CN114937303B - Scenic spot registration monitoring method based on face recognition - Google Patents
Scenic spot registration monitoring method based on face recognition Download PDFInfo
- Publication number
- CN114937303B CN114937303B CN202210636975.8A CN202210636975A CN114937303B CN 114937303 B CN114937303 B CN 114937303B CN 202210636975 A CN202210636975 A CN 202210636975A CN 114937303 B CN114937303 B CN 114937303B
- Authority
- CN
- China
- Prior art keywords
- scenic spot
- scenic
- person
- spot
- area
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000012544 monitoring process Methods 0.000 title claims abstract description 22
- 230000009471 action Effects 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 23
- 230000001815 facial effect Effects 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 238000003384 imaging method Methods 0.000 claims description 4
- 230000003190 augmentative effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 9
- 230000036544 posture Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000009194 climbing Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
Images
Classifications
-
- 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
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063118—Staff planning in a project environment
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- 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
-
- 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
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B3/00—Audible signalling systems; Audible personal calling systems
- G08B3/10—Audible signalling systems; Audible personal calling systems using electric transmission; using electromagnetic transmission
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Human Computer Interaction (AREA)
- Operations Research (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Social Psychology (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Electromagnetism (AREA)
- Psychiatry (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Alarm Systems (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention provides a scenic spot registration monitoring method based on face recognition, which is characterized in that images shot at the entrance and exit of a scenic spot are compared to obtain the difference between the number and the identity of people entering and exiting the scenic spot, and the information of the people entering and exiting the scenic spot is effectively counted and analyzed, so that whether the situation that people stay in the scenic spot is accurately and comprehensively judged, and the reliability and the accuracy of the personnel entering and exiting the scenic spot are improved.
Description
Technical Field
The invention relates to the technical field of scenic spot management, in particular to a scenic spot registration monitoring method based on face recognition.
Background
At present, cameras are installed in entrance and exit areas of scenic spots, people gathered at the entrance and exit areas are shot by the aid of the cameras, and therefore whether ticket evading behaviors exist in monitoring people or not and whether potential safety hazards occur due to overlarge gathering density of the people in the entrance and exit areas or not are monitored conveniently. The cameras installed in the entrance and exit areas of the visible scenic spot only monitor the real-time states of the entrance and exit areas, and the information of people entering and exiting the scenic spot is not effectively counted and analyzed, so that whether the situation that people stay in the scenic spot exists or not can not be accurately and comprehensively judged, and the reliability and accuracy of the entrance and exit management of the scenic spot people are reduced.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a scenic spot registration monitoring method based on face recognition, which comprises the steps of respectively shooting through a camera to obtain images of an entrance area and an exit area of a scenic spot, recognizing the images of the faces and the action states of people in the entrance area and the exit area of the scenic spot from the images of the entrance area and recognizing the images of the faces of the people in the exit area of the scenic spot from the images of the exit area of the scenic spot; judging whether an illegal entry event of the personnel occurs in the entrance area of the scenic spot according to the action state of the personnel, so as to control the working state of the entrance gate of the scenic spot; comparing the face image of the person in the scenic spot entrance area with the face image of the person in the scenic spot exit area, determining the identity information of the person not leaving the scenic spot, and then determining the position information of the person corresponding to the person in the scenic spot so as to upload the position information to the scenic spot management platform; the monitoring method compares the images shot at the entrance and exit of the scenic spot to obtain the difference between the number and the identity of the people who come in and go out of the scenic spot, and effectively counts and analyzes the information of the people who come in and go out of the scenic spot, thereby accurately and comprehensively judging whether the situation that the people stay in the scenic spot exists or not and improving the reliability and the accuracy of the management of the people who come in and go out of the scenic spot.
The invention provides a scenic spot registration monitoring method based on face recognition, which comprises the following steps:
step S1, instructing a first camera device positioned in a scenic spot entrance area to shoot the scenic spot entrance area to obtain an image of the scenic spot entrance area; analyzing and processing the image of the scenic spot entrance area to obtain a face image and a person action state of a person in the scenic spot entrance area;
s2, judging whether the illegal entry event of the personnel occurs in the entrance area of the scenic spot according to the action state of the personnel; controlling the working state of the entrance gate of the scenic spot according to the judgment result;
s3, instructing second camera equipment positioned in the region of the exit of the scenic spot to shoot the region of the exit of the scenic spot to obtain an image of the region of the exit of the scenic spot; analyzing and processing the image of the exit area of the scenic spot to obtain a face image of a person existing in the exit area of the scenic spot;
s4, comparing the face image of the person existing in the scenic region entrance area with the face image of the person existing in the scenic region exit area, and determining the identity information of the person not leaving the scenic region; determining the existence position information of the corresponding personnel in the scenic spot according to the identity information of the personnel not leaving the scenic spot; and uploading the existing position information to a scenic spot management platform.
Further, in step S1, instructing the first image capturing device located in the scenic spot entrance area to capture the scenic spot entrance area, and obtaining an image of the scenic spot entrance area specifically includes:
indicating a first camera device positioned in the scenic spot entrance area to carry out binocular shooting on the scenic spot entrance area to obtain a binocular image of the scenic spot entrance area;
and obtaining a three-dimensional image of the scenic spot entrance area corresponding to the scenic spot entrance area according to the binocular parallax of the binocular image of the scenic spot entrance area.
Further, in the step S1, analyzing the image of the scenic spot entrance area to obtain a face image of the person in the scenic spot entrance area and a person action state specifically includes:
carrying out pixel graying processing and pixel edge sharpening processing on the three-dimensional image of the scenic region inlet area;
and identifying and obtaining a pixel boundary line between the body of the person and the background environment from the three-dimensional image of the entrance area of the scenic region, and extracting and obtaining a three-dimensional face image of the person and the four limbs movement posture of the person from the three-dimensional image of the entrance area of the scenic region according to the pixel boundary line.
Further, in the step S2, whether an illegal entry event of a person occurs in the entrance area of the scenic spot is judged according to the person action state; and according to the above-mentioned judged result, the operating condition of controlling the entrance gate of scenic spot specifically includes:
determining whether the person crosses an entrance gate of the scenic spot at present according to the four-limb action posture of the person; if yes, judging that illegal entry events of personnel occur in the entrance area of the scenic spot; if not, judging that the illegal entry event of the personnel does not occur in the entrance area of the scenic spot;
when the illegal entry event of the personnel in the entrance area of the scenic spot is determined, the entrance gate of the scenic spot is instructed to send out a sound alarm signal and switch to a closed state.
Further, in step S3, instructing a second imaging device located in the area of the exit of the scenic spot to capture the area of the exit of the scenic spot, and obtaining an image of the area of the exit of the scenic spot specifically includes:
indicating second camera equipment positioned in the area of the exit of the scenic spot to carry out binocular shooting on the area of the exit of the scenic spot to obtain binocular images of the area of the exit of the scenic spot;
and obtaining a three-dimensional image of the scenic region exit area corresponding to the scenic region exit area according to the binocular parallax of the binocular images of the scenic region exit area.
Further, in step S3, analyzing the image of the exit area of the scenic spot to obtain a face image of the person in the exit area of the scenic spot specifically includes:
carrying out pixel graying processing and pixel edge sharpening processing on the three-dimensional image of the region of the scenic spot outlet;
and identifying and obtaining a pixel boundary line between the body of the person and the background environment from the three-dimensional image of the region of the scenic spot, and extracting and obtaining a three-dimensional face image of the person from the three-dimensional image of the region of the scenic spot according to the pixel boundary line.
Further, in the step S4, the step of comparing the face image of the person in the scenic area entrance area with the face image of the person in the scenic area exit area, and determining the identity information of the person who does not leave the scenic area specifically includes:
carrying out face feature comparison processing on the three-dimensional face image of the person corresponding to the three-dimensional image of the scenic region inlet area and the three-dimensional face image of the person corresponding to the three-dimensional image of the scenic region outlet area, and screening to obtain the three-dimensional face image of the person corresponding to the person not leaving the scenic region;
and then according to the facial features of the three-dimensional face image of the person obtained by screening, using the facial features as the identity information of the person who does not leave the scenic spot.
Further, in the step S4, the information of the position of the person in the scenic spot is determined according to the identity information of the person who does not leave the scenic spot; uploading the existing position information to a scenic spot management platform specifically comprises:
calling an image of an internal area of the scenic spot, and determining that the image of the internal area of the scenic spot contains an image picture of a person who does not leave the scenic spot according to facial feature information of the person who does not leave the scenic spot;
extracting background environment picture content existing in the image picture from the image picture, and determining the existing position information in the corresponding scenic spot according to the background environment picture content; and uploading the existing position information to a scenic spot management platform, and sending a notification message to the terminal equipment of the staff near the existing position in the corresponding staff scenic spot through the scenic spot management platform.
Further, in the step S4, sending a notification message to a terminal device of a staff near an existing position in the corresponding staff scenic spot through the scenic spot management platform specifically includes:
terminal devices of a plurality of workers are respectively distributed at each scene point of a scene area, and the number of the workers nearby each scene point worker and the distance between each scene point worker and the workers nearby are obtained according to the position information of the workers in the scene area received by the scene area management platform; obtaining the stay duration of the personnel near each sight spot worker in the corresponding sight spot according to the historical change condition of the position of the personnel near each sight spot worker; determining the number of the scenery spot workers additionally assigned to each scenery spot according to the stay duration of the personnel nearby each scenery spot worker in the corresponding scenery spot and the number of the personnel nearby each scenery spot worker; and finally, determining the maximum distance between two adjacent workers in the corresponding scenic spot after the scenic spot workers are assigned according to the number of the scenic spot workers of each scenic spot and the distance between each scenic spot worker and the nearby personnel, wherein the process is as follows:
step S401, obtaining the stay duration of the persons near each sight spot at the corresponding sight spot according to the historical change condition of the positions of the persons near each sight spot by using the following formula (1),
in equation (1) above, T (a, i) represents the stay duration of the ith individual member at the a-th attraction present near the a-th attraction worker; s t (a, i) represents the distance value between the ith person and the a-th attraction person existing near the a-th attraction person at the time t; s 0 Indicating a preset distance value determined to be near the sight crew, i.e., a distance from the sight crew less than or equal to S 0 The person of (a) is identified as belonging to a person present near the sight spot staff; t is t n Represents the current time; f represents the frequency of locating the position of the person; k represents an integer variable whose value increases from 0;means that the value of k is increased from 0 and substituted into the parenthesis until the condition in parenthesis is not satisfied, and the value of k at this time is obtained;
step S402, determining the number of the scenery spot workers assigned to each scenery spot according to the stay duration of the personnel nearby each scenery spot worker at the corresponding scenery spot and the number of the personnel nearby each scenery spot worker by using the following formula (2),
in the above formula (2), M a The number of the scenic spot workers needing to be correspondingly assigned to the a-th scenic spot in the scenic spot is represented; m is a unit of a Indicating the number of people present near the a-th attraction worker; t is 0 Representing a preset stay duration threshold corresponding to the augmented staff; int-denotes rounding the value in parentheses;
step S403, determining the maximum distance between two adjacent workers in the corresponding scenic spot after adding the scenic spot workers according to the number of the scenic spot workers added to each scenic spot and the distance between each scenic spot worker and the nearby workers by using the following formula (3),
in the formula (3), L (a) represents the maximum distance between two adjacent workers corresponding to the a-th scenic spot after the scenic spot workers are assigned, that is, each scenic spot worker of the a-th scenic spot in the scenic area needs to have another scenic spot worker within the distance range of L (a);the distance value between the ith person and the ith sight spot worker existing near the ith sight spot worker at the current moment is represented; />Means taking the value of i from 1 to m a To obtain the maximum value in parentheses; />Means taking the value of i from 1 to m a The minimum value in parentheses is obtained.
Compared with the prior art, the scenic spot registration monitoring method based on the face recognition obtains the images of the entrance area and the exit area of the scenic spot by shooting through the camera equipment respectively, obtains the face images and the action states of the people in the entrance area of the scenic spot by recognizing from the images of the entrance area of the scenic spot, and obtains the face images of the people in the exit area of the scenic spot by recognizing from the images of the exit area of the scenic spot; judging whether an illegal entry event of the personnel occurs in the entrance area of the scenic spot according to the action state of the personnel, so as to control the working state of the entrance gate of the scenic spot; comparing the face image of the person in the scenic spot entrance area with the face image of the person in the scenic spot exit area, determining the identity information of the person not leaving the scenic spot, and then determining the position information of the person corresponding to the person in the scenic spot so as to upload the position information to the scenic spot management platform; the monitoring method compares the images shot at the entrance and exit of the scenic spot to obtain the difference between the number and the identity of the people who come in and go out of the scenic spot, and effectively counts and analyzes the information of the people who come in and go out of the scenic spot, thereby accurately and comprehensively judging whether the situation that the people stay in the scenic spot exists or not and improving the reliability and the accuracy of the management of the people who come in and go out of the scenic spot.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a scenic spot registration monitoring method based on face recognition provided by the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a scenic spot registration monitoring method based on face recognition according to an embodiment of the present invention. The scenic spot registration monitoring method based on face recognition comprises the following steps:
step S1, instructing a first camera device positioned in a scenic spot entrance area to shoot the scenic spot entrance area to obtain an image of the scenic spot entrance area; analyzing and processing the image of the scenic spot entrance area to obtain a face image and a person action state of a person in the scenic spot entrance area;
s2, judging whether the illegal entry event of the personnel occurs in the entrance area of the scenic spot according to the action state of the personnel; controlling the working state of the scenic spot entrance gate according to the judgment result;
s3, instructing second camera equipment positioned in the region of the exit of the scenic spot to shoot the region of the exit of the scenic spot to obtain an image of the region of the exit of the scenic spot; analyzing and processing the image of the exit area of the scenic spot to obtain a face image of a person in the exit area of the scenic spot;
s4, comparing the face image of the person in the scenic region entrance area with the face image of the person in the scenic region exit area to determine the identity information of the person not leaving the scenic region; determining the existence position information of the corresponding personnel in the scenic spot according to the identity information of the personnel who do not leave the scenic spot; and upload the presence information to the scenic spot management platform.
The beneficial effects of the above technical scheme are: the scenic spot registration monitoring method based on the face recognition obtains images of an entrance area and an exit area of a scenic spot by shooting through camera equipment respectively, obtains face images and personnel action states of personnel in the entrance area of the scenic spot by recognition from the images of the entrance area of the scenic spot, and obtains face images of the personnel in the exit area of the scenic spot by recognition from the images of the exit area of the scenic spot; judging whether an illegal entry event of the personnel occurs in the entrance area of the scenic spot according to the action state of the personnel, so as to control the working state of the entrance gate of the scenic spot; comparing the face image of the person in the scenic spot entrance area with the face image of the person in the scenic spot exit area, determining the identity information of the person not leaving the scenic spot, and then determining the position information of the person corresponding to the person in the scenic spot so as to upload the position information to the scenic spot management platform; the monitoring method compares the images shot at the entrance and exit of the scenic spot to obtain the difference between the number and the identity of the people who come in and go out of the scenic spot, and effectively counts and analyzes the information of the people who come in and go out of the scenic spot, thereby accurately and comprehensively judging whether the situation that the people stay in the scenic spot exists or not and improving the reliability and the accuracy of the management of the people who come in and go out of the scenic spot.
Preferably, in step S1, instructing the first image capturing device located at the scenic spot entrance area to capture the scenic spot entrance area, and obtaining an image of the scenic spot entrance area specifically includes:
indicating a first camera device positioned in the scenic spot entrance area to carry out binocular shooting on the scenic spot entrance area to obtain a binocular image of the scenic spot entrance area;
and obtaining a three-dimensional image of the scenic region inlet area corresponding to the scenic region inlet area according to the binocular parallax of the binocular image of the scenic region inlet area.
The beneficial effects of the above technical scheme are: through at scenic spot entrance area (for example scenic spot entry gate) installation binocular camera equipment, when the personnel entered into scenic spot entrance area, binocular camera equipment can carry out the binocular shooting to scenic spot entrance area, obtains scenic spot entrance area binocular image, carries out binocular parallax calculation to scenic spot entrance binocular image again and handles, obtains corresponding three-dimensional image in scenic spot entrance area to be convenient for carry out three-dimensional image monitoring to scenic spot entrance area personnel's state.
Preferably, in the step S1, the analyzing the image of the entrance area of the scenic spot to obtain the face image of the person in the entrance area of the scenic spot and the action state of the person includes:
carrying out pixel graying processing and pixel edge sharpening processing on the three-dimensional image of the scenic region inlet area;
and identifying and obtaining a pixel boundary line between the body of the person and the background environment from the three-dimensional image of the scenic spot entrance area, and extracting and obtaining a three-dimensional face image of the person and four limbs movement postures of the person from the three-dimensional image of the scenic spot entrance area according to the pixel boundary line.
The beneficial effects of the above technical scheme are: through the mode, the whole body area of the person in the scenic spot entrance area can be extracted from the three-dimensional image of the scenic spot entrance area, and then the three-dimensional face image of the person and the movement posture of the four limbs of the person are obtained according to the whole body area of the person, so that the accuracy of identifying the face and the four limbs of the person is improved.
Preferably, in the step S2, whether an illegal entry event of a person occurs in the entrance area of the scenic spot is determined according to the person action state; and according to the above-mentioned judged result, the operating condition of controlling the entrance gate of scenic spot specifically includes:
determining whether the person crosses an entrance gate of the scenic spot at present according to the four-limb action posture of the person; if yes, judging that illegal entry events of personnel occur in the entrance area of the scenic spot; if not, judging that the illegal entry event of the personnel does not occur in the entrance area of the scenic spot;
when the illegal entry event of the personnel in the entrance area of the scenic spot is determined, the entrance gate of the scenic spot is instructed to send out a sound alarm signal and switch to a closed state.
The beneficial effects of the above technical scheme are: according to this personnel four limbs action posture, confirm whether current four limbs action of personnel belongs to the action of climbing scenic spot entry gate more to whether accurate judgement personnel are at present to climb scenic spot entry gate, then confirm that the illegal entering incident of personnel takes place in scenic spot entry area, can in time instruct scenic spot entry gate like this to send audible alarm signal and switch to the closed condition, effectively stop the emergence of behavior of fleing a bill.
Preferably, in step S3, instructing the second imaging apparatus located in the scenic region exit area to capture the scenic region exit area, and obtaining the image of the scenic region exit area specifically includes:
indicating second camera equipment positioned in the area of the exit of the scenic spot to carry out binocular shooting on the area of the exit of the scenic spot to obtain binocular images of the area of the exit of the scenic spot;
and obtaining a three-dimensional image of the scenic area exit area corresponding to the scenic area exit area according to the binocular parallax of the binocular images of the scenic area exit area.
The beneficial effects of the above technical scheme are: through at scenic spot exit region (for example scenic spot export gate) installation binocular camera equipment, when personnel entered into the scenic spot exit region, binocular camera equipment can carry out the binocular shooting to the scenic spot exit region, obtains scenic spot entry region binocular image, carries out binocular parallax computation processing to scenic spot export binocular image again, obtains corresponding scenic spot exit region three-dimensional image to be convenient for carry out three-dimensional image monitoring to scenic spot exit region personnel state.
Preferably, in step S3, the analyzing the image of the exit area of the scenic spot to obtain the face image of the person in the exit area of the scenic spot specifically includes:
carrying out pixel graying processing and pixel edge sharpening processing on the three-dimensional image of the region of the scenic spot outlet;
and identifying and obtaining a pixel boundary line between the human body and the background environment from the three-dimensional image of the region of the scenic spot, and extracting and obtaining a three-dimensional face image of the human from the three-dimensional image of the region of the scenic spot according to the pixel boundary line.
The beneficial effects of the above technical scheme are: through the mode, the whole body area of the person positioned in the exit area of the scenic region can be extracted from the three-dimensional image of the exit area of the scenic region, and then the three-dimensional face image of the person is obtained according to the whole body area of the person, so that the accuracy of identifying the face of the person is improved.
Preferably, in the step S4, the comparing the face image of the person in the scenic area entrance area with the face image of the person in the scenic area exit area, and the determining of the identity information of the person not leaving the scenic area specifically includes:
carrying out face feature comparison processing on the three-dimensional face image of the person corresponding to the three-dimensional image of the scenic region inlet area and the three-dimensional face image of the person corresponding to the three-dimensional image of the scenic region outlet area, and screening to obtain the three-dimensional face image of the person corresponding to the person not leaving the scenic region;
and then according to the facial features of the three-dimensional face image of the person obtained by screening, using the facial features as the identity information of the person who does not leave the scenic spot.
The beneficial effects of the above technical scheme are: through the steps, the person three-dimensional face image sets respectively corresponding to the scenic spot inlet area and the scenic spot outlet area can be obtained, and then the face five-sense feature comparison processing is carried out on the two person three-dimensional face image sets, so that the person identity information of the person three-dimensional face image set which is present in the scenic spot inlet area and is absent in the scenic spot outlet area is used as the person identity information which does not leave the scenic spot, and therefore the person identity information which does not leave the scenic spot is comprehensively and accurately determined.
Preferably, in the step S4, the information of the presence position of the corresponding person in the scenic spot is determined according to the identity information of the person who does not leave the scenic spot; uploading the presence location information to the scenic spot management platform specifically comprises:
calling an image of an internal area of the scenic spot, and determining that the image of the internal area of the scenic spot contains an image picture of a person who does not leave the scenic spot according to facial feature information of the person who does not leave the scenic spot;
extracting the background environment picture content existing in the image picture, and determining the existing position information in the corresponding scenic spot according to the background environment picture content; and uploading the existing position information to a scenic spot management platform, and sending a notification message to the terminal equipment of the staff near the existing position in the corresponding staff scenic spot through the scenic spot management platform.
The beneficial effects of the above technical scheme are: in actual operation, a plurality of cameras are arranged in the internal areas of the scenic region to shoot different internal areas of the scenic region, and the images of the internal areas of the scenic region are called, and the images containing the persons who do not leave the scenic region are picked out from the images of the internal areas of the scenic region according to the facial feature information of the persons who do not leave the scenic region. And extracting the background environment picture content existing in the image picture, and determining the existing position information in the corresponding scenic spot by taking the background environment picture content as a reference. And finally, the scenic spot management platform sends a notification message to terminal equipment of workers near the position in the corresponding personnel scenic spot, so that the workers can go to the corresponding position area in time to remind the personnel who do not leave the scenic spot to leave the scenic spot in time.
Preferably, in step S4, the sending, by the scenic spot management platform, the notification message to the terminal device of the staff near the existing position inside the corresponding staff scenic spot specifically includes:
terminal devices of a plurality of workers are respectively distributed at each scene point of the scene area, and the number of the workers nearby each scene point worker and the distance between each scene point worker and the workers nearby are obtained according to the position information of the workers in the scene area received by the scene area management platform; obtaining the stay duration of the personnel nearby each sight spot worker in the corresponding sight spot according to the historical change condition of the position of the personnel nearby each sight spot worker; determining the number of the scenery spot workers additionally assigned to each scenery spot according to the stay duration of the personnel nearby each scenery spot worker in the corresponding scenery spot and the number of the personnel nearby each scenery spot worker; and finally, determining the maximum distance between two adjacent workers in the corresponding scenic spot behind the increase-dispatch scenic spot worker according to the number of the increase-dispatch scenic spot workers of each scenic spot and the distance between each scenic spot worker and the nearby personnel, wherein the process is as follows:
step S401, obtaining the stay duration of the persons near each sight spot at the corresponding sight spot according to the historical change condition of the positions of the persons near each sight spot by using the following formula (1),
in equation (1) above, T (a, i) represents the stay duration at the a-th attraction for the i-th individual present near the a-th attraction worker; s t (a, i) represents the distance value between the ith person and the a-th attraction person existing near the a-th attraction person at the time t; s 0 Indicating that the work is deemed to be scenicA preset distance value near the staff, namely the distance between the staff and the scenic spot is less than or equal to S 0 The person of (a) is identified as belonging to a person present near the sight spot staff; t is t n Represents the current time; f represents the frequency of locating the position of the person; k represents an integer variable whose value increases from 0;means that the value of k is increased from 0 and substituted into the parenthesis until the condition in parenthesis is not satisfied, and the value of k at this time is obtained;
step S402, determining the number of the scenery spot workers assigned to each scenery spot according to the stay duration of the personnel nearby each scenery spot worker at the corresponding scenery spot and the number of the personnel nearby each scenery spot worker by using the following formula (2),
in the above formula (2), M a Expressing the number of sight spot workers needing to be correspondingly assigned to the a-th sight spot in the sight area; m is a Representing the number of people present near the a-th attraction worker; t is 0 Representing a preset stay duration threshold corresponding to the augmented staff; int-denotes rounding the value in parentheses;
step S403, determining the maximum distance between two adjacent workers in the corresponding scenic spot after adding the scenic spot workers according to the number of the scenic spot workers added to each scenic spot and the distance between each scenic spot worker and the nearby workers by using the following formula (3),
in the above formula (3), L (a) represents the maximum distance between two adjacent workers corresponding to the a-th scenic spot after assigning the scenic spot workers, i.e. each of the a-th scenic spots in the scenic spotOne scenic spot worker needs to have another scenic spot worker in the distance range L (a);the distance value between the ith person and the ith sight spot worker existing near the ith sight spot worker at the current moment is represented; />Means taking the value of i from 1 to m a Obtaining the maximum value in brackets; />Means taking the value of i from 1 to m a The minimum value in parentheses is obtained.
The beneficial effects of the above technical scheme are: obtaining the stay duration of the personnel near each sight spot worker at the sight spot corresponding to the sight spot worker according to the historical change condition of the position of the personnel near each sight spot worker by using the formula (1), so that the stay condition of each personnel at each sight spot can be known, and the assignment of the sight spot workers can be controlled according to the stay condition; then, the number of the scenery spot workers assigned to each scenery spot is controlled by using the formula (2) according to the stay duration of the personnel nearby each scenery spot worker at the scenery spot corresponding to the scenery spot worker and the number of the personnel nearby each scenery spot worker, so that enough scenery spot workers can control the current scenery spot; and finally, controlling the maximum distance between two adjacent scenery spot workers of the scenery spot after the dispatch is controlled according to the number of the scenery spot workers of the dispatch of each scenery spot and the distance between the personnel near each scenery spot worker and each scenery spot worker, so that more workers can be timely managed and controlled around the scene when illegal workers appear.
As can be seen from the content of the above embodiment, the scenic spot registration monitoring method based on face recognition obtains the images of the entrance area and the exit area of the scenic spot by shooting with the camera device, respectively, obtains the face image and the person action state of the person in the entrance area of the scenic spot by recognition from the images of the entrance area of the scenic spot, and obtains the face image of the person in the exit area of the scenic spot by recognition from the images of the exit area of the scenic spot; judging whether an illegal entry event of the personnel occurs in the entrance area of the scenic spot according to the action state of the personnel, so as to control the working state of the entrance gate of the scenic spot; comparing the face image of the person in the scenic spot entrance area with the face image of the person in the scenic spot exit area, determining the identity information of the person not leaving the scenic spot, and then determining the position information of the person corresponding to the person in the scenic spot so as to upload the position information to the scenic spot management platform; the monitoring method compares the images shot at the entrance and exit of the scenic spot to obtain the difference between the number and the identity of the people who come in and go out of the scenic spot, and effectively counts and analyzes the information of the people who come in and go out of the scenic spot, thereby accurately and comprehensively judging whether the situation that the people stay in the scenic spot exists or not and improving the reliability and the accuracy of the management of the people who come in and go out of the scenic spot.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (3)
1. A scenic spot registration monitoring method based on face recognition is characterized by comprising the following steps:
step S1, instructing a first camera device positioned in a scenic spot entrance area to shoot the scenic spot entrance area to obtain an image of the scenic spot entrance area; analyzing and processing the image of the scenic spot entrance area to obtain a face image and a person action state of a person in the scenic spot entrance area;
s2, judging whether the illegal entry event of the personnel occurs in the entrance area of the scenic spot according to the action state of the personnel; and controlling the working state of the scenic spot entrance gate according to the judgment result;
s3, instructing second camera equipment positioned in the region of the exit of the scenic spot to shoot the region of the exit of the scenic spot to obtain an image of the region of the exit of the scenic spot; analyzing and processing the image of the exit area of the scenic spot to obtain a face image of a person existing in the exit area of the scenic spot;
s4, comparing the face image of the person existing in the scenic region entrance area with the face image of the person existing in the scenic region exit area, and determining the identity information of the person not leaving the scenic region; determining the existence position information of the corresponding personnel in the scenic spot according to the identity information of the personnel not leaving the scenic spot; uploading the existing position information to a scenic spot management platform;
in step S1, instructing the first imaging device located in the scenic spot entrance area to capture the scenic spot entrance area, and obtaining an image of the scenic spot entrance area specifically includes:
indicating a first camera device positioned in the scenic spot entrance area to carry out binocular shooting on the scenic spot entrance area to obtain a binocular image of the scenic spot entrance area;
obtaining a three-dimensional image of the scenic region inlet area corresponding to the scenic region inlet area according to the binocular parallax of the binocular images of the scenic region inlet area;
in step S3, instructing a second imaging device located in the scenic spot exit area to capture the scenic spot exit area, and obtaining an image of the scenic spot exit area specifically includes:
indicating second camera equipment positioned in the area of the exit of the scenic spot to carry out binocular shooting on the area of the exit of the scenic spot to obtain binocular images of the area of the exit of the scenic spot;
obtaining a three-dimensional image of the scenic region exit area corresponding to the scenic region exit area according to the binocular parallax of the binocular images of the scenic region exit area;
in step S3, analyzing the image of the scenic spot exit area to obtain a face image of a person in the scenic spot exit area specifically includes:
carrying out pixel graying processing and pixel edge sharpening processing on the three-dimensional image of the region of the scenic spot outlet;
identifying and obtaining a pixel boundary line between a person body and a background environment from the three-dimensional image of the scenic spot outlet area, and extracting and obtaining a three-dimensional face image of the person from the three-dimensional image of the scenic spot outlet area according to the pixel boundary line;
in step S4, the comparing the face image of the person existing in the scenic spot entrance area with the face image of the person existing in the scenic spot exit area, and determining the identity information of the person who does not leave the scenic spot specifically includes:
carrying out face feature comparison processing on the three-dimensional face image of the person corresponding to the three-dimensional image of the scenic region inlet area and the three-dimensional face image of the person corresponding to the three-dimensional image of the scenic region outlet area, and screening to obtain the three-dimensional face image of the person corresponding to the person not leaving the scenic region;
then according to the facial features of the three-dimensional face image of the person obtained by screening, the facial features are used as the identity information of the person who does not leave the scenic spot;
in the step S4, the information of the positions of the persons in the scenic spot is determined according to the identity information of the persons who do not leave the scenic spot; uploading the existing position information to a scenic spot management platform specifically comprises:
calling an image of an internal area of the scenic spot, and determining that the image of the internal area of the scenic spot contains an image picture of a person who does not leave the scenic spot according to facial feature information of the person who does not leave the scenic spot;
extracting background environment picture content existing in the image picture from the image picture, and determining the existing position information in the corresponding scenic spot according to the background environment picture content; uploading the existing position information to a scenic spot management platform, and sending a notification message to terminal equipment of a worker near the existing position in the corresponding person scenic spot through the scenic spot management platform;
in step S4, sending a notification message to a terminal device of a staff near an existing position in the corresponding staff scenic region through the scenic region management platform specifically includes:
terminal devices of a plurality of workers are respectively distributed at each scene point of a scene, and the number of the workers nearby each scene point worker and the distance between each scene point worker and the workers nearby are obtained according to the information of the positions of the workers in the scene, which is received by the scene management platform; obtaining the stay duration of the personnel nearby each sight spot worker in the corresponding sight spot according to the historical change condition of the position of the personnel nearby each sight spot worker; determining the number of the scenic spot workers additionally assigned to each scenic spot according to the stay duration of the personnel nearby each scenic spot worker in the corresponding scenic spot and the number of the personnel nearby each scenic spot worker; and finally, determining the maximum distance between two adjacent workers in the corresponding scenic spot behind the increase-dispatch scenic spot worker according to the number of the increase-dispatch scenic spot workers of each scenic spot and the distance between each scenic spot worker and the nearby personnel, wherein the process is as follows:
step S401, obtaining the stay duration of the personnel near the staff of each scenic spot in the corresponding scenic spot according to the historical change condition of the position of the personnel near the staff of each scenic spot by using the following formula (1),
in the above-mentioned formula (1),is shown asThe first place existing near the staff of the individual scenic spotThe individual is at the firstThe stay duration of the individual attraction;to representAt the first momentThe first place existing near the staff of the individual scenic spotIndividual and the firstDistance values of individual sight spot workers;indicating a preset distance value determined to be near the sight crew, i.e., a distance from the sight crew less than or equal toThe person of (a) is identified as belonging to a person present near the sight spot staff;represents the current time;a frequency indicative of a location of a located person;represents an integer variable whose value increases from 0;show thatThe value of (b) is increased from 0 and substituted into the parenthesis until the condition in parenthesis is not satisfied, and the value of K at this time is obtained;
step S402, determining the number of the scenery spot workers assigned to each scenery spot according to the stay duration of the personnel nearby each scenery spot worker at the corresponding scenery spot and the number of the personnel nearby each scenery spot worker by using the following formula (2),
in the above-mentioned formula (2),indicating the second in the desired sceneThe number of the scenic spot workers of each scenic spot is correspondingly increased;is shown asThe number of persons present near the staff of each attraction;representing a preset stay duration threshold corresponding to the augmented staff;means to round the values in parentheses;
step S403, determining the maximum distance between two adjacent workers in the corresponding scenic spot after adding the scenic spot workers according to the number of the scenic spot workers added to each scenic spot and the distance between each scenic spot worker and the nearby workers by using the following formula (3),
in the above-mentioned formula (3),the number of the staff who add the scenic spot is expressedMaximum distance between two adjacent workers of an individual scenic spot, i.e. the first in the scenic spotEach sight spot staff of each sight spot isAnother scenic spot worker needs to exist within the distance range;indicates the current timeThe first place existing near the staff of the individual scenic spotIndividual and person ofDistance values between the personnel of the individual scenic spots;show thatFrom 1 toTo obtain the maximum value in parentheses;show thatFrom 1 toThe minimum value in parentheses is obtained.
2. The scenic spot registration monitoring method based on face recognition as set forth in claim 1, characterized in that:
in the step S1, analyzing the image of the scenic spot entrance area to obtain a face image of the person in the scenic spot entrance area and a person action state specifically includes:
carrying out pixel graying processing and pixel edge sharpening processing on the three-dimensional image of the scenic region inlet area;
and identifying and obtaining a pixel boundary line between the body of the person and the background environment from the three-dimensional image of the entrance area of the scenic region, and extracting and obtaining a three-dimensional face image of the person and the four limbs movement posture of the person from the three-dimensional image of the entrance area of the scenic region according to the pixel boundary line.
3. The scenic spot registration monitoring method based on face recognition as set forth in claim 2, characterized in that:
in the step S2, judging whether an illegal entry event of the personnel occurs in the entrance area of the scenic spot according to the action state of the personnel; and according to the above-mentioned judged result, the operating condition of controlling the entrance gate of scenic spot specifically includes:
determining whether the person crosses an entrance gate of the scenic spot at present according to the four-limb action posture of the person; if yes, judging that illegal entry events of personnel occur in the entrance area of the scenic spot; if not, judging that the illegal entry event of the personnel does not occur in the entrance area of the scenic spot;
when the illegal entry event of the person in the entrance area of the scenic spot is determined, the entrance gate of the scenic spot is instructed to send out a sound alarm signal and switch to a closed state.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210636975.8A CN114937303B (en) | 2022-06-07 | 2022-06-07 | Scenic spot registration monitoring method based on face recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210636975.8A CN114937303B (en) | 2022-06-07 | 2022-06-07 | Scenic spot registration monitoring method based on face recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114937303A CN114937303A (en) | 2022-08-23 |
CN114937303B true CN114937303B (en) | 2023-03-24 |
Family
ID=82867006
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210636975.8A Active CN114937303B (en) | 2022-06-07 | 2022-06-07 | Scenic spot registration monitoring method based on face recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114937303B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110110669A (en) * | 2019-05-08 | 2019-08-09 | 广东赛翼智能科技有限公司 | A kind of wisdom scenic spot tourist's localization method and system based on face recognition technology |
CN112614160A (en) * | 2020-12-24 | 2021-04-06 | 中标慧安信息技术股份有限公司 | Multi-object face tracking method and system |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5349080B2 (en) * | 2009-02-27 | 2013-11-20 | 株式会社東芝 | Admission management system, admission management device, and admission management method |
CN107992786A (en) * | 2016-10-27 | 2018-05-04 | 中国科学院沈阳自动化研究所 | A kind of people streams in public places amount statistical method and system based on face |
CN109544728B (en) * | 2017-09-21 | 2021-08-27 | 鸿富锦精密电子(天津)有限公司 | Regional population management and control system and method |
CN110428522B (en) * | 2019-07-24 | 2021-04-30 | 青岛联合创智科技有限公司 | Intelligent security system of wisdom new town |
CN114550357A (en) * | 2020-11-26 | 2022-05-27 | 比亚迪股份有限公司 | Scenic spot tourist management method, medium and terminal |
CN112907785A (en) * | 2021-01-15 | 2021-06-04 | 广东趣买票科技有限公司 | Scenic spot number control system and control device based on Internet of things |
-
2022
- 2022-06-07 CN CN202210636975.8A patent/CN114937303B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110110669A (en) * | 2019-05-08 | 2019-08-09 | 广东赛翼智能科技有限公司 | A kind of wisdom scenic spot tourist's localization method and system based on face recognition technology |
CN112614160A (en) * | 2020-12-24 | 2021-04-06 | 中标慧安信息技术股份有限公司 | Multi-object face tracking method and system |
Also Published As
Publication number | Publication date |
---|---|
CN114937303A (en) | 2022-08-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106412501B (en) | A kind of the construction safety behavior intelligent monitor system and its monitoring method of video | |
CN110852148B (en) | Visitor destination verification method and system based on target tracking | |
CN112737121A (en) | Intelligent video monitoring, analyzing, controlling and managing system for power grid | |
KR101036947B1 (en) | The automatic guard system to prevent the crime and accident using computer video image analysis technology | |
CN106296045A (en) | A kind of electrical network foreign body laser removes equipment safety management control device and method | |
CN109492548B (en) | Method for obtaining region mask picture based on video analysis | |
CN115376269B (en) | Fire monitoring system based on unmanned aerial vehicle | |
CN115512304B (en) | Subway station safety monitoring system based on image recognition | |
CN110956769B (en) | Monitoring method of perimeter anti-intrusion system based on target position | |
CN113066248A (en) | Intelligent community construction security monitoring intelligent management system based on video image processing | |
CN114648855B (en) | Intelligent community security comprehensive management system and control method thereof | |
CN114937237A (en) | Construction site safety monitoring method and system based on AI intelligent identification | |
CN110809137A (en) | Campus safety trampling prevention monitoring system and method | |
CN111795716A (en) | Pipe gallery maintenance validity judgment method based on city perception microgrid | |
CN115797856A (en) | Intelligent construction scene safety monitoring method based on machine vision | |
CN114937303B (en) | Scenic spot registration monitoring method based on face recognition | |
CN113044694B (en) | System and method for counting number of persons in building elevator based on deep neural network | |
CN108090452A (en) | Personnel statistical method and device | |
CN115223105B (en) | Big data based risk information monitoring and analyzing method and system | |
CN115457331A (en) | Intelligent inspection method and system for construction site | |
CN114387665A (en) | Unmanned staircase identification system ascends a height based on portable cloth accuse ball | |
CN113496564A (en) | Park artificial intelligence management and control system | |
CN114639216A (en) | Specific personnel track area analysis early warning system and method | |
CN110287929B (en) | Method, device, equipment and storage medium for determining number of targets in group area | |
CN113158744A (en) | Security protection management system based on face recognition |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |