN106446797A (en) * | 2016-08-31 | 2017-02-22 | 腾讯科技（深圳）有限公司 | Image clustering method and device |
| CN107292252A (en) * | 2017-06-09 | 2017-10-24 | 南京华捷艾米软件科技有限公司 | A kind of personal identification method of autonomous learning |
| CN109086720A (en) * | 2018-08-03 | 2018-12-25 | 腾讯科技（深圳）有限公司 | A kind of face cluster method, apparatus and storage medium |
| CN109684913A (en) * | 2018-11-09 | 2019-04-26 | 长沙小钴科技有限公司 | A kind of video human face mask method and system based on community discovery cluster |
| CN114299435A (en) * | 2021-12-30 | 2022-04-08 | 北京爱奇艺科技有限公司 | Scene clustering method and device in video and related equipment |
| CN114332716A (en) * | 2021-12-30 | 2022-04-12 | 北京爱奇艺科技有限公司 | Method and device for clustering scenes in video, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 康耀龙等: "基于网格索引的云海大数据模糊聚类方法仿真", 《计算机仿真》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115512427A (en) * | 2022-11-04 | 2022-12-23 | 北京城建设计发展集团股份有限公司 | User face registration method and system combined with matched biopsy |
| CN115512427B (en) * | 2022-11-04 | 2023-04-25 | 北京城建设计发展集团股份有限公司 | User face registration method and system combined with matched biopsy |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111339990B (en) | Face recognition system and method based on dynamic update of face features | |
| CN103761531B (en) | The sparse coding license plate character recognition method of Shape-based interpolation contour feature | |
| CN102346847B (en) | License plate character recognizing method of support vector machine | |
| CN104778457B (en) | Video face identification method based on multi-instance learning | |
| KR100247969B1 (en) | Apparatus and method for massive pattern matching | |
| CN103605972A (en) | Non-restricted environment face verification method based on block depth neural network | |
| CN112070058A (en) | Face and face composite emotional expression recognition method and system | |
| CN109711384A (en) | A kind of face identification method based on depth convolutional neural networks | |
| CN111582178B (en) | Vehicle weight recognition method and system based on multi-azimuth information and multi-branch neural network | |
| CN109543753B (en) | License plate recognition method based on self-adaptive fuzzy repair mechanism | |
| CN105825233A (en) | Pedestrian detection method based on random fern classifier of online learning | |
| CN103905824A (en) | Video semantic retrieval and compression synchronization camera system and method | |
| CN107577994A (en) | A kind of pedestrian based on deep learning, the identification of vehicle auxiliary product and search method | |
| CN114783038A (en) | Automatic identification method and system for unregistered passenger and electronic equipment | |
| CN111104973B (en) | Knowledge attention-based fine-grained image classification method | |
| CN108921186A (en) | A kind of fingerprint image categorizing system and method based on twin support vector machines | |
| CN110555125A (en) | Vehicle retrieval method based on local features | |
| Shuai et al. | Multi-source feature fusion and entropy feature lightweight neural network for constrained multi-state heterogeneous iris recognition | |
| CN113011444A (en) | Image identification method based on neural network frequency domain attention mechanism | |
| CN110619280B (en) | Vehicle re-identification method and device based on deep joint discrimination learning | |
| CN111898454A (en) | Weight binarization neural network and transfer learning human eye state detection method and device | |
| Zheng et al. | Research on offline palmprint image enhancement | |
| CN112200831B (en) | Dynamic template-based dense connection twin neural network target tracking method | |
| CN106874920A (en) | License plate character recognition method based on wavelet packet analysis and SVMs | |
| Chen et al. | Chinese license plate recognition based on human vision attention mechanism |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220722 |