Elevator camera monitoring method

Abstract

The present invention proposes an elevator camera monitoring method, comprising: obtaining temperature compensation through temperature detection, and then correcting the air pressure value corresponding to the floor information; positioning an image acquisition device according to the air pressure value, and tracking and locating a target object according to the image information acquired by the image acquisition device; wherein the image acquisition device integrates a temperature detection module and an air pressure detection module; the present invention can effectively improve the monitoring efficiency of sensitive personnel.

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring, and in particular to an elevator camera monitoring method. Background Art

[0002] Traditional elevator monitoring relies on manual viewing of elevator monitoring cameras to determine the operation status of the elevator. Monitoring personnel need to stare at the screen all the time, which is time-consuming and laborious. Traditional elevator monitoring systems currently support video monitoring, face detection, volume detection, etc., which are obtained through cameras and audio collectors. Elevator boxes have built-in sensors, such as smoke monitoring sensors, gravity sensors for overweight detection in elevator security inspections, infrared sensors for elevator door detection of people entering and exiting, and magnetic strip sensors for determining floors.

[0003] However, the prior art often has the following problems:

[0004] The camera cannot flexibly combine special sensors according to different scenarios and cannot be replaced at any time. The sensor module in the elevator shell is not combined with the surveillance camera and cannot share the perceived floor information. This is mainly due to poor compatibility, too many elevator manufacturers, a large number of technical barriers, and high cost for unified elevator sensor module transformation, which is not easy to promote.

[0005] The camera cannot sense which floor it is on by itself, and cannot locate the movement of sensitive personnel within the building.

[0006] The existing elevator monitoring system is generally used for safe operation and maintenance, fault status, etc. It only pays attention to the movement of special personnel between floors when an abnormality occurs. It can only be discovered manually and does not have real-time monitoring and tracking of sensitive personnel on multiple floors.

[0007] When judging the vertical elevator floor, the multi-axis acceleration sensor has large errors, complex compensation algorithms, calculation delays, and low accuracy when locating the floor.

[0008] The sensor information and real-time monitoring video are transmitted to the back-end for unified analysis, which greatly increases the amount of computing power on the back-end. As the computing power of the front-end camera motherboard becomes more and more powerful, the computing load on the back-end server should be reduced.

[0009] In indoor security monitoring of high-rise buildings, when sensitive personnel enter the elevator, the back-end monitoring system does not know their trajectory in and out of the elevator, so it can only call up a large number of camera surveillance videos on each floor to search for the personnel, which has a very high computing cost. Summary of the invention

[0010] In view of the above problems existing in the prior art, the present invention proposes an elevator camera monitoring method, which mainly solves the problem of low efficiency of behavior monitoring.

[0011] In order to achieve the above purpose and other purposes, the technical solution adopted by the present invention is as follows.

[0012] An elevator camera monitoring method, comprising:

[0013] Obtain temperature compensation through temperature detection, and then correct the air pressure value corresponding to the floor information;

[0014] The image acquisition device is positioned according to the air pressure value, and the target object is tracked and positioned according to the image information acquired by the image acquisition device; wherein the image acquisition device integrates a temperature detection module and an air pressure detection module.

[0015] Optionally,

[0016] Detect changes in the elevator car air pressure value;

[0017] When the time for which the cabin air pressure value remains unchanged exceeds a set time threshold, images related to the floors in the cabin are collected to obtain floor information;

[0018] The real-time detected car air pressure value is compared with the preset air pressure value corresponding to the floor information to calibrate the air pressure detection module.

[0019] Optionally,

[0020] When the target object leaves the elevator car, identifying a movement trajectory of the target object;

[0021] According to the current air pressure value of the car and the motion trajectory, multiple image acquisition devices on the same floor are triggered to acquire images of the target object.

[0022] Optionally,

[0023] Set temperature thresholds;

[0024] When the detected temperature exceeds the temperature threshold, the floor height corresponding to the current air pressure value is obtained through temperature compensation, and then the floor positioning is performed.

[0025] Optionally,

[0026] Collecting identification features of people entering the car, identifying the identification features to obtain the target object;

[0027] The car acceleration value is collected to obtain the motion state of the car and then the motion state of the target object.

[0028] Optionally, the movement status includes upward, downward, and docked.

[0029] Optionally, after acquiring the target object, the location of the target object is acquired, and an alarm signal is triggered, and the target object and location information are sent to a server.

[0030] Optionally, the temperature detection module and the air pressure detection module transmit the collected information to the image acquisition device via a serial bus interface respectively.

[0031] Optionally, the image acquisition device establishes a connection with the other image acquisition devices in a wireless manner, and calibrates the floor information of the corresponding image acquisition device by the air pressure value of the other image acquisition device.

[0032] Optionally,

[0033] Detecting the air pressure value when the car is parked;

[0034] The image acquisition device in the car communicates with the image acquisition device on the adjacent floor to obtain the air pressure value of the adjacent image acquisition device, and compares the air pressure values ​​to determine whether the operation status of the car is normal.

[0035] As described above, the elevator camera monitoring method of the present invention has the following beneficial effects.

[0036] By combining temperature detection and air pressure monitoring to correct the elevator air pressure value in real time, the elevator's operating status can be accurately controlled in real time; by positioning the image acquisition device through the air pressure value, multiple image acquisition devices can be coordinated to track and locate the target object, thereby improving monitoring efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 The figure is a flow chart of an elevator camera monitoring method in one embodiment of the present invention. DETAILED DESCRIPTION

[0038] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0039] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0040] See also Figure 1 The present invention provides an elevator camera monitoring method, comprising steps S01-S02.

[0041] In step S01, temperature compensation is obtained through temperature detection, and then the air pressure value corresponding to the floor information is corrected:

[0042] In one embodiment, a temperature sensor may be used to detect temperature and obtain real-time temperature changes. A pressure sensor may be used to obtain air pressure values. The pressure sensor is sensitive to temperature changes. The temperature difference caused by seasonal changes can easily cause the pressure sensor to drift, affecting the accuracy. It is usually necessary to manually calibrate the pressure sensor regularly, which is not conducive to operation. In order to solve this problem, the present solution performs temperature compensation on the pressure sensor through a temperature sensor. The pressure sensor may be a silicon piezoresistive sensor. The temperature sensor is placed close to the silicon piezoresistive sensor to detect the temperature changes of the environment around the pressure sensor in real time. When the temperature is abnormal, the temperature compensation is output to ensure that the pressure sensor works in a relatively stable temperature environment. Specifically, a temperature threshold may be set. When the temperature detected by the temperature sensor exceeds the temperature threshold, the temperature compensation value is calculated to adjust the working environment temperature of the pressure sensor in real time.

[0043] In step S02, the image acquisition device is positioned according to the air pressure value, and the target object is tracked and positioned according to the image information acquired by the image acquisition device; wherein the image acquisition device integrates a temperature detection module and an air pressure detection module.

[0044] In one embodiment, the image acquisition device includes a camera, a mainboard, and sensor modules integrated on the mainboard. The mainboard is provided with a wireless bus and a pluggable serial bus interface. The sensor module can be integrated on the mainboard via the serial bus interface, and can be easily replaced at any time when a problem occurs. Each sensor module shares data with the camera via the mainboard. The sensor module may include an air pressure sensor, a temperature sensor, etc.

[0045] The mainboard can be connected to the server side via wired or wireless means, and obtain the calculation unit matched with the sensor component from the server side. Taking the air pressure sensor and temperature sensor as an example, the calculation unit can use the algorithm of the sensor and temperature compensation mode to calculate the temperature compensation value according to the temperature change value, so as to ensure that the air pressure sensor can calculate the accurate floor information according to the detected air pressure value.

[0046] In one embodiment, a plurality of serial bus interfaces may be provided on the serial bus of the mainboard for connecting a plurality of sensors, and the sensor modules may be combined at will according to the environmental requirements.

[0047] In one embodiment, the image acquisition device can be set in the elevator car, or installed in the corridor of the floor, etc. The tracking and positioning of the target object can be achieved by coordinating the image acquisition device in the car with the image acquisition devices in other locations on the floor.

[0048] Specifically, the air pressure sensor installed on the corresponding image acquisition device in the car can detect the change of air pressure in real time during the movement of the car. The current height of the car is calculated according to the air pressure value, and the height of the car is compared with the floor height to determine the floor or position of the current car. The parking state of the car can also be determined by detecting the air pressure value. When the air pressure value obtained by the air pressure sensor remains unchanged within a preset time, it is determined that the current car is in a docked state. The air pressure sensor sends the car state to the camera, and the camera collects image information in the car.

[0049] In one embodiment, the floor image displayed on the display panel in the car can be collected by a camera, and the numbers in the image can be identified to obtain the current floor information. The air pressure value corresponding to the floor can be preset for different floor information according to the actual environment. According to the recognition result, the preset air pressure value corresponding to the stop floor information is compared with the air pressure value detected in real time by the air pressure sensor in the car, and the air pressure sensor is calibrated according to the comparison result to improve the detection accuracy of the air pressure sensor. The preset air pressure value corresponding to the floor information can be measured manually regularly to correct the changes in air pressure value caused by seasonal changes. The air pressure value corresponding to the floor can also be collected in real time by an image acquisition device set in the corridor of the corresponding floor, and the preset air pressure value can be updated in real time.

[0050] In one embodiment, when the temperature of a certain floor or several consecutive floors has a large temperature difference with the adjacent floors, a temperature threshold can be set, and the real-time temperature is detected by a temperature sensor. When the temperature exceeds the set temperature threshold, the temperature compensation value is calculated, the temperature compensation is performed on the air pressure sensor, and the floor height corresponding to the air pressure value detected by the current air pressure sensor is calculated in real time. The floor positioning is performed according to the floor height to avoid the real-time temperature difference during the operation of the elevator affecting the floor positioning.

[0051] In one embodiment, the identification features of the person entering the car can be collected in real time by the image acquisition device in the car, and the real-time collected identification features can be sent to the server for feature recognition. The identification features include facial features, clothing features, gender, height, etc. The server can obtain the feature information of the suspicious person from the specified database, compare the feature information of the suspicious person with the real-time feature information collected by the camera, and identify the suspicious person in the car.

[0052] In one embodiment, a feature recognition model can also be integrated on the mainboard, and the camera directly sends the collected image information to the corresponding recognition model on the mainboard. The mainboard can obtain the feature information of suspicious persons stored in the database from the server side through wireless communication to identify the identity of the suspicious persons. The feature recognition model can be obtained through conventional deep neural network algorithm training. For example, images of people in the car at different times can be obtained in advance, and the image information can be organized into a training sample set. The initial training model is created by constructing an objective function through a deep neural network, and multiple personnel features are manually labeled to create a training target set. The training sample set is input into the initial training model for model training, and finally the feature recognition model is obtained.

[0053] In one embodiment, a gravity sensor may also be provided in the car, and the acceleration value of the car is detected by the gravity sensor, and the motion state of the car is determined according to the acceleration value. The motion state includes upward, downward, and docked. When the upward acceleration of the car is detected, it can be determined that the car is in an upward state, and when the downward acceleration of the car is detected, it can be determined that the car is in a downward state; when the acceleration of the car remains zero within a preset time period, it can be determined that the car is in a docked state. When the target object is identified to enter the car, the image acquisition device can be connected to the gravity sensor wirelessly to obtain the acceleration value detected by the gravity sensor, and load the calculation unit corresponding to the gravity acceleration from the server side, and determine the motion state of the car through the calculation unit, and then determine whether the target object is going up or down, and obtain the motion state of the suspicious person, so as to facilitate target tracking.

[0054] In one embodiment, when a suspicious person is identified, the image acquisition device can send out an alarm signal and, combined with the data from multiple sensor modules, send the location information of the suspicious person to the server via wired or wireless means to notify relevant management personnel so that a response strategy can be formulated based on the suspicious person's behavior.

[0055] In one embodiment, a gyroscope may be installed in the car. When a suspicious person is determined to have entered the car, the image acquisition device reads the gyroscope information and can roughly calculate the distance between the suspicious person and the person being tracked based on the height value and pitch angle. The camera can be used to increase the positioning accuracy of the suspicious person.

[0056] In one embodiment, when a suspicious person leaves the car, the camera can be used to collect feature information of the suspicious person and predict the movement trajectory of the suspicious person. For example, if the camera obtains an image of the suspicious person turning to the left, it can be combined with several consecutive frames of images to determine whether the suspicious person turns left or right after leaving the car.

[0057] In one embodiment, the images captured by the camera in the car can also be recognized in real time, specifically the behavior of people riding the elevator, such as pickpocketing and other bad behaviors, the characteristic information of suspicious persons can be recorded, and the suspicious persons can be tracked and located.

[0058] When the suspicious person leaves the car and turns right, the image acquisition device in the car identifies the current floor information, and then triggers the image acquisition device on the corresponding floor through wireless communication. Since the image acquisition device set up in the floor corridor and other locations is integrated with an air pressure sensor, the image acquisition device can autonomously identify the floor it is on through the air pressure sensor. The image acquisition device in the car can be directly connected to other image acquisition devices on the corresponding floor, and based on the movement trajectory of the suspicious person when leaving the car, the behavior trajectory of the suspicious person on the corresponding floor can be continuously tracked.

[0059] In summary, the present invention provides an elevator video monitoring method, which collects sensor information and senses the floor position of the elevator through the built-in or external sensor module of the camera, and then coordinates multiple camera modules to improve the monitoring efficiency of sensitive personnel; the sensor can be replaced and plugged in at any time, which solves the compatibility problem of elevator manufacturers' products; the movement trajectory of sensitive personnel can be quickly marked through the front-end elevator camera, reducing the amount of calculation on the server side; the air pressure sensor and temperature sensor can output stable air pressure values ​​at different heights, with small errors and high precision. Therefore, the present invention effectively overcomes the various shortcomings of the prior art and has a high industrial utilization value.

[0060] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. An elevator camera monitoring method, characterized in that: include: Obtain temperature compensation through temperature detection, and then correct the air pressure value corresponding to the floor information; Positioning an image acquisition device according to the air pressure value, and tracking and locating a target object according to the image information acquired by the image acquisition device; wherein the image acquisition device integrates a temperature detection module and an air pressure detection module; When the target object leaves the elevator car, identifying a movement trajectory of the target object; According to the current air pressure value of the car and the motion trajectory, multiple image acquisition devices on the same floor are triggered to acquire images of the target object.

2. The elevator video monitoring method according to claim 1, characterized in that: Detect changes in the elevator car air pressure value; When the time for which the cabin air pressure value remains unchanged exceeds a set time threshold, images related to the floors in the cabin are collected to obtain floor information; The real-time detected car air pressure value is compared with the preset air pressure value corresponding to the floor information to calibrate the air pressure detection module.

3. The elevator video monitoring method according to claim 1, characterized in that: Set temperature thresholds; When the detected temperature exceeds the temperature threshold, the floor height corresponding to the current air pressure value is obtained through temperature compensation, and then the floor positioning is performed.

4. The elevator video monitoring method according to claim 2, characterized in that: Collecting identification features of people entering the car, identifying the identification features to obtain the target object; The car acceleration value is collected to obtain the motion state of the car and then the motion state of the target object.

5. The elevator video monitoring method according to claim 4, characterized in that: The movement states include upward, downward, and docked.

6. The elevator video monitoring method according to claim 4, characterized in that: After acquiring the target object, the location of the target object is acquired, and an alarm signal is triggered, and the target object and location information are sent to the server.

7. The elevator video monitoring method according to claim 1, characterized in that: The temperature detection module and the air pressure detection module transmit the collected information to the image acquisition device through a serial bus interface or wireless communication.

8. The elevator video monitoring method according to claim 1, characterized in that: The image acquisition device establishes connection with other image acquisition devices in a wireless manner, and calibrates the floor information of the corresponding image acquisition device through the air pressure value of other image acquisition devices.

9. The elevator video monitoring method according to claim 8, characterized in that: Detecting the air pressure value when the car is parked; The image acquisition device in the car communicates with the image acquisition device on the adjacent floor to obtain the air pressure value of the adjacent image acquisition device, and compares the air pressure values ​​to determine whether the operation status of the car is normal.

Images