CN117682400A - Identification method for whether person exists in elevator, elevator management unit and system - Google Patents

Identification method for whether person exists in elevator, elevator management unit and system Download PDF

Info

Publication number
CN117682400A
CN117682400A CN202311697119.4A CN202311697119A CN117682400A CN 117682400 A CN117682400 A CN 117682400A CN 202311697119 A CN202311697119 A CN 202311697119A CN 117682400 A CN117682400 A CN 117682400A
Authority
CN
China
Prior art keywords
elevator
image
person
identification
server
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311697119.4A
Other languages
Chinese (zh)
Inventor
王小青
何奎
单智辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Lubangtong Intelligent Technology Co ltd
Original Assignee
Guangzhou Lubangtong Intelligent Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Lubangtong Intelligent Technology Co ltd filed Critical Guangzhou Lubangtong Intelligent Technology Co ltd
Priority to CN202311697119.4A priority Critical patent/CN117682400A/en
Publication of CN117682400A publication Critical patent/CN117682400A/en
Pending legal-status Critical Current

Links

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
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
    • B66B5/0006—Monitoring devices or performance analysers
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
    • B66B5/0006—Monitoring devices or performance analysers
    • B66B5/0012—Devices monitoring the users of the elevator system
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/94—Hardware or software architectures specially adapted for image or video understanding
    • G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Human Computer Interaction (AREA)
  • Indicating And Signalling Devices For Elevators (AREA)

Abstract

The invention belongs to the field of computers, and discloses a method for identifying whether a person exists in an elevator, which comprises the following steps: step 1: acquiring an image in the elevator and sending the image to a server; step 2: receiving an identification result sent by a server, if the identification result is unmanned, performing step 1 or terminating the process, and if the identification result is unmanned, performing step 3; step 3: and (3) judging whether the coordinates of the person in the image enter a preset identification area, if so, alarming, and if not, performing the step (1) or stopping the process. The method comprises the steps of firstly identifying the person through the server, and judging whether the coordinates of the person are in an identification area or not after identifying the person, so as to judge whether the person is in the elevator or not, wherein the calculated amount is low, and the false alarm rate is low. Meanwhile, the invention also discloses an elevator management unit and an elevator management system.

Description

Identification method for whether person exists in elevator, elevator management unit and system
Technical Field
The invention relates to the field of computers, in particular to a method for identifying whether a person exists in an elevator, an elevator management unit and a system.
Background
At present, various manufacturer AI cameras pass through ladder trapping algorithms (three dimensions of people, time and area are combined), the people in the poster and living body cannot be distinguished by the current AI camera manufacturer algorithms, and the AI identification people have different algorithms, so that problems can occur in the identification people, the false alarm of ladder trapping faults can be finally caused, and the waste of manpower and material resources is caused.
CN110790101a discloses a method for identifying false alarm of trapped elevator based on big data analysis, which comprises the following steps: (A1) Collecting the condition of people in an elevator car as a training sample; (A2) Classifying training samples according to real people trapping, cleaning and advertisement board changing, and adding marks; (A3) performing an identification analysis using a network; (A4) validating the analyzed network.
The above method is a common method in the art for identifying posters and living persons.
Particularly, the electronic advertisement screen in the existing elevator is widely applied, people pictures appear in some scenes, and no people pictures appear in some scenes, so that the difficulty of the existing AI identification is higher and higher.
Therefore, the technical problem solved by the scheme is as follows: how to reduce the analysis difficulty of living people in the elevator and the false alarm rate.
Disclosure of Invention
The invention aims to provide a method for identifying whether a person exists in an elevator, which comprises the steps of firstly identifying the person through a server, judging whether coordinates of the person are in an identification area after identifying the person, and further judging whether the person exists in the elevator or does not exist in the elevator, wherein the method is low in calculated amount and low in false alarm rate.
Meanwhile, the invention also discloses an elevator management unit and an elevator management system.
In order to achieve the above purpose, the present invention provides the following technical solutions: a method of identifying whether a person is in an elevator, comprising the steps of:
step 1: acquiring an image in the elevator and sending the image to a server; the server is used for identifying the image and obtaining an identification result, wherein the identification result is that people exist or no people exist; if the person exists in the image, the identification result also comprises the coordinates of the person in the image;
step 2: receiving an identification result sent by a server, if the identification result is unmanned, performing step 1 or terminating the process, and if the identification result is unmanned, performing step 3;
step 3: judging whether the coordinates of the person in the image enter a preset identification area, if so, alarming, otherwise, performing the step 1 or stopping the process; the identification area is an area defined in advance in a global image acquired from a camera of each elevator.
In the above method for identifying whether a person exists in the elevator, if the person exists in the image, the identification result also includes a confidence level;
in step 2, if the identification result is that a person exists and the confidence in the identification result is lower than a preset threshold, step 1 is performed.
In the above method for identifying whether a person exists in an elevator, the specific method for determining whether the coordinates of the person in the image enter a preset identification area in step 3 includes: judging whether all the coordinates of the person in the image are in the area outside the identification area, if so, the coordinates of the person in the image do not enter the preset identification area, and if not, the coordinates of the person in the image enter the preset identification area.
In the above method for identifying whether a person is in the elevator, the step 1 further includes:
step 10: and judging whether the elevator is in a fault alarm state, if so, performing the step 1.
Meanwhile, the invention also discloses an elevator management unit, which comprises the following modules:
an image acquisition module: the method comprises the steps of acquiring an image in an elevator through a camera arranged in the elevator;
and a communication module: the image acquisition module is used for acquiring images of the user, and sending the images to the server; the server is used for identifying the image and obtaining an identification result, wherein the identification result is that people exist or no people exist; if the person exists in the image, the identification result also comprises the coordinates of the person in the image;
and an identification module: the method comprises the steps of judging whether coordinates of a person in an image enter a preset identification area according to an identification result, alarming if yes, and not alarming if no; the identification area is an area defined in advance in a global image acquired from a camera of each elevator.
In the elevator management unit, the identification result further comprises confidence of judgment of the server on the person;
the identification module is also used for identifying that the result is people and not alarming when the confidence level in the identification result is lower than a preset threshold value.
In the above elevator management unit, further comprising:
elevator status acquisition module: and the image acquisition module is used for judging whether the elevator is in a fault alarm state, and if so, controlling the image acquisition module to acquire an image.
Meanwhile, the invention also discloses an elevator management system, which comprises the elevator management unit, a server and a camera in the elevator;
the camera is electrically connected with the image acquisition module; the server is in communication connection with the communication module.
In the elevator management system, the server is a cloud server.
Compared with the prior art, the invention has the beneficial effects that:
the scheme defines the identification area and the non-identification area by capturing the visual angle picture of the camera in advance. The meaning of the identification area is that if the coordinates of the person intersect with the identification area, the judgment and the identification pass; the meaning of the non-recognition area is that if the coordinates of the person fall entirely in the non-recognition area, it means that the recognition is not passed. When the camera reports the image to the server, if the server recognizes the coordinates of the person, the server returns a result to judge the recognition area and the non-recognition area, and if the recognition is passed, the result indicates that the ladder is trapped.
The method divides the identification of the person into two parts, wherein the main calculation part is arranged on a server, and the other part is arranged on a control platform directly connected with the elevator; the final judgment result is obtained through the control platform, so that the calculated amount can be effectively reduced, the judgment method does not need to rely on AI calculation and training when figures exist on objects such as posters, billboards and the like, only needs to adopt the most common human body identification method to identify whether people exist (whether living people or people on the posters) or not, and then further judgment is carried out, so that the accuracy can be effectively improved.
Drawings
FIG. 1 is a flow chart of embodiment 1 of the present invention;
fig. 2 is a block diagram showing the structure of embodiment 2 of the present invention.
Detailed Description
All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
A method for identifying whether a person is in an elevator, which is a direct object of this embodiment, is to apply when the elevator is in trouble and has a risk of getting trapped, so that the method is not applied during normal use. The method of the present embodiment is not inapplicable to the scene of identification of a normal living person. The following describes a specific scenario in connection with elevator people trapped.
The method of the invention comprises the following steps:
step 1: judging whether the elevator is in a fault alarm state, if so, performing step 2, and if not, repeating step 1;
the elevator is internally provided with a plurality of sensors for detecting different faults, an elevator management unit directly connected with the elevator can always analyze the operation data of the elevator, and the step 2 can be started no matter whether the sensors transmit fault signals or the elevator management unit obtains that the elevator is in a fault state through calculation;
step 2: acquiring an image in the elevator and sending the image to a server; the server is used for identifying the image and obtaining an identification result, wherein the identification result is that people exist or no people exist; if the person exists in the image, the identification result also comprises the coordinates of the person in the image;
the image acquisition is realized through a camera fixed in the elevator car;
since the camera mounting angles may be different for each elevator, it is necessary to define an identification area and a non-identification area in advance;
generally, the identification area is bounded by an elevator floor, and the areas outside the elevator floor are all non-identification areas;
in some application scenarios, the elevator floor can be bounded by 20cm, 30cm or 40cm upwards, and the non-recognition area is above the boundary; as this height will generally not place posters, advertising displays, etc.
The server is generally a cloud server, the existing commercial cloud platform is a better cloud server, and each large-scale platform provides an AI human body identification algorithm and only needs to purchase and use the services; the exclusive AI human body recognition algorithm of the enterprise can be built at the cloud.
The identification result is divided into people and no people;
if one is present, there are three possibilities: 1. the portrait is on the advertisement/poster in the elevator car; 2. no advertisement/poster of a person is displayed in the car, and a living person is in the car; 3. the figures are on advertisements/posters in the elevator car and there are living persons in the car.
For the server, whether the server is a living person or not is not required to be distinguished, and only the identification result is required to be output according to an AI human body identification algorithm.
As a further preference of this embodiment, the recognition result also includes a confidence of the judgment of the person for further recognition and operation by the elevator management unit.
Step 3: receiving an identification result sent by a server, if the identification result is unmanned, performing step 1 or terminating the process, and if the identification result is unmanned, performing step 4;
if the identification result is unmanned, the step 1 can be carried out again to acquire the image, so that the erroneous judgment of the current result is avoided, and the accuracy is improved; the result of no people trapped can be directly output and the process is terminated;
if the identification result is that there is a person, the elevator management unit is required to further judge whether the person on the house advertisement/poster is a living person.
The confidence level is mentioned in the step 2, and is taken as a necessarily generated result of AI human body recognition, in this step, the judgment accuracy can be further improved or whether to introduce a human for recognition is determined, specifically, if the recognition result is a person and the confidence level is lower than the threshold value, then we consider that the result of the server judging the person is not accepted, and directly consider that no person exists in the car;
or if the identification result is that someone exists and the confidence level is lower than the threshold value, notifying operation and maintenance or manual intervention of elevator management personnel to carry out auxiliary judgment.
Step 4: judging whether the coordinates of the person in the image enter a preset identification area, if so, alarming, otherwise, performing the step 1 or stopping the process; the identification area is an area defined in advance in a global image acquired from a camera of each elevator.
The importance of the division of the identification area has been described above, and on the server side, it is unnecessary to consider the identification area and the non-identification area, so that in this step, as long as the coordinates of the person in the image enter the identification area, it is considered that there is a part of the limb, and it can be judged as a living person without any doubt.
The scheme defines the identification area and the non-identification area by capturing the visual angle picture of the camera in advance. The meaning of the identification area is that if the coordinates of the person intersect with the identification area, the judgment and the identification pass; the meaning of the non-recognition area is that if the coordinates of the person fall entirely in the non-recognition area, it means that the recognition is not passed. When the camera reports the image to the server, if the server recognizes the coordinates of the person, the server returns a result to judge the recognition area and the non-recognition area, and if the recognition is passed, the result indicates that the ladder is trapped.
The method divides the identification of the person into two parts, wherein the main calculation part is arranged on a server, and the other part is arranged on a control platform directly connected with the elevator; the final judgment result is obtained through the control platform, so that the calculated amount can be effectively reduced, the judgment method does not need to rely on AI calculation and training when figures exist on objects such as posters, billboards and the like, only needs to adopt the most common human body identification method to identify whether people exist (whether living people or people on the posters) or not, and then further judgment is carried out, so that the accuracy can be effectively improved.
Example 2
An elevator management system comprises an elevator management unit 1, a server 2 and a camera 3 in an elevator;
the elevator management unit 1 comprises the following modules:
elevator status acquisition module 11: the image acquisition module 12 is used for judging whether the elevator is in a fault alarm state, and if so, the image acquisition module 12 is controlled to acquire an image;
image acquisition module 12: the method comprises the steps of acquiring an image in an elevator through a camera 3 arranged in the elevator;
the communication module 13: for transmitting the image obtained by the image obtaining module 12 to the server 2 and receiving the recognition result transmitted by the server 2; the server 2 is used for identifying images and obtaining identification results, wherein the identification results are people or no people; if a person exists in the image, the identification result also comprises the coordinates of the person in the image and preferably the confidence of the judgment of the server 2 on the person;
the identification module 14: the method comprises the steps of judging whether coordinates of a person in an image enter a preset identification area according to an identification result, alarming if yes, and not alarming if no; the identification area is an area previously delimited in the global image obtained from the camera 3 of each elevator, and is preferably also used for not alerting if the identification result is human and the confidence in the identification result is below a preset threshold.
The camera 3 is electrically connected with the image acquisition module 12; the server 2 is in communication connection with the communication module 13, and the server 2 is a cloud server.
The working process is as follows:
if the elevator fails, the elevator status acquisition module 11 acquires the message at the first time, and then starts the image acquisition module 12 to acquire the image in the elevator; the communication module 13 transmits the image to the server 2; the server 2 performs human AI identification and sends the device result to the identification module 14, and the identification module 14 judges whether the coordinates of the person enter the identification area if the identification result is that the person is present, if so, it is determined that the person is present in the car without doubt, and if not, no person is present in the car.
Through the system configuration, the recognition difficulty of trapped people in the car can be reduced, the recognition speed is improved, and the safety of equipment is improved.

Claims (9)

1. A method for identifying whether a person is in an elevator, comprising the steps of:
step 1: acquiring an image in the elevator and sending the image to a server; the server is used for identifying the image and obtaining an identification result, wherein the identification result is that people exist or no people exist; if the person exists in the image, the identification result also comprises the coordinates of the person in the image;
step 2: receiving an identification result sent by a server, if the identification result is unmanned, performing step 1 or terminating the process, and if the identification result is unmanned, performing step 3;
step 3: judging whether the coordinates of the person in the image enter a preset identification area, if so, alarming, otherwise, performing the step 1 or stopping the process; the identification area is an area defined in advance in a global image acquired from a camera of each elevator.
2. The method of claim 1, wherein if a person is in the image, the recognition result further comprises a confidence level;
in step 2, if the identification result is that a person exists and the confidence in the identification result is lower than a preset threshold, step 1 is performed or the process is terminated.
3. The method for identifying whether a person exists in an elevator according to claim 1, wherein the specific method for determining whether the coordinates of the person in the image enter a preset identification area in step 3 is as follows: judging whether all the coordinates of the person in the image are in the area outside the identification area, if so, the coordinates of the person in the image do not enter the preset identification area, and if not, the coordinates of the person in the image enter the preset identification area.
4. The method for identifying whether a person is present in an elevator according to claim 1, wherein the step 1 is preceded by:
step 10: and judging whether the elevator is in a fault alarm state, if so, performing the step 1.
5. An elevator management unit comprising the following modules:
an image acquisition module: the method comprises the steps of acquiring an image in an elevator through a camera arranged in the elevator;
and a communication module: the image acquisition module is used for acquiring images of the user, and sending the images to the server; the server is used for identifying the image and obtaining an identification result, wherein the identification result is that people exist or no people exist; if the person exists in the image, the identification result also comprises the coordinates of the person in the image;
and an identification module: the method comprises the steps of judging whether coordinates of a person in an image enter a preset identification area according to an identification result, alarming if yes, and not alarming if no; the identification area is an area defined in advance in a global image acquired from a camera of each elevator.
6. The elevator management unit of claim 5, wherein the identification result further comprises a confidence level of the server's judgment of the person;
the identification module is also used for identifying that the result is people and not alarming when the confidence level in the identification result is lower than a preset threshold value.
7. The elevator management unit of claim 5, further comprising:
elevator status acquisition module: and the image acquisition module is used for judging whether the elevator is in a fault alarm state, and if so, controlling the image acquisition module to acquire an image.
8. An elevator management system comprising an elevator management unit according to any one of claims 5-7, a server, a camera in an elevator;
the camera is electrically connected with the image acquisition module; the server is in communication connection with the communication module.
9. The elevator management system of claim 8, wherein the server is a cloud server.
CN202311697119.4A 2023-12-11 2023-12-11 Identification method for whether person exists in elevator, elevator management unit and system Pending CN117682400A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311697119.4A CN117682400A (en) 2023-12-11 2023-12-11 Identification method for whether person exists in elevator, elevator management unit and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311697119.4A CN117682400A (en) 2023-12-11 2023-12-11 Identification method for whether person exists in elevator, elevator management unit and system

Publications (1)

Publication Number Publication Date
CN117682400A true CN117682400A (en) 2024-03-12

Family

ID=90125921

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311697119.4A Pending CN117682400A (en) 2023-12-11 2023-12-11 Identification method for whether person exists in elevator, elevator management unit and system

Country Status (1)

Country Link
CN (1) CN117682400A (en)

Similar Documents

Publication Publication Date Title
CN111762649B (en) Elevator article detection system and method, article detection system, elevator light curtain and elevator equipment
CN110348312A (en) A kind of area video human action behavior real-time identification method
CN102750709B (en) Video is utilized to detect the method and apparatus of behavior of fighting
CN102521578A (en) Method for detecting and identifying intrusion
CN113096158A (en) Moving object identification method and device, electronic equipment and readable storage medium
CN108289191B (en) Image recognition method and device
CN112733690A (en) High-altitude parabolic detection method and device and electronic equipment
CN111918039A (en) Artificial intelligence high risk operation management and control system based on 5G network
CN116962598B (en) Monitoring video information fusion method and system
CN111985373A (en) Safety early warning method and device based on traffic intersection identification and electronic equipment
CN111191507A (en) Safety early warning analysis method and system for smart community
CN114332925A (en) Method, system and device for detecting pets in elevator and computer readable storage medium
CN112528825A (en) Station passenger recruitment service method based on image recognition
CN111908288A (en) TensorFlow-based elevator safety system and method
CN112585957A (en) Station monitoring system and station monitoring method
CN113553922A (en) Mask wearing state detection method based on improved convolutional neural network
CN117682400A (en) Identification method for whether person exists in elevator, elevator management unit and system
CN117768610A (en) High-speed railway perimeter intrusion risk monitoring method and system based on multi-target recognition
CN116071711B (en) Traffic jam condition detection method and device
CN114529979A (en) Human body posture identification system, human body posture identification method and non-transitory computer readable storage medium
CN113283273A (en) Front obstacle real-time detection method and system based on vision technology
CN113727215B (en) Data processing method, device, storage medium and equipment
CN110188645A (en) For the method for detecting human face of vehicle-mounted scene, device, vehicle and storage medium
CN114281656A (en) Intelligent central control system
CN114463911A (en) Safety protection system applied to high-speed rail platform

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