KR101784399B1 - A floor operating information recognition system of elevator camera using atmospheric pressure and acceleration sensor - Google Patents

Abstract

The present invention relates to a floor driving information recognition system for an elevator camera using an atmospheric pressure and an acceleration sensor, and is installed to photograph the inside of the elevator. The atmospheric pressure, temperature and acceleration detected from the built- An IP camera which acquires information on the travel floor of the elevator based on the information of the uppermost layer, converts the travel floor information of the elevator acquired with the photographed image into an RTSP (Real-Time Streaming Protocol) method, and transmits the RTSP; And a controller for receiving the photographed image converted from the IP camera by the RTSP method and the traveling floor information of the elevator, displaying the photographed image and the floor data on a screen, displaying the lowest and highest floor information of the building, And includes a client for transmitting to an IP camera.
According to the layer driving information recognition system of the elevator camera using the atmospheric pressure and acceleration sensor proposed in the present invention, regardless of whether the floor display panel is fixed or the floor is not displayed or the floor is not displayed, It is possible to recognize the position of the photographing area, so that it is not necessary to include the floor display panel in the photographing area, so that the blind spot of the photographing area can be minimized.
In addition, according to the present invention, since the IP camera installed in the elevator can independently recognize the layer, there is no need to install a device other than the camera without affecting other elevator systems, and the installation time is shortened So that the convenience of installation can be improved.
In addition, the present invention is configured to acquire the travel floor information using the accumulated deep running data for layer classification, so that when the IP camera is installed in the elevator for the first time, information of all layers to the building, It is possible to increase the convenience of inputting only the information of the lowest floor and the floor of the building without inputting the height, the elevator speed, and the like.

Description

TECHNICAL FIELD [0001] The present invention relates to a floor operating information recognition system for an elevator camera using an atmospheric pressure and an acceleration sensor,

The present invention relates to a layer driving information recognition system for an elevator camera using an atmospheric pressure and an acceleration sensor. More specifically, the present invention calculates gravity acceleration using accelerations of three axes originating from an acceleration sensor built in an IP camera, After calculating the moving direction of the elevator and the time from the start to the arrival of the elevator by using the acceleration, the algorithm for classifying and averaging the moving direction of the elevator and the time taken for the layer moving to the number of moved layers is applied, The present invention relates to a floor driving information recognition system for an elevator camera using an atmospheric pressure and acceleration sensor for comparing driving room information of an elevator with an image of an inside of the elevator and transmitting the same to a client so that elevator driving information can be recognized.

Generally, elevators are installed in buildings such as apartments and buildings. Such an elevator may cause various types of accidents. For example, an elevator suddenly stops, a person is trapped, or a person who intends for a person to be alone, or a sexual harassment case aiming at a woman is frequent. CCTV is installed for the purpose of crime prevention, the follow-up of criminals, or to ascertain the internal situation of the elevator when an incident occurs. The CCTV image is transmitted to the guard room or the management room Managed and monitored.

However, when an accident occurs in an elevator, it is necessary to find out the number of elevators in which an accident occurred. However, it is difficult to judge the number of floors based on only the captured images, and it is also difficult to analyze the floors . In the conventional camera installed in the elevator, the photographing area is provided so as to photograph the floor display panel part, so that it is possible to know how many layers are seen from the image. However, in this method, the number of layers of the display panel is not clear, There was a problem that inconvenience was followed.

Further, even in the case of other cameras installed in a conventional elevator, the technology of displaying the number of layers on the image of the camera by using the image recognition technology of the camera to digitize the value of the layer display panel is used. However, , A camera is taken up to the floor display panel, and a blind spot is formed in the lower part of the camera. If the floor display panel is covered, the layer may not be known. In addition, in the case of the conventional elevator, there is a problem that a device for measuring layer driving information for outputting floor driving information together with images of the photographed camera needs to be installed separately. As an apparatus for measuring layer information of an elevator, Korean Patent Laid-Open Publication No. 10-2013-0123798, Registered Patent Publication No. 10-0976781, and Registered Patent Publication No. 10-1404453 are disclosed in the prior art documents.

The present invention has been proposed in order to solve the above-mentioned problems of the previously proposed methods. The present invention proposes a method in which a layer display panel is photographed so as to display a layer position of an elevator on an image taken by a camera of a conventional elevator, Atmospheric pressure and acceleration, which can solve the conventional problems of having to input both the elevator and building floor information before driving the camera, recognizing the floor by using the atmospheric pressure and acceleration sensor but installing other additional devices at the outside, And an object of the present invention is to provide a floor driving information recognition system of an elevator camera using a sensor.

According to an aspect of the present invention, there is provided a layer driving information recognition system for an elevator camera using atmospheric pressure and acceleration sensors,

A floor operating information recognition system of an elevator camera using an atmospheric pressure and an acceleration sensor,

The information on the operating floor of the elevator is acquired based on the atmospheric pressure, the temperature, and the acceleration detected from the built-in sensor and the information of the lowest floor and the highest floor of the building in which the elevator is installed. An IP camera for converting the obtained transport layer information of the elevator into an RTSP (Real-Time Streaming Protocol) format and transmitting the same; And

The IP camera receives the photographed image converted from the IP camera and the traveling floor information of the elevator, displays the photographed image and the floor data on a screen, displays the lowest layer and the highest layer of the building, And includes a client for transmitting to a camera.

Preferably, the IP camera further comprises:

A camera image receiving unit for converting an analog image captured inside the elevator into a digital image;

And an acceleration sensor for measuring an acceleration, wherein the atmospheric pressure / temperature sensor for measuring the atmospheric pressure and the temperature and the acceleration sensor for measuring the acceleration are used, the measurement atmospheric pressure is corrected using the measurement temperature among the sensor data detected from the atmospheric pressure / temperature sensor and the acceleration sensor, A sensor processing unit for calculating an operation direction of the elevator measured by gravitational acceleration and gravitational acceleration according to the installation inclination of the camera using the acceleration,

A depth learning unit for classifying the time taken for the layer movement of the sensor processing unit according to the number of moving layers, calculating layer data using the number of moving layers, and correcting the layer data by comparing the time with the previously stored atmospheric pressure;

An OSD processing unit for transmitting OSD setting data in which layer data output from the deep learning processing unit is set as an OSD (On Screen Display) position and an OSD character;

An OSD image generation unit for generating an OSD image by superimposing the digital image of the camera image receiving unit and the OSD setting data of the OSD processing unit, and transmitting the generated OSD image;

An RTSP metadata generation unit for converting the analyzed layer data and sensor data received from the deep learning processing unit and the OSD image received from the OSD image generation unit into RTSP metadata and transmitting the RTSP metadata; And

And an RTSP metadata transmitter for transmitting the converted RTSP metadata received from the RTSP metadata generator to the client.

More preferably, the sensor processing unit includes:

And the correction atmospheric pressure is calculated by correcting the measured atmospheric pressure using the measured temperature detected from the atmospheric pressure / temperature sensor.

Still more preferably, the sensor processing unit includes:

The gravity acceleration can be calculated using the accelerations of the three axes detected from the acceleration sensor, and the traveling direction of the elevator and the time taken to move the layer can be measured using the calculated gravity acceleration.

Preferably, the deep-learning processing unit includes:

It is possible to accumulate the deep learning data for layer classification by classifying and storing the time data obtained during the layer movement calculated from the sensor processing unit according to the number of layers moved.

More preferably, the deep-

It is possible to calculate how many layers have been moved by comparing the accumulated information of the deep learning data classified and stored in the layer moving time data with the time data of the newly created layer moving in the sensor processing unit, have.

Still more preferably, the deep-

The layer data may be corrected in such a manner as to determine how many layers have been moved by comparing the atmospheric pressure with the previously stored layered atmospheric pressure data and then comparing the same with the time data at the time of layer transfer to determine the same.

Advantageously, the client comprises:

A user setting unit for setting camera settings and information of the lowest layer and the highest layer of the elevator and transmitting the set information to the deep learning processing unit of the IP camera; And

And an image display and data processing unit for classifying the RTSP metadata received from the RTSP metadata transmitting unit of the IP camera and displaying image data and sensor data on a screen,

The client includes:

A mobile client having a user environment setting unit and a video display and data processing unit, and a web client.

According to the floor driving information recognition system of the elevator camera using the atmospheric pressure and acceleration sensor proposed in the present invention, the IP camera installed in the elevator and capturing an image is provided. In the acceleration sensor, And calculates the gravitational acceleration using the calculated gravitational acceleration to determine the moving direction of the elevator and the time from the departure to the arrival of the elevator and then classifies the moving direction of the elevator and the time taken to move the floor to the number of moved floors The algorithm of the averaging algorithm is applied to compare the accumulated running data with the accumulated deep running data to acquire the operating layer information of the elevator and transmit the image of the inside of the elevator to the client so that the elevator driving information can be recognized, The floor display panel is covered or the floor display panel is fixed or the floor Since it is possible to recognize the position of a layer, regardless of whether that is not visible and do not need to include this layer display panel on the recording region through can allow the blind spot of the recording area can be minimized.

In addition, according to the present invention, since the IP camera installed in the elevator can independently recognize the layer, there is no need to install a device other than the camera without affecting other elevator systems, and the installation time is shortened So that the convenience of installation can be improved.

In addition, the present invention is configured to acquire the travel floor information using the accumulated deep running data for layer classification, so that when the IP camera is installed in the elevator for the first time, information of all layers to the building, It is possible to increase the convenience of inputting only the information of the lowest floor and the floor of the building without inputting the height, the elevator speed, and the like.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a conceptual diagram of a layer driving information recognition system of an elevator camera using an atmospheric pressure and acceleration sensor according to an embodiment of the present invention; FIG.
FIG. 2 is a functional block diagram showing the overall structure of a floor driving information recognition system of an elevator camera using an atmospheric pressure and acceleration sensor according to an embodiment of the present invention. FIG.
FIG. 3 is a graph showing data of gravitational acceleration when the driving direction of the elevator is raised or lowered during operation of the elevator to which the floor driving information recognition system of the elevator camera using the atmospheric pressure and acceleration sensor according to the embodiment of the present invention is applied. FIG.
FIG. 4 is a graph showing gravitational acceleration output during one-layer, two-layer, and five-layer movements of an elevator to which a floor driving information recognition system of an elevator camera using an atmospheric pressure and acceleration sensor according to an embodiment of the present invention is applied drawing.
FIG. 5 is a graph illustrating a time classifying a time taken depending on the number of layers when an elevator to which a floor driving information recognition system of an elevator camera using an atmospheric pressure and acceleration sensor according to an embodiment of the present invention is applied moves several layers drawing.
FIG. 6 is a graph showing the data obtained by correcting the data of the atmospheric pressure using the temperature of the elevator to which the floor driving information recognition system of the elevator camera using the atmospheric pressure and acceleration sensor according to the embodiment of the present invention is applied, FIG.
7 is a flowchart illustrating a process of classifying and storing layer movement time in a deep learning processing unit of an IP camera applied to a layer driving information recognition system of an elevator camera using an atmospheric pressure and acceleration sensor according to an embodiment of the present invention .

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings, in order that those skilled in the art can easily carry out the present invention. In the following detailed description of the preferred embodiments of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear. In the drawings, like reference numerals are used throughout the drawings.

In addition, in the entire specification, when a part is referred to as being 'connected' to another part, it may be referred to as 'indirectly connected' not only with 'directly connected' . Also, to "include" an element means that it may include other elements, rather than excluding other elements, unless specifically stated otherwise.

FIG. 1 is a view showing a conceptual structure of a floor driving information recognition system of an elevator camera using an atmospheric pressure and acceleration sensor according to an embodiment of the present invention, and FIG. 2 is a schematic view showing an atmospheric pressure and acceleration sensor according to an embodiment of the present invention. Fig. 2 is a functional block diagram showing the overall configuration of a layer driving information recognition system of a lift camera used. 1 and 2, the floor driving information recognition system of an elevator camera using atmospheric pressure and acceleration sensors according to an embodiment of the present invention includes an IP camera 100 and a client 200 Lt; / RTI >

The IP camera 100 is installed to photograph the inside of the elevator and acquires the operating floor information of the elevator on the basis of the atmospheric pressure, the temperature, the acceleration detected from the built-in sensor, and the information of the lowest floor and the highest floor of the building in which the elevator is installed And converts the travel floor information of the elevator acquired together with the photographed image into a real-time streaming protocol (RTSP) method and transmits the same to the client 200, which will be described later. 2, the IP camera 100 includes a camera image receiving unit 110 for converting an analog image photographed inside the elevator into a digital image, an atmospheric pressure / temperature sensor 121 for measuring atmospheric pressure and temperature, And an acceleration sensor 122 for measuring the acceleration, and performs correction of the measurement atmospheric pressure using the measurement temperature among the sensor data detected from the atmospheric pressure / temperature sensor 121 and the acceleration sensor 122, A sensor processing unit 120 for performing an arithmetic operation to obtain a driving direction and a time taken to move the floor due to gravitational acceleration and gravitational acceleration according to the inclination of the camera, A deep learning processing unit 130 for classifying the layer data, calculating layer data using the data, and comparing the layer data with the previously stored atmospheric pressure, An OSD processing unit 140 for transmitting OSD setting data in which the layer data output from the OSD processing unit 130 is set as an OSD (On Screen Display) position and an OSD character, a digital image of the camera image receiving unit 110, An OSD image generation unit 150 for superimposing the OSD setting data of the OSD setting data on the OSD image data and generating and transmitting an OSD image to the OSD setting data received from the OSD image generating unit 150, An RTSP metadata generation unit 160 that converts the OSD image into RTSP metadata and transmits the RTSP metadata to the client 200 and an RTSP metadata transmission unit 160 that transmits the converted RTSP metadata received from the RTSP metadata generation unit 160 to the client 200 (170). ≪ / RTI >

Here, the acceleration sensor 122 is installed inside the IP camera 100 to recognize the layer of the elevator, and outputs the acceleration data about the three axes of the position provided in the IP camera 100 to the sensor processing unit 120 , The sensor processing unit 120 measures the gravitational acceleration and measures a change in the gravitational acceleration when the elevator is moved to calculate the traveling direction of the elevator and the time taken to operate the elevator. In a typical acceleration sensor, the number of axes for measuring acceleration is divided into three axes, which are divided into x, y, and z axes, respectively. In this case, if three axes are used, it becomes a three-axis acceleration sensor. If two axes are used, a two-axis acceleration sensor and one axis can be used as a one-axis acceleration sensor. In using the acceleration sensor as described above, it is preferable to use the one-axis acceleration sensor because the elevator uses only the up-and-down vertical motion. However, since the direction of the acceleration sensor may be changed according to the movement of the camera and the installation direction of the camera It is more preferable to use a three-axis acceleration sensor capable of measuring all three axes. Therefore, in the present invention, when the acceleration sensor 122 is installed inside the IP camera 100 and the camera is installed regardless of the direction of the elevator, a three-axis acceleration sensor is used so that the acceleration can be measured according to the vertical movement of the elevator , The gravity acceleration is measured using the measured acceleration data of the three axes, and the elevator is operated only when the gravity acceleration has moved vertically.

That is, the sensor processing unit 120 may calculate the corrected atmospheric pressure by correcting the measured atmospheric pressure in the case of the measured temperature detected from the atmospheric pressure / temperature sensor 121, and store the corrected atmospheric pressure as the atmospheric pressure data for each layer. The sensor processing unit 120 may calculate the gravitational acceleration using the accelerations of the three axes detected from the acceleration sensor 122, and measure the traveling direction of the elevator and the time taken to move the layer using the calculated gravitational acceleration.

In addition, the deep learning processor 130 may accumulate deep learning data for layer classification by classifying and storing the time data calculated during the layer movement calculated from the sensor processor 120 according to the number of layers moved. Also, the deep learning processor 130 compares the accumulated information of the deep learning data classified and stored in the layer moving time data with the time data of the newly created layer moving in the sensor processing unit 120 to determine how many layers have been moved And the arrival layer data after the movement can be obtained.

The depth learning processor 130 obtains the atmospheric pressure that is changed at the time of layer movement and compares the atmospheric pressure with the stored atmospheric pressure data stored in advance to determine how many layers have been moved. Then, the depth learning processor 130 compares the time data Correction processing can be performed.

The deep learning processor 130 minimizes the initial input information such as the direction of operation of the acceleration sensor, the reference height of the elevator, the elevation height of each floor, the moving speed of the elevator, and the like, The uppermost layer and the lowermost layer are set by receiving information on the uppermost layer and the lowermost layer from the client 200 as information necessary for minimum depth running. In other words, if the top and bottom layers of the building are not set up, even if 10 layers are divided by deep running, it may be difficult to distinguish the layers from the 1st floor to the 10th floor or from the 3rd floor to the 7th floor. That is, the deep learning processing unit 130 classifies and stores data according to the number of layers moved, and stores data based on the time data received during the movement of the layer calculated from the sensor processing unit 120. Here, the reason for classifying according to the number of layers moved is data generated when layer movement is performed irrespective of the directionality, and the speed of the elevator does not greatly change. Time data during layer movement is similar to the number of layers, It is possible to check how many layers have been moved by comparing with the time data of the newly created layer in the processing unit 120, so that the layer data after the movement can be obtained.

When the depth learning processor 130 determines how many layers have been moved from the start layer to the arrival layer, the depth learning processor 130 determines how much the atmospheric pressure of the moved layer has changed and compares it with the previously stored atmospheric pressure data, The layer data is compared with the layer data obtained by the time data taken at the time of layer transfer, so that the layer data can be corrected and the reliability can be increased.

In addition, the OSD processing unit 140 can set the OSD character, the output position of the screen, and the size of the character based on the layer data output from the deep learning processing unit 130.

The client 200 receives the photographed image converted from the IP camera 100 by the RTSP method and the travel floor information of the elevator, displays the photographed image and the floor data on the screen, And transmits the information of the lowest layer and the highest layer to the IP camera 100. FIG. The client 200 includes a user environment setting unit 203 for setting camera settings and information of the lowest and highest layers of the elevator and transmitting the set information to the deep learning processing unit 130 of the IP camera 100, And an image display and data processing unit 204 for classifying the RTSP metadata received from the RTSP metadata transmitting unit 170 of the mobile terminal 100 and displaying image data and sensor data on the screen. The client 200 is connected to the mobile client 201 and the web client 202 having the user environment setting unit 203 and the image display and data processing unit 204 according to a method connected to the IP camera 100 Respectively. That is, the client 200 can monitor the OSD image, the sensor data, and the calculation data of the RTSP metadata transmitted from the IP camera 100 as a remote image of the image display and data processing unit 204, Unit 203 performs environment setting such as the uppermost layer and the lowermost layer for the range of data accumulation in the deep learning processing unit 130 of the IP camera 100 and transmits the set data.

FIG. 3 is a graph showing data of gravitational acceleration when the driving direction of the elevator is raised or lowered during operation of the elevator to which the floor driving information recognition system of the elevator camera using the atmospheric pressure and acceleration sensor according to the embodiment of the present invention is applied. And FIG. 4 is a graph showing the gravitational acceleration output from one-layer, two-layer, and five-layer movements of the elevator in which the layer driving information recognition system of the elevator camera using the atmospheric pressure and acceleration sensor according to the embodiment of the present invention is applied. As a graph. 3 is a graph showing data when the driving direction of the elevator is raised or lowered after calculating acceleration of three axes detected by the acceleration sensor 122 when the elevator is operated by gravity acceleration, Gravity acceleration output at the time of one-layer movement, two-layer movement, and five-layer movement is shown in a graph. That is, FIG. 3 is a graph for explaining that the direction of travel of the elevator can be determined using only the acceleration sensor 122. It is seen that the gravitational acceleration is lowered at the time of descent and is increased, and the gravitational acceleration is increased and decreased at the time of ascending. . Therefore, the direction in which the elevator travels can be obtained by using the gravitational acceleration. FIG. 4 is a graph for explaining a change in acceleration when the elevator moves in several layers. As shown in FIG. 4, when the graph of the first floor moves and the graph of the second floor moves, And the part where the equivalent speed motion is generated in the rising part can be seen. It can be seen from the graph that the 5th floor is moved at once that the part that performs the equivalent speed motion is longer. Here, since the x-axis of the graph represents time, it can be said that when moving several layers, the time increases in proportion to the number of layer movements. That is, it is possible to know how many layers have been moved according to the layer moving time, and accordingly, the layer moving time can be classified and stored, and the layer can be recognized by comparing the time taken for the driving of the elevator.

FIG. 5 is a graph illustrating a time classifying a time taken depending on the number of layers when an elevator to which a floor driving information recognition system of an elevator camera using an atmospheric pressure and acceleration sensor according to an embodiment of the present invention is applied moves several layers FIG. That is, FIG. 5 is a graph that classifies the time taken depending on the number of layer movements when the elevator moves on several layers. In the graph of gravity acceleration, it is seen that the maximum rise and the maximum fall values of the graph are almost constant when the lift is moved have. On the basis of this, when the elevator ascends, the time starts to be measured on the assumption that the acceleration of the gravity starts to increase when the acceleration exceeds a certain value, and the time measurement is terminated assuming that the gravity acceleration has arrived below the predetermined value. In the case of falling, the measurement is performed in reverse to the rising time. When the time is measured, the layer movement time graph is displayed. It is possible to know how many layers have moved due to the number of layer movements.

FIG. 6 is a graph showing the data obtained by correcting the data of the atmospheric pressure using the temperature of the elevator to which the floor driving information recognition system of the elevator camera using the atmospheric pressure and acceleration sensor according to the embodiment of the present invention is applied, Fig. 6 is a graph showing atmospheric pressure data obtained by correcting the atmospheric pressure data using a temperature sensor. In the case of the gravity acceleration graph of FIG. 5, the operation direction of the elevator and the number of layers and the number of floors can be directly calculated and compared. However, in the case of the atmospheric pressure graph of FIG. 6, In the case of the layer and the number of layers, since the layers are separated at regular intervals, they can be easily compared without calculation. However, in the case of obtaining the number of layers based on the atmospheric pressure, since the value of the atmospheric pressure changes with time, the layer data obtained by using the acceleration and the layer data obtained by the atmospheric pressure are compared and used.

7 is a flowchart illustrating a process of classifying and storing layer movement time in a deep learning processing unit of an IP camera applied to a layer driving information recognition system of an elevator camera using an atmospheric pressure and acceleration sensor according to an embodiment of the present invention to be. FIG. 7 shows a flow of a process of classifying and storing layer movement time in the deep-learning processing unit 130. FIG. In the case of the list, the number is determined by the uppermost layer and the lowermost layer information transmitted from the user environment setting unit 203 of the client 200 to the deep learning processing unit 130 of the IP camera 100, So that it can be stored. After the time taken to move the layer using the gravitational acceleration is generated, it is checked whether the list to be stored is empty (S300). If the list is empty, the time taken to move the layer created in the list is inserted (S310). If the list is filled with something, the time taken to move the created layer is set to -1, which is the minimum time (S320), which is greater than or equal to +1 of the maximum time of the time taken to move the floor. At this time, as a result of the comparison (S320), it is checked whether the time taken for the layer movement classified in the corresponding list and the time taken for the generated layer movement are the same number of layer movements. The hanging time is again compared (S330) whether it is larger than -2 of the average time of the layer movement in the list and smaller than +2 of the average time of the floor movement. At this time, in the case of the comparison (S330), if the time taken to move the generated layer falls within the applicable range, a time for moving the layer is inserted in the list (S340). In addition, after inserting data into the list (S310, S340), it is determined whether there is more than one data in the list (S350), and the minimum value of the list in the minimum time of the layer shift, the maximum value of the list in the maximum time of the layer shift, The average value of the list is added to the average time, and the updated time is updated to a value including the time taken to move the created layer (S360). If it is not included in the corresponding range in step S320, it is determined whether the difference between the time taken to move the previous layer and the time taken to move the created layer is greater than -1.5 and smaller than 1.5 (S370) It is determined that it is not the list in which the time taken for moving the new layer is to be moved, and it is moved to the next list (S380), and the comparison is made whether the list is empty (S300). If it is not included in the corresponding range of the comparison (S330, S350, S370), the time data on the floor movement is recognized as invalid data to be stored in the list, and the time taken for the floor movement is newly received and stored repeatedly.

As described above, according to the floor driving information recognition system of the elevator camera using the atmospheric pressure and acceleration sensor according to the embodiment of the present invention, the IP camera installed in the elevator and capturing an image is provided. The present invention provides a system in which an atmospheric pressure and an acceleration sensor are incorporated so that floor driving information is separated from inside a camera and a separate floor measuring device is not installed.

The present invention may be embodied in many other specific forms without departing from the spirit or essential characteristics of the invention.

100: IP camera
110: camera image receiving unit
120: Sensor processor
121: Atmospheric pressure / temperature sensor
122: Accelerometer
130: Deep learning processing unit
140: OSD processing section
150: OSD image generating unit
160: RTSP meta data generation unit
170: RTSP metadata transmission unit
200: Client
201: Mobile client
202: Web client
203: User environment setting section
204: image display and data processing unit

Claims (8)

A floor operating information recognition system of an elevator camera using an atmospheric pressure and an acceleration sensor,
The information on the operating floor of the elevator is acquired based on the atmospheric pressure, the temperature, and the acceleration detected from the built-in sensor and the information of the lowest floor and the highest floor of the building in which the elevator is installed. An IP camera 100 for converting the obtained transport layer information of the elevator into an RTSP (real-time streaming protocol) method and transmitting the transport layer information; And
The photographed image converted from the IP camera 100 and the operating layer information of the elevator are received, and the photographed image and the layer data are distinguished from each other and displayed on the screen. The lowest layer and the highest layer information To the IP camera (100), wherein the client (200)
The IP camera (100)
A camera image receiving unit 110 for converting an analog image captured inside the elevator into a digital image;
Temperature sensor 121 and an acceleration sensor 122 for measuring the acceleration of the atmospheric pressure / temperature sensor 121 and the acceleration sensor 122. The atmospheric pressure / temperature sensor 121 measures the atmospheric pressure and the temperature, And a sensor processing unit 120 for performing an arithmetic process of calculating a traveling direction of the elevator and a time taken to move the floor measured by the gravitational acceleration and the gravitational acceleration according to the installation inclination of the camera using the measurement acceleration );
A deep processing unit 130 for classifying the time taken for the layer movement of the sensor processing unit 120 according to the number of moving layers, calculating the layer data using the number of moving layers, and correcting the layer data by comparing with the previously stored atmospheric pressure;
An OSD processing unit 140 for transmitting OSD setting data in which layer data outputted from the deep learning processing unit 130 is set as an OSD (On Screen Display) position and an OSD character;
An OSD image generation unit 150 for superimposing the digital image of the camera image receiving unit 110 and the OSD setting data of the OSD processing unit 140 and generating and transmitting an OSD image;
An RTSP metadata generation unit 160 for converting the analyzed layer data and sensor data received from the deep learning processing unit 130 and the OSD image received from the OSD image generation unit 150 into RTSP metadata and transmitting the converted RTSP metadata; And
And an RTSP metadata transmitting unit 170 for transmitting the converted RTSP metadata received from the RTSP metadata generating unit 160 to the client 200. Floor operating information recognition system of elevator camera.
delete The apparatus according to claim 1, wherein the sensor processing unit (120)
The atmospheric pressure / temperature sensor 121, the atmospheric pressure / temperature sensor 121, the atmospheric pressure / temperature sensor 121, the atmospheric pressure / temperature sensor 121, Floor operating information recognition system of elevator camera.
4. The apparatus of claim 3, wherein the sensor processing unit (120)
Wherein the gravity acceleration is calculated using the accelerations of the three axes detected by the acceleration sensor (122), and the traveling direction of the elevator and the time taken to move the layer are measured using the calculated gravity acceleration A layered information recognition system for elevator camera using.
The apparatus according to claim 3 or 4, wherein the deep learning processor (130)
The method according to any one of claims 1 to 3, wherein the step of classifying and storing the time data taken at the time of layer movement calculated from the sensor processing unit (120) according to the number of moved layers accumulates the deep learning data Information-aware system.
6. The apparatus of claim 5, wherein the deep-learning processor (130)
The accumulated information of the deep running data classified by storing the time data of the layer movement is compared with the time data of the newly created layer moved by the sensor processing unit 120 to calculate how many layers have been moved, Wherein the floor driving information recognition system of the elevator camera using the atmospheric pressure and the acceleration sensor.
7. The apparatus of claim 6, wherein the deep-learning processor (130)
The layer data is corrected by calculating the pressure at the time of the layer movement and comparing with the previously stored layered atmospheric pressure data to determine how many layers have been moved and then comparing the time data with the time data at the time of layer movement to determine whether they are the same. , Floor operating information recognition system of elevator camera using atmospheric pressure and acceleration sensor.
6. The method of claim 5, wherein the client (200)
A user setting unit 203 for setting camera settings and information of the lowest layer and the highest layer of the elevator and transmitting the set information to the deep learning processing unit 130 of the IP camera 100; And
And an image display and data processing unit 204 for classifying the RTSP metadata received from the RTSP metadata transmitting unit 170 of the IP camera 100 and displaying image data and sensor data on the screen,
The client (200)
The mobile client 201 and the web client 202 including the user environment setting unit 203 and the image display and data processing unit 204 are provided on the floor of the elevator camera using the atmospheric pressure and the acceleration sensor. Driving information recognition system.

Images