CN111062294B - Passenger flow queuing time detection method, device and system - Google Patents
Passenger flow queuing time detection method, device and system Download PDFInfo
- Publication number
- CN111062294B CN111062294B CN201911260108.3A CN201911260108A CN111062294B CN 111062294 B CN111062294 B CN 111062294B CN 201911260108 A CN201911260108 A CN 201911260108A CN 111062294 B CN111062294 B CN 111062294B
- Authority
- CN
- China
- Prior art keywords
- face
- time
- queuing
- snapshot time
- clustering
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims 1
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 239000013598 vector Substances 0.000 description 5
- 230000006399 behavior Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 210000000887 face Anatomy 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C11/00—Arrangements, systems or apparatus for checking, e.g. the occurrence of a condition, not provided for elsewhere
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of artificial intelligence and discloses a passenger flow queuing time detection method, device and system. The method comprises the following steps: acquiring a video image frame set to be detected; performing face clustering according to the video image frame set to be detected, and obtaining at least one group of identical face clustering sets; the same face cluster set includes: face characteristic information and face snapshot time information; and determining the queuing time of the same face clustering set according to the face characteristic information and the face time information. By adopting the technical scheme of the invention to determine the queuing time of the queuing personnel, the queuing time of the queuing personnel can be accurately determined, the hardware cost can be saved, and the demand of computing resources can be reduced.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a passenger flow queuing time detection method, device and system.
Background
In recent years, deep learning techniques represented by convolutional neural networks are widely used for various artificial intelligence tasks such as object classification, face recognition, pedestrian identification and the like. The breakthrough progress made by convolutional neural networks in these problems stems from the strong expressive power that is brought about by its hierarchical learning structure. In the context of passenger flow statistics applications, passenger flow queuing time is a very important parameter. The estimated queuing time is subject to errors due to the unknown passenger flow velocity. The passenger flow speed is usually set according to field experience, and if the passenger flow speed is changed, the passenger flow speed cannot be updated in time.
Since passenger flow queuing time is a very important information. By estimating the queuing time of the passenger flow, a passenger flow guiding scheme can be made. If the passenger flow is overcrowded, customers are liable to give up queuing, and the yield is reduced. In subways, parks, etc., even a trampling event may be initiated.
However, estimation of the queuing time of the passenger flow is also a very difficult problem. First, information on passenger flows is difficult to collect. In the conventional method, a gate is placed at the entrance to count the passenger flow, so as to estimate the queuing time. Second, customers may have variations in the queuing process, such as queue insertion, relinquishing, etc. In addition, when the passenger flow is very crowded, the shielding problem exists between customers, so that the acquired information is incomplete.
In the implementation process of the prior art, the inventor finds that at least the following technical problems exist in the prior art:
in the prior art, passenger flow queuing time detection is not accurate enough, real-time judgment cannot be performed according to actual conditions, real-time queuing time is given, and a plurality of hardware devices are needed to be matched for implementation, so that the use and maintenance cost of the system is high.
Disclosure of Invention
The invention aims to provide a method, a device and a system for detecting passenger flow queuing time, which are used for overcoming the defects in the prior art.
In order to solve the above technical problems, an embodiment of the present invention provides a method for detecting a queuing time of a passenger flow, including:
acquiring a video image frame set to be detected;
performing face clustering according to the video image frame set to be detected, and obtaining at least one group of identical face clustering sets; the same face cluster set includes: face characteristic information and face snapshot time information;
and determining the queuing time of the same face clustering set according to the face characteristic information and the face time information.
The embodiment of the invention also provides a passenger flow queuing time detection device, which comprises the following steps of.
The information acquisition unit is used for acquiring a video image frame set to be detected;
the clustering unit is used for carrying out face clustering according to the video image frame set to be detected and obtaining at least one group of identical face clustering set; the same face cluster set includes: face characteristic information and face snapshot time information;
and the queuing time determining unit is used for determining the queuing time of the same face clustering set according to the face characteristic information and the face time information.
The embodiment of the invention also provides a system for detecting the queuing time of the passenger flow, which comprises the following steps: the passenger flow queuing time detection device is described above.
The invention provides a method, a device and a system for detecting the queuing time of passenger flow, which are used for acquiring a video image frame set to be detected; performing face clustering according to the video image frame set to be detected, and obtaining at least one group of identical face clustering sets; the same face cluster set includes: face characteristic information and face snapshot time information; and determining the queuing time of the same face clustering set according to the face characteristic information and the face time information. By adopting the technical scheme of the invention to determine the queuing time of the queuing personnel, the queuing time of the queuing personnel can be accurately determined, the hardware cost can be saved, and the demand of computing resources can be reduced.
Drawings
FIG. 1 is a flow chart of a method for detecting queuing time of passenger flow, which is provided by an embodiment of the invention;
fig. 2 (a) is a schematic diagram of queuing time calculation according to a method for detecting queuing time of passenger flow according to an embodiment of the present invention;
FIG. 2 (b) is a queuing time calculation list of a detection method for queuing time of passenger flow in combination with FIG. 2 (a) according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a device for detecting queuing time of passenger flow according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, those of ordinary skill in the art will understand that in various embodiments of the present invention, numerous technical details have been set forth in order to provide a better understanding of the present application. However, the technical solutions claimed in the claims of the present application can be realized without these technical details and various changes and modifications based on the following embodiments.
The first embodiment of the invention relates to a passenger flow queuing time detection method. The specific flow is shown in figure 1. The method comprises the following steps:
101: acquiring a video image frame set to be detected;
102: performing face clustering according to the video image frame set to be detected, and obtaining at least one group of identical face clustering sets; the same face cluster set includes: face characteristic information and face snapshot time information;
103: and determining the queuing time of the same face clustering set according to the face characteristic information and the face time information.
It should be noted that, the step of performing face clustering according to the to-be-detected video image frame set to obtain at least one identical face clustering set includes:
carrying out face recognition on each frame in the video image frame set to be detected to obtain face attribute information;
carrying out face clustering according to the face attribute information to obtain at least one group of identical face clustering sets; the same face cluster set includes: face feature information and face snapshot time information.
The step of determining the queuing time of the same face clustering set according to the face feature information and the face time information further includes:
according to the face characteristic information and the face time information, sequencing all faces in the same face clustering set according to time sequence; the face time information corresponding to the same face clustering set comprises: the first snapshot time and the last snapshot time;
sequencing the at least one group of identical face cluster sets according to the first snapshot time to obtain identical face cluster sets 1,2, … …, N-1 and N;
and determining the queuing time of the same face cluster set 1,2, … …, N-1 and N according to the first snapshot time of the same face cluster set N and the last snapshot time of the same face cluster set N-1.
It should also be noted that the same face cluster sets 1,2, … …, N-1, N;
if the first snapshot time of the same face cluster set N is greater than or equal to the last snapshot time of the same face cluster set N-1, the queuing time of the person corresponding to the same face cluster set N is 0.
Based on the specific embodiment shown in fig. 1, a camera is installed on the front of the queuing area, namely, the camera can shoot the front face of queuing personnel; the height of the camera is 2.5m-3.5m, and the inclination angle is 45 degrees, so that the tail of a team can be shot. In the detection process, firstly, capturing and extracting face features; the essence of face recognition is that a model is needed to extract the feature vector of a face picture, two feature vectors of the same person are close, and two feature vectors of different persons are far. The scheme uses a deep learning algorithm to construct a face recognition model to recognize faces in images. The face recognition model process comprises three processes of key point detection, face alignment and face comparison, wherein the key point detection model detects 5 key points (two eyes, nose and two mouth corners) of the face of the queuing crowd, the face is aligned through a face alignment algorithm, and finally a 256-dimensional feature vector is calculated through the face recognition model and recorded asf. For all extracted feature sets in the ith moment image at the entrance of the queuing area, it is marked as F i ={f i,k I k=1, 2,3.. } k is the face number in the image. Secondly, face matching and clustering; for F i ={f i,k And (3) starting from the first snapshot at the first moment, calculating cosine distances between the first snapshot and feature vectors of all snapshots within the next maximum queuing time, and if the cosine distances are greater than a certain threshold, considering the different snapshots of the same person, and clustering. Wherein the maximum queuing time and the threshold are superparameters that can be adjusted with the actual scene.
In the present invention, the queuing time refers to the time from the start of queuing to the head of queuing as shown in fig. 2 (a) and 2 (b). The face snapshots of the same person are clustered through a face comparison method, and the face snapshot blocking method can effectively solve the problem that face snapshots are blocked in teams. The minimum time in the face cluster is considered as queuing start time, and the maximum time is considered as leaving time. As shown in the figure, when there is no queuing behavior, the queuing time is 0, and if there is queuing behavior, the queuing time cannot be calculated only by the departure time and the queuing start time. The algorithm also needs to know the queuing start time and departure time of the previous person. The clustered face snapshots are ranked according to the minimum time, and the sequence of teams is obtained. If the minimum snapshot time (i.e., first snapshot time) of the queuing person is less than the maximum snapshot time (i.e., last snapshot time) of the previous person, then the person queuing time is (departure time-start queuing time) - (departure time-previous person departure time). If the minimum snapshot time of a queuing person is greater than the maximum snapshot time of the previous person, then the queuing time of that person is 0. From this strategy and so on, the queuing times of all people can be obtained.
The technology effectively estimates the queuing time of queuing personnel based on the face characteristic information extracted by deep learning, and provides effective information for business planning of stores. The camera is reasonably installed to shoot pedestrians in a natural state, and a good estimation result can be obtained under the condition of shielding.
In addition, the technology of the invention scientifically and reasonably utilizes the face information of queuing personnel and the prior information of queuing behavior. Therefore, the hardware cost can be saved, the demand of computing resources is reduced, and the queuing situation can be analyzed by using only one camera.
A second embodiment of the present invention relates to a device for detecting queuing time of passenger flow, as shown in fig. 3, the device includes:
an information acquisition unit 301, configured to acquire a set of video image frames to be detected;
the clustering unit 302 is configured to perform face clustering according to the set of video image frames to be detected, and obtain at least one set of identical face clustering sets; the same face cluster set includes: face characteristic information and face snapshot time information;
a queuing time determining unit 303, configured to determine queuing times of the same face cluster set according to the face feature information and the face time information.
The clustering unit is further configured to perform face recognition on each frame in the video image frame set to be detected, and obtain face attribute information; carrying out face clustering according to the face attribute information to obtain at least one group of identical face clustering sets; the same face cluster set includes: face feature information and face snapshot time information.
The queuing time determining unit is further configured to sort each face in the same face cluster set according to time sequence according to the face feature information and the face time information; the face time information corresponding to the same face clustering set comprises: the first snapshot time and the last snapshot time; sequencing the at least one group of identical face cluster sets according to the first snapshot time to obtain identical face cluster sets 1,2, … …, N-1 and N; and determining the queuing time of the same face cluster set 1,2, … …, N-1 and N according to the first snapshot time of the same face cluster set N and the last snapshot time of the same face cluster set N-1.
It should also be noted that the same face cluster sets 1,2, … …, N-1, N; if the first snapshot time of the same face cluster set N is greater than or equal to the last snapshot time of the same face cluster set N-1, the queuing time of the person corresponding to the same face cluster set N is 0.
A third embodiment of the present invention relates to a system for detecting queuing time of passenger flow, including: the passenger flow queuing time detection device is described above.
It is to be noted that this embodiment is an example of a device corresponding to the first embodiment, and can be implemented in cooperation with the first embodiment. The related technical details mentioned in the first embodiment are still valid in this embodiment, and in order to reduce repetition, a detailed description is omitted here. Accordingly, the related art details mentioned in the present embodiment can also be applied to the first embodiment.
It should be noted that each module in this embodiment is a logic module, and in practical application, one logic unit may be one physical unit, or may be a part of one physical unit, or may be implemented by a combination of multiple physical units. In addition, in order to highlight the innovative part of the present invention, units that are not so close to solving the technical problem presented by the present invention are not introduced in the present embodiment, but this does not indicate that other units are not present in the present embodiment.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
For convenience of description, the above apparatus is described as being functionally divided into various units/modules, respectively. Of course, the functions of the various elements/modules may be implemented in the same piece or pieces of software and/or hardware when implementing the present invention.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), or the like.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any changes or substitutions easily contemplated by those skilled in the art within the scope of the present invention should be included in the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (5)
1. The method for detecting the passenger flow queuing time is characterized by comprising the following steps of:
acquiring a video image frame set to be detected;
performing face clustering according to the video image frame set to be detected, and obtaining at least one group of identical face clustering sets; the same face cluster set includes: face characteristic information and face snapshot time information;
according to the face characteristic information and the face snapshot time information, determining the queuing time of the same face clustering set;
the step of determining the queuing time of the same face clustering set according to the face characteristic information and the face snapshot time information comprises the following steps:
according to the face characteristic information and the face snapshot time information, sequencing all faces in the same face clustering set according to time sequence; the face snapshot time information corresponding to the same face clustering set comprises: the first snapshot time and the last snapshot time;
sequencing the at least one group of identical face cluster sets according to the first snapshot time to obtain sequenced identical face cluster sets;
determining queuing time of the same face cluster set according to first snapshot time of the current same face cluster set and last snapshot time of the previous same face cluster set in the ordered same face cluster sets; if the first snapshot time of the current same face cluster set in the ordered same face cluster set is smaller than the last snapshot time of the previous same face cluster set, the queuing time of the person corresponding to the current same face cluster set is the difference value between the last snapshot time of the previous same face cluster set and the first snapshot time of the current same face cluster set; and if the first snapshot time of the current group of identical face cluster sets in the ordered identical face cluster sets is greater than or equal to the last snapshot time of the previous group of identical face cluster sets, the queuing time of the people corresponding to the current group of identical face cluster sets is 0.
2. The method for detecting the queuing time of passenger flow according to claim 1, wherein the step of performing face clustering according to the set of video image frames to be detected to obtain at least one set of identical face clusters comprises the steps of:
carrying out face recognition on each frame in the video image frame set to be detected to obtain face attribute information;
and carrying out face clustering according to the face attribute information to obtain at least one group of identical face clustering sets.
3. A passenger flow queuing time detection device, comprising:
the information acquisition unit is used for acquiring a video image frame set to be detected;
the clustering unit is used for carrying out face clustering according to the video image frame set to be detected and obtaining at least one group of identical face clustering set; the same face cluster set includes: face characteristic information and face snapshot time information;
the queuing time determining unit is used for determining the queuing time of the same face clustering set according to the face characteristic information and the face snapshot time information; the face extraction module is also used for sequencing all faces in the same face clustering set according to the face characteristic information and the face snapshot time information and time sequence; the face snapshot time information corresponding to the same face clustering set comprises: the first snapshot time and the last snapshot time; sequencing the at least one group of identical face cluster sets according to the first snapshot time to obtain sequenced identical face cluster sets; determining queuing time of the same face cluster set according to first snapshot time of the current same face cluster set and last snapshot time of the previous same face cluster set in the ordered same face cluster sets; if the first snapshot time of the current same face cluster set in the ordered same face cluster set is smaller than the last snapshot time of the previous same face cluster set, the queuing time of the person corresponding to the current same face cluster set is the difference value between the last snapshot time of the previous same face cluster set and the first snapshot time of the current same face cluster set; and if the first snapshot time of the current group of identical face cluster sets in the ordered identical face cluster sets is greater than or equal to the last snapshot time of the previous group of identical face cluster sets, the queuing time of the people corresponding to the current group of identical face cluster sets is 0.
4. The passenger flow queuing time detection device according to claim 3, wherein the clustering unit is further configured to perform face recognition on each frame in the set of video image frames to be detected to obtain face attribute information; and carrying out face clustering according to the face attribute information to obtain at least one group of identical face clustering sets.
5. A system for detecting queuing time of passenger flow, the system comprising: a passenger flow queuing time detection apparatus as claimed in claim 3 or 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911260108.3A CN111062294B (en) | 2019-12-10 | 2019-12-10 | Passenger flow queuing time detection method, device and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911260108.3A CN111062294B (en) | 2019-12-10 | 2019-12-10 | Passenger flow queuing time detection method, device and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111062294A CN111062294A (en) | 2020-04-24 |
CN111062294B true CN111062294B (en) | 2024-03-22 |
Family
ID=70300309
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911260108.3A Active CN111062294B (en) | 2019-12-10 | 2019-12-10 | Passenger flow queuing time detection method, device and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111062294B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113012335A (en) * | 2021-03-22 | 2021-06-22 | 上海工程技术大学 | Subway platform guide queuing system based on YOLOv3 face detection |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105139040A (en) * | 2015-10-13 | 2015-12-09 | 商汤集团有限公司 | Queuing state information detection method and system thereof |
CN105530319A (en) * | 2016-01-26 | 2016-04-27 | 上海斐讯数据通信技术有限公司 | Detection method for queuing state information, system and server terminal having the system |
CN105632003A (en) * | 2014-11-04 | 2016-06-01 | 香港理工大学深圳研究院 | Evaluation method and apparatus thereof for customs clearance port queuing time |
CN107578521A (en) * | 2017-08-22 | 2018-01-12 | 西南交通大学 | Queuing management method and system, electronic equipment and computer-readable recording medium |
CN109145844A (en) * | 2018-08-29 | 2019-01-04 | 北京旷视科技有限公司 | Archive management method, device and electronic equipment for city safety monitoring |
CN109767196A (en) * | 2019-01-22 | 2019-05-17 | 武汉武吉智能科技有限公司 | A kind of intelligent attendance system |
CN110046535A (en) * | 2018-01-16 | 2019-07-23 | 国民技术股份有限公司 | Intelligent travel time prediction system, method and storage medium based on machine learning |
CN110059668A (en) * | 2019-04-29 | 2019-07-26 | 中国民用航空总局第二研究所 | Behavior prediction processing method, device and electronic equipment |
CN110399835A (en) * | 2019-07-26 | 2019-11-01 | 北京文安智能技术股份有限公司 | A kind of analysis method of personnel's residence time, apparatus and system |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160191865A1 (en) * | 2014-12-30 | 2016-06-30 | Nice-Systems Ltd. | System and method for estimating an expected waiting time for a person entering a queue |
JP6840492B2 (en) * | 2016-08-30 | 2021-03-10 | キヤノン株式会社 | Information processing equipment, information processing methods and programs |
-
2019
- 2019-12-10 CN CN201911260108.3A patent/CN111062294B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105632003A (en) * | 2014-11-04 | 2016-06-01 | 香港理工大学深圳研究院 | Evaluation method and apparatus thereof for customs clearance port queuing time |
CN105139040A (en) * | 2015-10-13 | 2015-12-09 | 商汤集团有限公司 | Queuing state information detection method and system thereof |
CN105530319A (en) * | 2016-01-26 | 2016-04-27 | 上海斐讯数据通信技术有限公司 | Detection method for queuing state information, system and server terminal having the system |
CN107578521A (en) * | 2017-08-22 | 2018-01-12 | 西南交通大学 | Queuing management method and system, electronic equipment and computer-readable recording medium |
CN110046535A (en) * | 2018-01-16 | 2019-07-23 | 国民技术股份有限公司 | Intelligent travel time prediction system, method and storage medium based on machine learning |
CN109145844A (en) * | 2018-08-29 | 2019-01-04 | 北京旷视科技有限公司 | Archive management method, device and electronic equipment for city safety monitoring |
CN109767196A (en) * | 2019-01-22 | 2019-05-17 | 武汉武吉智能科技有限公司 | A kind of intelligent attendance system |
CN110059668A (en) * | 2019-04-29 | 2019-07-26 | 中国民用航空总局第二研究所 | Behavior prediction processing method, device and electronic equipment |
CN110399835A (en) * | 2019-07-26 | 2019-11-01 | 北京文安智能技术股份有限公司 | A kind of analysis method of personnel's residence time, apparatus and system |
Non-Patent Citations (3)
Title |
---|
Automated Attendance Systems Using Face Recognition by K-Means Algorithms;Dr.PALANIVEL. N;《Processing of International Conference on Systems Computation Automation and Networking 2019》;1-8 * |
基于人脸识别的课堂考勤系统的设计与实现;张其帆;《中国优秀硕士学位论文全文数据库 (信息科技辑)》(第2019(08)期);I138-352 * |
建设银行T支行排队系统研究;孟悦;《中国优秀硕士学位论文全文数据库 (经济与管理科学辑)》(第2019(07)期);J159-205 * |
Also Published As
Publication number | Publication date |
---|---|
CN111062294A (en) | 2020-04-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103824070B (en) | A kind of rapid pedestrian detection method based on computer vision | |
Saxena et al. | Crowd behavior recognition for video surveillance | |
CN104751136B (en) | A kind of multi-camera video event back jump tracking method based on recognition of face | |
KR102217253B1 (en) | Apparatus and method for analyzing behavior pattern | |
CN107230267B (en) | Intelligence In Baogang Kindergarten based on face recognition algorithms is registered method | |
CN110399835B (en) | Analysis method, device and system for personnel residence time | |
JP2004199669A (en) | Face detection | |
JP2004192637A (en) | Face detection | |
Hashemzadeh et al. | Counting moving people in crowds using motion statistics of feature-points | |
KR101472674B1 (en) | Method and apparatus for video surveillance based on detecting abnormal behavior using extraction of trajectories from crowd in images | |
CN111353338A (en) | Energy efficiency improvement method based on business hall video monitoring | |
WO2013075295A1 (en) | Clothing identification method and system for low-resolution video | |
CN112215156A (en) | Face snapshot method and system in video monitoring | |
CN109902550A (en) | The recognition methods of pedestrian's attribute and device | |
Lijun et al. | Video-based crowd density estimation and prediction system for wide-area surveillance | |
CN110826390A (en) | Video data processing method based on face vector characteristics | |
Yang et al. | A method of pedestrians counting based on deep learning | |
CN110175553B (en) | Method and device for establishing feature library based on gait recognition and face recognition | |
CN113436231B (en) | Pedestrian track generation method, device, equipment and storage medium | |
CN111046769A (en) | Queuing time detection method, device and system | |
CN111062294B (en) | Passenger flow queuing time detection method, device and system | |
Lee et al. | Estimation and analysis of urban traffic flow | |
Ilao et al. | Crowd estimation using region-specific HOG With SVM | |
WO2022228325A1 (en) | Behavior detection method, electronic device, and computer readable storage medium | |
Hsieh et al. | Grid-based template matching for people counting |
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 | ||
CB02 | Change of applicant information |
Country or region after: China Address after: 1602, 16th Floor, Building 4, Zone 4, No. 81 Beiqing Road, Haidian District, Beijing, 100094 Applicant after: BEIJING VION INTELLIGENT TECHNOLOGY Co.,Ltd. Address before: Unit 801, Unit 5, No. 2 Building, 9 Yuan, Fenghao East Road, Haidian District, Beijing 100094 Applicant before: BEIJING VION INTELLIGENT TECHNOLOGY Co.,Ltd. Country or region before: China |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |