KR101752066B1 - Development of emergency detection system using environment information in elevator passenger and method thereof - Google Patents
Development of emergency detection system using environment information in elevator passenger and method thereof Download PDFInfo
- Publication number
- KR101752066B1 KR101752066B1 KR1020150165300A KR20150165300A KR101752066B1 KR 101752066 B1 KR101752066 B1 KR 101752066B1 KR 1020150165300 A KR1020150165300 A KR 1020150165300A KR 20150165300 A KR20150165300 A KR 20150165300A KR 101752066 B1 KR101752066 B1 KR 101752066B1
- Authority
- KR
- South Korea
- Prior art keywords
- elevator
- motion
- sound
- impact
- image
- Prior art date
Links
Images
Classifications
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
-
- 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
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H11/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by detecting changes in electric or magnetic properties
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/136—Incoming video signal characteristics or properties
- H04N19/137—Motion inside a coding unit, e.g. average field, frame or block difference
- H04N19/139—Analysis of motion vectors, e.g. their magnitude, direction, variance or reliability
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Abstract
The present invention relates to an emergency situation detection system and method using environment information of an elevator occupant who recognizes occurrence of an abnormal situation primarily by detecting noise, impact, etc. generated after a passenger boarding an elevator, A plurality of photographing units 100 for photographing the interior of the elevator and outputting photographed image signals; An acoustic sensing unit 200 provided in the elevator for receiving and outputting sound generated in the elevator; An impact sensing unit 300 provided in the elevator and sensing and outputting an impact state of the elevator; A sound intensity analyzer 420 for measuring a sound intensity of the sound signal input from the sound sensing unit 200 and generating and outputting a warning event if the sound intensity is greater than a reference sound intensity level, An impact analyzer 430 for comparing the derived impact quantity with a reference impact quantity and generating and outputting a warning event when the input shock quantity is large; and a warning event detector 430 for detecting a warning event from the sound quantity analyzer 420 and the impact analyzer 430 And an alarm generating unit 440 for recognizing an emergency situation when it is inputted and generating and sending an alarm signal. Therefore, even if the victim can not be notified of the dangerous situation, it is possible to quickly identify the emergency situation and protect the passenger from the serious crime.
Description
The present invention relates to an emergency situation detection system and method using environmental information of an elevator occupant, and more particularly, to an elevator occupant detection system and method for detecting an emergency situation by detecting a noise, an impact, etc., And more particularly, to a system and method for detecting an emergency situation using environmental information.
As a national policy, the Ministry of Public Administration and Security (MOFA) has mandated the installation of an emergency call system to detect an emergency situation in an elevator. In 2014, the law was amended to enact legal remedies if emergency call systems were not installed. Current demand for elevator policies and market expansion has increased sharply, but currently installed emergency systems are being used for follow - up action or crackdown rather than accident prevention. This focuses on situational responses rather than solving fundamental problems.
The incidence of crime in elevators is on the rise and is a social issue. An elevator having an isolated structure from the outside has various problems such as reduction of the number of passengers and deterioration of CCTV installed inside.
This affects the increasing frequency of felony crimes such as sex crimes and violent incidents in the elevator. To cope with such a problem, a system for ensuring the safety of passengers is required.
In case of crime inside the elevator, it is necessary for the victim to directly communicate the emergency situation to the guard room and the rescue institution or to check directly by the administrator. The faster the transmission of the emergency situation, the less the human or material loss of the victim. However, there is a problem that access is difficult when the CCTV manager is absent, or when the attacker blocks access to the device. If the response is late as in the above case, the victim may suffer irreparable damage.
It is necessary to develop a safety device to automatically determine the emergency situation in case of such felony crime, greatly reduce the crime rate and allow the victim to easily inform the emergency situation.
In order to meet such a technical development need, the present invention provides an emergency situation detection system using environmental information of an elevator occupant who senses a noise occurrence or an impact generated after a passenger is boarded in an elevator, And a method therefor.
Further, in the present invention, when the occurrence of an abnormal situation is recognized primarily through the noise and impact generated in the elevator, it is possible to verify whether or not an abnormality recognized primarily by using the image photographed through the photographing unit provided in the elevator is generated And an emergency situation detection system using the environment information of an elevator occupant and a method thereof.
An emergency situation detection system using environmental information of an elevator occupant according to an embodiment of the present invention includes a plurality of photographing
As an embodiment related to the present invention, the
Further, as an embodiment related to the present invention, the
In an embodiment related to the present invention, the
The method of detecting an emergency situation using environment information of an elevator occupant according to an embodiment of the present invention is characterized in that the
As an embodiment related to the present invention, when the
As an embodiment related to the present invention, if the magnitude of the amount of force and the magnitude of the impact amount are greater than the reference magnitude as a result of the environmental information analysis, the
The present invention recognizes the occurrence of an abnormal situation primarily by detecting a noise or an impact generated after a passenger boarding the elevator, and notifies the emergency situation that the emergency situation can be notified even when the victim can not notify the dangerous situation And to protect passengers from serious crimes.
Further, in the present invention, when the occurrence of an abnormal situation is recognized primarily through the noise and impact generated in the elevator, it is possible to verify whether or not an abnormality recognized primarily by using the image photographed through the photographing unit provided in the elevator is generated Thus, it is possible to improve the reliability of the emergency situation detection system by preventing the emergency situation from being recognized due to the noise and shock caused by the child's play or the behavior of the passenger.
1 is a view for explaining a configuration of an emergency situation detection system using environmental information of an elevator occupant according to the present invention.
FIG. 2 is a diagram for explaining a feature learning process using AdaBoost in the image analysis unit of FIG. 1. FIG.
FIG. 3 is a diagram for explaining a process for confirming whether a passenger is boarding in an elevator using block matching in the image analysis unit of FIG. 1. FIG.
4 is a flowchart illustrating an operation method of an emergency situation detection system using environmental information of an elevator occupant according to an embodiment of the present invention.
5 is a flowchart illustrating an operation method of an emergency situation detection system using environmental information of an elevator occupant according to another embodiment of the present invention.
It is noted that the technical terms used in the present invention are used only to describe specific embodiments and are not intended to limit the present invention. In addition, the technical terms used in the present invention should be construed in a sense generally understood by a person having ordinary skill in the art to which the present invention belongs, unless otherwise defined in the present invention, Should not be construed to mean, or be interpreted in an excessively reduced sense. In addition, when a technical term used in the present invention is an erroneous technical term that does not accurately express the concept of the present invention, it should be understood that technical terms can be understood by those skilled in the art. In addition, the general terms used in the present invention should be interpreted according to a predefined or prior context, and should not be construed as being excessively reduced.
Furthermore, the singular expressions used in the present invention include plural expressions unless the context clearly dictates otherwise. In the present invention, terms such as "comprising" or "comprising" and the like should not be construed as encompassing various elements or various steps of the invention, Or may further include additional components or steps.
Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings, wherein like reference numerals refer to like or similar elements throughout the several views, and redundant description thereof will be omitted.
1 is a view for explaining a configuration of an emergency situation detection system using environmental information of an elevator occupant according to the present invention. FIG. 2 is a diagram for explaining a feature learning process using AdaBoost in the image analysis unit of FIG. 1. FIG. FIG. 3 is a diagram for explaining a process for confirming whether a passenger is boarding in an elevator using block matching in the image analysis unit of FIG. 1. FIG.
1 to 3, an emergency situation detection system using environment information of an elevator passenger to which the present invention is applied includes a plurality of photographing units 100 (shown in FIG. 1) provided in an elevator and photographing an interior of the elevator, An
The
The
The
Here, the characteristic data learning method uses the AdaBoost algorithm as shown in FIG. The AdaBoost algorithm combines WC (Weak Classifier) through learning to generate SC (Strong classifier) with high detection performance and performs learning by iterative calculation of WC. SC is a linear combination of WC Combining features with WC allows you to distinguish the type of occupant practically.
That is, the
Also, the
In more detail, the
As shown in Equation 1, D (x, y) is a difference image, T h is a threshold value, and? (X, y) is a pixel difference between x and y coordinates. That is, if the difference of the pixels is equal to or greater than the threshold value, it indicates that there is motion, otherwise it can be determined that there is no motion. In the case of the difference method, it is used to determine whether there is an occupant or not on the basis of the case where the occupant rides on the elevator
On the other hand, a motion vector is obtained by using a block matching method as shown in FIG. When the passenger is present inside the elevator, the motion state of the passenger can be determined through the magnitude of the motion vector. The block matching method assumes that all pixels in a block have the same motion and that the motion of the object is a parallel motion. Each block is independent and this method is robust to noise and low computational complexity and is useful for real-time processing. In general, the blocks are preferably 8x8 or 16x16. The smaller the size of the block, the more accurate the motion vector can be predicted, but the larger the amount of computation.
The block matching method determines a search position indicating a macroblock (MB), obtains a sum of absolute difference (SAD) thereof, and determines a direction having a smallest value as a motion vector. The method of determining the SAD value is as shown in Equation 2 above. R (i, j) is the pixel in the current frame MB and S (x + u, j + v) is the pixel in the reference frame. The range of i and j is -p ≤ u, v ≤ p ([- p, p]: search area), where N and M are block sizes. Therefore, the block with the smallest SAD (u, v) in the search area is determined as the best-matched block, and M (i, j) at this time is set as the motion vector.
An operation method of the emergency situation detection system using the environment information of the elevator occupant configured as described above will be described as follows.
( Example 1 _ Weight Size And emergency situation recognition through the amount of impact)
4 is a flowchart illustrating an operation method of an emergency situation detection system using environmental information of an elevator occupant according to an embodiment of the present invention.
4, the method of operating the emergency situation sensing system using the environmental information of the elevator occupant can be performed by using only the signals input through the
4, the
Then, the
Here, the criteria of the quantitative analysis are as follows according to the data of the Korea Research Institute of Standards and Science.
As can be seen from Table 1, it is possible to compare and analyze the occupant performance in a general situation and the performance in an unusual situation. Typically, units of decibels (dB) are used to represent noise, vibration, and electricity. This is likely to indicate a change in sensitivity.
(1.5 meters away)
(1 meter away)
The performance in the normal situation is based on the normal conversation in the elevator and the amount of communication during the conversation, based on the <Table>. Assuming that the sound of the passenger is a whisper and a general conversation, whispers are 20-25 decibels, and conversations within a meter are 40-50 decibels.
But it is different in an emergency situation. Unlike the general situation, screaming or shouting occurs, which varies in size. Usually, a shout at 1.5 meters away is 80 to 100 decibels. However, when the perpetrator stops the victim's mouth, the decibel analysis using the
As a result of analyzing the environment information collected by the
When the
When the
There is a limit in recognizing an emergency situation using only the sound sensing unit and the shock sensing unit which are acoustic sensors in the first embodiment. These limitations make it difficult for criminals to provide information and reduce credibility. The reliability problem in the emergency situation detection system is very important. For example, it is less reliable if the children who ride the elevator play inside or misunderstand that the environmental information generated by staggering the driver while singing loudly and hitting the inner wall of the elevator is called an emergency situation. When outputting an alarm signal to the
In addition, as in the second embodiment, the
( Example 2 _ Weight Size And recognition of the first emergency situation through the impact amount, and recognition of the second emergency situation through the image size)
5 is a flowchart illustrating an operation method of an emergency situation detection system using environmental information of an elevator occupant according to another embodiment of the present invention.
As shown in FIG. 5, the
The
As a result of analyzing the environment information collected by the
As a result of the analysis, if the
The detailed description of parts applied in the second embodiment in the same way as in the first embodiment will be omitted.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or essential characteristics thereof. Therefore, the embodiments disclosed in the present invention are intended to illustrate rather than limit the scope of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents should be construed as falling within the scope of the present invention.
100: photographing part 200: sound sensing part
300: shock detection unit 400: controller
410: Image analysis unit 420:
430: Impact analyzer 440: Alert generator
450: communication unit 500: control system
Claims (7)
An acoustic sensing unit 200 provided in the elevator for receiving and outputting sound generated in the elevator;
An impact sensing unit 300 provided in the elevator and sensing and outputting an impact state of the elevator;
A sound intensity analyzer 420 for measuring a sound intensity of the sound signal input from the sound sensing unit 200 and generating and outputting a warning event if the sound intensity is greater than a reference sound intensity; An impact analyzer 430 for comparing the derived impact quantity with a reference impact quantity and generating and outputting a warning event if the input shock quantity is large; A controller (400) comprising an alarm generating unit (440) for recognizing an emergency situation when an alarm event is input and generating and sending an alarm signal; And
The controller 400 obtains the motion of the elevator occupant based on the video signals of the plurality of photographing units 100 and derives the motion magnitude. If the motion magnitude is larger than the reference motion magnitude, An analysis unit 410;
/ RTI >
The image analysis unit 410 detects the face, the upper body, and the body information of the passenger using the learned feature data, and the learning method of the feature data combines the Weak Classifier (WC) SC is a linear combination of WC, which combines several features with WC to distinguish the form of passenger,
The image analyzer 410 searches the input image for a searching range and separates the sub-image into sub-images. The sub-image is an input portion of the SC, If it is determined that the passenger is the result of the detection, it is determined that the sub-image is the passenger,
The warning generating unit 400 of the controller 400 checks whether a warning event is inputted from the image analyzing unit 410 when the warning analyzing unit 420 and the impact analyzing unit 430 input a warning event When the emergency information is received, generates an alarm signal including an image confirmation informing message, recognizes the emergency situation, and transmits the alarm signal to the emergency situation detecting system using the environment information of the elevator occupant.
An acoustic sensing unit 200 provided in the elevator for receiving and outputting sound generated in the elevator;
An impact sensing unit 300 provided in the elevator and sensing and outputting an impact state of the elevator;
A sound intensity analyzer 420 for measuring a sound intensity of the sound signal input from the sound sensing unit 200 and generating and outputting a warning event if the sound intensity is greater than a reference sound intensity; An impact analyzer 430 for comparing the derived impact quantity with a reference impact quantity and generating and outputting a warning event when the input shock quantity is large; A controller (400) comprising an alarm generating unit (440) for recognizing an emergency situation when an alarm event is input and generating and sending an alarm signal; And
The controller 400 obtains the motion of the elevator occupant based on the video signals of the plurality of photographing units 100 and derives the motion magnitude. If the motion magnitude is larger than the reference motion magnitude, An analysis unit 410;
/ RTI >
The image analyzing unit 410 calculates pixel differences of two frames in the image analysis, determines whether a passenger is present in the elevator through a pixel change, extracts a motion vector from the photographed image, The state of the occupant's movement is determined,
When the occupant is present in the elevator, the motion vector is obtained by using a block matching method in which all pixels in the block have the same motion and the motion of the object is assumed to be parallel movement. The SAD (Sum of Absolute Difference) value is determined, and the direction having the smallest value is determined as a motion vector,
The alarm generating unit 400 of the controller 400 checks whether a warning event is inputted from the image analyzing unit 410 when the alarm analyzing unit 420 and the impact analyzing unit 430 input a warning event When the emergency information is received, generates an alarm signal including an image confirmation informing message, recognizes the emergency situation, and transmits the alarm signal to the emergency situation detecting system using the environment information of the elevator occupant.
Analyzing the video signal from the collected environment information to derive a magnitude of motion and analyzing whether the magnitude of the derived motion is larger than a reference motion magnitude;
Analyzing the sound signal from the collected environment information to derive the size of the sound and analyzing whether the size of the derived sound is larger than the reference sound size; And
The controller (400) derives an impulse amount from the collected environment information, compares the impulse amount with a reference impulse amount, and analyzes whether the derived impulse amount is larger than a reference impulse amount;
/ RTI >
In the step of analyzing whether the size of the derived motion is larger than the reference motion size, the controller 400 analyzes the video signal from the collected environment information to derive the magnitude of the motion,
The image analyzing unit 410 in the controller detects the face, the upper body, and the body information of the occupant using the learned feature data. The learning method of the feature data combines the Weak Classifier (WC) SC (Strong classifier) with performance is performed, and learning is performed by iterative calculation of WC. SC combines several features WC in linear combination form of WC to distinguish the form of passenger substantially The image analyzing unit 410 searches the inputted image for a range of searching range and separates the input image into sub-images. The separated sub-images become an input portion of the SC. And determining the sub-image as an occupant if the value is a result of determining that the occupant is the resultant passenger.
Analyzing the video signal from the collected environment information to derive a magnitude of motion and analyzing whether the magnitude of the derived motion is larger than a reference motion magnitude;
Analyzing the sound signal from the collected environment information to derive the size of the sound and analyzing whether the size of the derived sound is larger than the reference sound size; And
The controller (400) derives an impulse amount from the collected environment information, compares the impulse amount with a reference impulse amount, and analyzes whether the derived impulse amount is larger than a reference impulse amount;
/ RTI >
In the step of analyzing whether the size of the derived motion is larger than the reference motion size, the controller 400 analyzes the video signal from the collected environment information to derive the magnitude of the motion,
In the controller, the image analysis unit 410 calculates pixel differences of two frames in the image analysis, determines whether a passenger is present in the elevator through a pixel change, extracts a motion vector from the photographed image, The size of the occupant determines the movement state of the occupant,
When the occupant is present in the elevator, the motion vector is obtained by using a block matching method in which all pixels in the block have the same motion and the motion of the object is assumed to be a parallel motion. And determining the direction having the smallest value as a motion vector. The emergency situation detection method according to claim 1, further comprising:
The controller 400 determines whether the size of the movement is larger than the reference size, if the size of the content and the magnitude of the amount of impact are larger than the reference size as a result of the environment information analysis. If the size of the movement is larger than the reference size, Further comprising the step of recognizing that an emergency situation has occurred in the elevator.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020150165300A KR101752066B1 (en) | 2015-11-25 | 2015-11-25 | Development of emergency detection system using environment information in elevator passenger and method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020150165300A KR101752066B1 (en) | 2015-11-25 | 2015-11-25 | Development of emergency detection system using environment information in elevator passenger and method thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
KR20170060756A KR20170060756A (en) | 2017-06-02 |
KR101752066B1 true KR101752066B1 (en) | 2017-06-30 |
Family
ID=59222444
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020150165300A KR101752066B1 (en) | 2015-11-25 | 2015-11-25 | Development of emergency detection system using environment information in elevator passenger and method thereof |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR101752066B1 (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11643302B2 (en) * | 2017-11-22 | 2023-05-09 | Otis Elevator Company | Sensing and notifying device for elevator emergencies |
CN107911663A (en) * | 2017-11-27 | 2018-04-13 | 江苏理工学院 | A kind of elevator passenger hazardous act intelligent recognition early warning system based on Computer Vision Detection |
CN115829655B (en) * | 2022-12-30 | 2023-09-22 | 广州掌购网络科技有限公司 | Advertisement effect intelligent analysis management system and method based on big data analysis |
-
2015
- 2015-11-25 KR KR1020150165300A patent/KR101752066B1/en active IP Right Grant
Also Published As
Publication number | Publication date |
---|---|
KR20170060756A (en) | 2017-06-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101445367B1 (en) | Intelligent cctv system to recognize emergency using unusual sound source detection and emergency recognition method | |
US9779614B2 (en) | System and method of alerting CMS and registered users about a potential duress situation using a mobile application | |
US9761248B2 (en) | Action analysis device, action analysis method, and action analysis program | |
CN111063162A (en) | Silent alarm method and device, computer equipment and storage medium | |
KR101899436B1 (en) | Safety Sensor Based on Scream Detection | |
KR101752066B1 (en) | Development of emergency detection system using environment information in elevator passenger and method thereof | |
AU2009210794A1 (en) | Video sensor and alarm system and method with object and event classification | |
US20080068158A1 (en) | Danger sensing information device | |
KR101609914B1 (en) | the emergency situation sensing device responding to physical and mental shock and the emergency situation sensing method using the same | |
WO2019185045A1 (en) | Transport device collision detection, alarm, and guard method | |
JP5833995B2 (en) | Elevator abnormality monitoring device | |
KR101384781B1 (en) | Apparatus and method for detecting unusual sound | |
KR102069270B1 (en) | CCTV system with fire detection | |
KR20160150323A (en) | Sensor-based Intelligent Emergency Call Client Device | |
JP2013063810A (en) | Elevator monitoring device | |
KR20180066688A (en) | Digital Social Shield System using Deep Active Semi-Supervised Learning | |
KR101093022B1 (en) | System for monitoring in passenger car | |
KR20170126821A (en) | Sensor-based Intelligent Emergency Call Client Device | |
CN111860194A (en) | Household intelligent safety monitoring system and method | |
KR101629219B1 (en) | An elevator monitor that restricts access through face recognition | |
JP2005309965A (en) | Home security device | |
KR20140059962A (en) | Elevator crime prvent system and method of controlling the same | |
KR101509223B1 (en) | Security system with an auto capturing for monitoring screen and method of the same | |
KR101669885B1 (en) | method of detecting pedestrian collision and IoT apparatus thereof | |
KR101582454B1 (en) | Method for cognition of movement object in photographing image and system for prevention of vehicle boarding accident |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
E902 | Notification of reason for refusal | ||
E701 | Decision to grant or registration of patent right | ||
GRNT | Written decision to grant |