Elevator taking safety monitoring method, device, equipment and medium

Abstract

The invention discloses an elevator taking safety monitoring method, device and equipment and a medium, and the method comprises the steps: judging whether an infrared monitoring signal meets a safety monitoring condition or not, if yes, obtaining an image set collected by image collection equipment, and intercepting a monitoring image in the image set to obtain an intercepted image, and performing individual identification on the intercepted image to obtain individual feature information, and performing safety detection to obtain a detection result that whether the personnel take the elevator safely or not. According to the elevator taking safety monitoring method, whether a person enters the elevator to take the elevator or not is judged through the infrared monitoring signals, so that the image set when the person takes the elevator is obtained in a targeted mode, individual recognition and safety detection are conducted, and the taking condition of each elevator does not need to be monitored one by one; according to the technical method, intelligent monitoring on whether the personnel take the elevator safely or not is achieved, and the efficiency and accuracy of safety monitoring on elevator taking are greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring technology, and in particular to an elevator riding safety monitoring method, device, equipment and medium. Background Art

[0002] Due to the large internal area of ​​nuclear power plants, escalators need to be installed to improve the efficiency of operators reaching various nuclear power equipment; however, some operators do not ride the escalator according to the specifications, which can easily cause safety accidents. In the prior art, monitoring personnel usually view the elevator monitoring images in the monitor to identify whether there are operators who illegally ride the escalator; however, due to the large number of elevators, this identification method cannot only judge whether people enter the elevator range, and the monitoring personnel cannot fully view each monitoring screen at the same time, resulting in low recognition efficiency. Therefore, the prior art method cannot efficiently monitor and identify people riding elevators in nuclear power plants. Summary of the invention

[0003] The embodiments of the present invention provide an elevator riding safety monitoring method, device, equipment and medium, aiming to solve the problem in the prior art that people riding elevators in nuclear power plants cannot be efficiently monitored and identified.

[0004] In a first aspect, an embodiment of the present invention provides an elevator riding safety monitoring method, wherein the method is applied to a management server, the management server establishes a network connection with an image acquisition device and an infrared sensor arranged at an escalator entrance to realize data information transmission, the image acquisition device is arranged toward the escalator, and the method comprises:

[0005] Determining whether the infrared monitoring signal from the infrared sensor meets the preset safety monitoring conditions;

[0006] If the infrared monitoring signal meets the safety monitoring condition, a set of images collected is obtained from the image acquisition device according to a preset acquisition strategy; the image set includes a plurality of monitoring images;

[0007] Intercepting the monitoring image in the image set according to a preset image interception strategy to obtain a corresponding intercepted image;

[0008] Performing individual identification on the captured images according to a preset individual identification model to obtain individual feature information corresponding to the image set;

[0009] A security check is performed on the individual feature information of the image set according to a preset security check rule to obtain a security check result.

[0010] Second aspect, an elevator ride safety monitoring device is further provided in an embodiment of the present invention. The device is configured in a management server, and the management server establishes a network connection with an image acquisition device and an infrared sensor arranged at the entrance of an escalator to realize the transmission of data information. The image acquisition device is arranged facing the escalator. The device is used to execute the elevator ride safety monitoring method as described in the first aspect above. The device includes:

[0011] A detection signal judgment unit, configured to judge whether an infrared monitoring signal from the infrared sensor meets a preset safety monitoring condition;

[0012] An image set acquisition unit, configured to, if the infrared monitoring signal meets the safety monitoring condition, acquire an acquired image set from the image acquisition device according to a preset acquisition strategy; the image set includes multiple monitoring images;

[0013] An intercepted image acquisition unit, configured to intercept the monitoring images in the image set according to a preset image interception strategy to obtain corresponding intercepted images;

[0014] An individual feature information acquisition unit, configured to respectively perform individual recognition on the intercepted images according to a preset individual recognition model to obtain individual feature information corresponding to the image set;

[0015] A detection result acquisition unit, configured to perform a safety detection on the individual feature information of the image set according to a preset safety detection rule to obtain a detection result of whether it is safe.

[0016] Third aspect, an embodiment of the present invention further provides a computer device. The device includes a processor, a communication interface, a memory, and a communication bus. The processor, the communication interface, and the memory complete communication with each other through the communication bus;

[0017] The memory is used to store a computer program;

[0018] The processor, when executing the program stored in the memory, implements the steps of the elevator ride safety monitoring method as described in the first aspect above.

[0019] Fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. The computer program, when executed by a processor, implements the steps of the elevator ride safety monitoring method as described in the first aspect above.

[0020] An embodiment of the present invention provides a method, device, equipment and medium for monitoring the safety of elevator rides. The method includes: judging whether an infrared monitoring signal meets the safety monitoring conditions. If it meets, obtain the image set collected by the image acquisition device and intercept the intercepted image from the monitoring images therein, perform individual recognition on the intercepted image to obtain individual feature information and perform safety detection to obtain the detection result of whether a person is safe when taking the elevator. The above-mentioned method for monitoring the safety of elevator rides first judges whether there are people entering the elevator to take a ride through the infrared monitoring signal, so as to specifically obtain the image set when people take the elevator and perform individual recognition and safety detection, without monitoring the ride situation of each elevator one by one; the above technical method realizes the intelligent monitoring of whether people take the elevator safely, and greatly improves the efficiency and accuracy of safety monitoring of elevator rides. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1 It is a flowchart of the method for monitoring the safety of elevator rides provided by the embodiment of the present invention;

[0023] Figure 2 It is a schematic diagram of the application scenario of the method for monitoring the safety of elevator rides provided by the embodiment of the present invention;

[0024] Figure 3 It is a schematic block diagram of the device for monitoring the safety of elevator rides provided by the embodiment of the present invention;

[0025] Figure 4 It is a schematic block diagram of the computer equipment provided by the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0027] It should be understood that when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0028] It should also be understood that the terms used in the specification of the present invention are for the purpose of describing particular embodiments only and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly dictates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0029] It should be further understood that the term "and / or" used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0030] Embodiments of the present invention application provide an elevator ride safety monitoring method, which is applied to the management server 10. The management server 10 executes the stored software program to implement the above elevator ride safety monitoring method; the management server 10 may be a server side configured in the machine room of a nuclear power plant for intelligently monitoring whether personnel safely take the elevator. The management server 10 may be a server device such as a cluster server or a parallel processing server. Please refer to Figure 2 , as shown in the figure, the management server 10 establishes a network connection with an image acquisition device 20, an alarm 40 and an infrared sensor 31 arranged at the entrance of the escalator 30 to realize the transmission of data information. The image acquisition device 20 is arranged facing the escalator 30. Among them, the infrared sensor 31 is also a sensor for detecting whether an object enters the elevator. The infrared sensor 31 includes a transmitter and a receiver. The transmitter emits infrared rays so that the receiver receives an infrared signal. If an object is located between the transmitter and the receiver, the infrared signal is blocked, and the receiver can sense whether the infrared signal is blocked. The image acquisition device 20 is also a device for visible light imaging of the escalator area in the nuclear power plant, such as a camera. The alarm 40 is also a device configured in each escalator area of the nuclear power plant for alarm prompts, such as a loudspeaker. There are multiple escalators in the nuclear power plant, and each escalator is correspondingly equipped with an infrared sensor 31, an image acquisition device 20 and an alarm 40.

[0031] As Figure 1 shown, the method includes steps S110 to S150.

[0032] S110. Judge whether the infrared monitoring signal from the infrared sensor meets the preset safety monitoring conditions.

[0033] Judge whether the infrared monitoring signal from the infrared sensor meets the preset safety monitoring conditions. The management server can obtain the infrared monitoring signals detected by each infrared sensor, and judge each infrared monitoring signal separately. If the infrared monitoring signal meets the safety monitoring conditions, further obtain the image of the escalator area corresponding to the infrared sensor for safety detection; if the infrared monitoring signal does not meet the safety monitoring conditions, there is no need to further perform safety detection on the image of the corresponding escalator area, thereby reducing the number of images for safety detection and improving the safety detection efficiency.

[0034] In a specific embodiment, step S110 includes sub-steps: judge whether the infrared monitoring signal has a signal interruption; if the infrared monitoring signal has a signal interruption, judge whether the signal interruption duration is greater than the preset duration in the safety monitoring conditions; if the signal interruption duration is greater than the preset duration, determine that the infrared monitoring signal meets the safety monitoring conditions; if the infrared monitoring signal does not have a signal interruption or the signal interruption duration is not greater than the preset duration, determine that the infrared monitoring signal does not meet the safety monitoring conditions.

[0035] Specifically, it can be judged whether the infrared monitoring signal is interrupted. If it is interrupted, it indicates that an object is blocking the infrared sensor; further obtain the duration of the interruption and judge whether the signal interruption duration is greater than the preset duration in the safety monitoring conditions. Since a person entering the elevator entrance will surely block the infrared sensor for a period of time, for example, the preset duration can be set to 0.2S. If the signal interruption duration is greater than this preset duration, it indicates that at least one person has entered the elevator entrance, and it can be determined that the infrared monitoring signal meets the safety monitoring conditions.

[0036] If the infrared monitoring signal does not have a signal interruption, it indicates that no object is blocking the infrared sensor, and at this time it is determined that the infrared monitoring signal does not meet the safety monitoring conditions. If the signal interruption duration is not greater than the preset duration, it may be that a small object invades the infrared sensor or signal drift occurs due to unstable voltage signals. At this time, it can be determined that the infrared monitoring signal does not meet the safety monitoring conditions.

[0037] S120. If the infrared monitoring signal meets the safety monitoring conditions, obtain the image set collected from the image acquisition device according to the preset acquisition strategy; the image set includes multiple monitoring images.

[0038] If the infrared monitoring signal meets the safety monitoring condition, obtain the acquired image set from the image acquisition device according to the preset acquisition strategy; the image set includes multiple monitoring images. An infrared sensor is correspondingly arranged at the entrance of each escalator, and an image acquisition device is correspondingly arranged in the direction opposite to each escalator, so one infrared sensor corresponds to one image acquisition device. If the infrared monitoring signal meets the safety monitoring condition, the image acquisition device corresponding to the infrared sensor to which the infrared monitoring signal belongs can be correspondingly obtained, and the acquired image set can be obtained from the image acquisition device according to the acquisition strategy. Then each escalator to be safety-monitored corresponds to an image set.

[0039] Specifically, the management server can send the corresponding acquisition instruction to the image acquisition device corresponding to the infrared monitoring signal according to the acquisition strategy. The image acquisition device takes images correspondingly according to the received acquisition instruction, and combines the acquired monitoring images into an image set and feeds it back to the management server, then the management server correspondingly completes the acquisition of the image set. For example, the acquisition cycle time and the acquisition quantity can be correspondingly configured in the acquisition strategy. Then when the image acquisition device receives the acquisition instruction corresponding to the acquisition strategy, it acquires the monitoring images correspondingly according to the acquisition cycle time, and the interval time between two adjacent monitoring images is also equal to the acquisition cycle time, and the number of monitoring images included in an acquired image set is equal to the acquisition quantity.

[0040] Alternatively, the image acquisition device transmits the video picture to the management server in real time, and the management server correspondingly intercepts the corresponding monitoring images from the video picture to form an image set. When the management server intercepts the video picture, the interval time between the two intercepted monitoring images is also equal to the acquisition cycle time, and the number of monitoring images included in the acquired image set is also equal to the acquisition quantity.

[0041] S130. Intercept the monitoring images in the image set according to the preset image interception strategy to obtain the corresponding intercepted images.

[0042] Intercept the monitoring images in the image set according to the preset image interception strategy to obtain the corresponding intercepted images. The monitoring images in the image set can be intercepted according to the image interception strategy. In the specific embodiments of the present application, only the processing flow of one image set is described in detail. In actual application, multiple image sets can be processed respectively; intercepting the monitoring images in one image set can obtain the corresponding intercepted images.

[0043] In a specific embodiment, step S130 includes sub-steps: obtaining underlying pixels in the monitoring image that match the underlying image template of the image capture strategy; calculating a pixel difference coefficient between each pixel point in the monitoring image and the corresponding underlying pixel; obtaining pixel points in the monitoring image whose pixel difference coefficient is greater than the coefficient threshold in the image capture strategy as candidate pixel points; determining whether the connected area of each candidate pixel point is greater than the area threshold in the image capture strategy to obtain a corresponding area determination result; and cropping a combination of candidate pixel points with a connected area greater than the area threshold according to the area determination result to obtain a corresponding cropped image.

[0044] The image capture strategy is configured with an underlying image template corresponding to each image capture device. The underlying image template is the template corresponding to the underlying image captured when no one is riding on the escalator. The underlying image template contains the underlying image, and template information such as the elevator standing area and the elevator handrail area is also marked on the underlying image.

[0045] Obtain underlying pixels in the monitoring image that match the underlying image template. Each pixel point in the monitoring image corresponds to an image coordinate position. Since the image capture devices capture images of the elevator area in the same orientation, the pixels at the same image coordinate position on the underlying image in the underlying image template can be obtained as the corresponding underlying pixels according to the image coordinate position of the pixel point in the monitoring image. Then, each pixel point in the monitoring image can correspond to a determined underlying pixel.

[0046] Further calculate the pixel difference coefficient between each pixel point in the monitoring image and the corresponding underlying pixel. Specifically, the pixel value of a pixel point is composed of the values of three color channels: R (red), G (green), and B (blue). Then, the numerical differences of the three color channels can be calculated correspondingly and superimposed as the pixel difference coefficient. Specifically, the pixel difference coefficient can be obtained by using formula (1) for calculation:

[0047]

[0048] where R d is the value of the R color channel in the underlying pixel, R j is the value of the R color channel of the pixel point in the monitoring image, G d is the value of the G color channel in the underlying pixel, G j is the value of the G color channel of the pixel point in the monitoring image, B d is the value of the B color channel in the underlying pixel, B j is the value of the B color channel of the pixel point in the monitoring image. C is the calculated pixel difference coefficient. Then, each pixel point in the monitoring image can correspond to a calculated pixel difference coefficient.

[0049] Further, it is possible to determine whether the pixel difference coefficient of each pixel point in the monitoring image is greater than the coefficient threshold in the image capture strategy; and obtain the pixel points with a pixel difference coefficient greater than the coefficient threshold as candidate pixel points.

[0050] Further, it is possible to determine whether the candidate pixel points are connected. If there are other candidate pixel points in the peripheral area adjacent to a certain candidate pixel point, it is determined that the two candidate pixel points are connected; if there is at least one pixel point between the two candidate pixel points, it is determined that the two candidate pixel points are not connected. According to the above rules, the connected area of each candidate pixel point can be obtained, and the connected areas of the candidate pixel points in the same connected region are equal. Determine whether the connected area of the connected region formed by the candidate pixel points is greater than the area threshold in the image capture strategy to obtain the corresponding area judgment result. Then the area judgment results of all pixel points in the same connected region are also exactly the same. If the area judgment result is yes, the candidate pixel points in the connected region are correspondingly captured; if the area judgment result is no, the candidate pixel points in the connected region are discarded. Obtain the candidate pixel points with a connected area greater than the area threshold as the corresponding captured image. Then one monitoring image can correspond to one or more captured images.

[0051] S140. Respectively perform individual recognition on the captured images according to a preset individual recognition model to obtain individual feature information corresponding to the image set.

[0052] Respectively perform individual recognition on the captured images according to a preset individual recognition model to obtain individual feature information corresponding to the image set. The individual recognition model can recognize the individuals in the captured images to extract the individual features corresponding to each person from the captured images. Then the obtained individual feature information correspondingly includes the individual features of each captured image corresponding to the image set.

[0053] In a specific embodiment, step S140 includes sub-steps: nesting the captured images according to the human vector template in the individual recognition model to obtain a human image matching the human vector template; respectively extracting corresponding individual marking features from the human image according to the marking feature rules in the individual recognition model; generating individual marks corresponding to the individual marking features in each captured image; and extracting individual features corresponding to each individual mark from the captured images according to the individual feature extraction rules in the human recognition model as the individual feature information.

[0054] The individual recognition model is configured with a human body vector template. The intercepted image can be nested through the human body vector template, and the human body vector template can be scaled arbitrarily without deformation. If a certain area in the intercepted image matches the scaled human body vector template, the image of this area is intercepted as the human body image. The corresponding individual marking features are extracted from the human body image according to the marking feature rules configured in the individual recognition model. The individual marking features include the vertical height (i.e., the corresponding human height) between the upper vertex in the human body image and the elevator standing area of the bottom image template, the width of the human body image, the upper color of the human body image (the color of the safety helmet), the trunk color of the human body image (the middle and lower colors of the human body image, corresponding to the clothing color), and other information.

[0055] Furthermore, individual marks corresponding to each human marking feature in the intercepted image are generated. For example, the human marking feature can be combined with the current time to generate the corresponding individual mark. Each human body image corresponds to only one individual mark in the same time period. For example, the current time is 14:33 on March 10th, the vertical height of the human body image is 35 pixels, the width of the human body image is 8 pixels, the upper color (RGB) is [15, 33, 245], and the trunk color is [47, 50, 158]. Then the feature string "031014324-35-8-15-33-245-47-50-158" can be generated correspondingly, and the corresponding human mark "AAAA" is assigned, where "AAAA" is any letter.

[0056] To avoid time conflicts, the time 14:33 is extended to the range between 14:32 and 14:34, and thus recorded as "14324", that is, the last three digits correspond to the time period from 14:32 to 14:34. As long as it coincides with this time period, it is regarded as the same individual, that is, the same human mark is used for identification. Each digit in the feature string corresponds to a tolerance range, and those within the same tolerance range are considered to be the same individual. For example, a person is walking on the elevator, and the acquisition time of a certain intercepted image of him is 14:29, then the corresponding feature string is "031014280-34-8-15-32-245-47-48-158"; the acquisition time of a subsequent intercepted image of him is 14:30, and the corresponding feature string is "031014301-35-8-15-33-245-47-50-158". Since "14280" corresponds to the time period from 14:28 to 14:30, and "14301" corresponds to the time period from 14:30 to 14:31, there is a time intersection between the two; and the different digits in the feature string are all within the corresponding tolerance ranges, so it is considered that these two feature strings correspond to the same human mark.

[0057] After extracting the entire human body image from the intercepted image, it can be determined whether the intercepted image contains pixel information. If the intercepted image contains pixel information, the pixel information contained in the intercepted image can be analyzed through an analysis model based on a convolutional neural network. For example, the image composed of pixel information is subjected to convolutional processing by the analysis model, and the convolutional neural network of the analysis model outputs an analysis result indicating whether a person is included. If the obtained analysis result indicates that a person is included, individual marker features are also extracted from the image composed of the pixel information and individual markers are generated. If the analysis result indicates that no person is included, the image composed of the pixel information is discarded.

[0058] Furthermore, according to the individual feature extraction rules in the human body recognition model, individual features corresponding to each individual marker are extracted from the intercepted image, and the individual features corresponding to each individual marker are combined into individual feature information. Specifically, the individual feature extraction rules can be used to extract features from the human body images with the same individual marker. The individual feature extraction rules include multiple extraction items, and the corresponding values for each extraction item can be obtained separately and combined into individual features. Each individual marker corresponds to a set of values in each monitoring image. The extraction items in the individual feature extraction rules can include the vertex coordinate positions of the human body image, the central point coordinate positions of the human body image, and the palm coordinate positions on the side of the human body image. Therefore, the coordinate positions of the human body image in the corresponding monitoring image can be obtained according to each extraction item as the values corresponding to each feature item.

[0059] S150. Perform a security detection on the individual feature information of the image set according to the preset security detection rules to obtain a detection result indicating whether it is safe.

[0060] Perform a security detection on the individual feature information of the image set according to the preset security detection rules to obtain a detection result indicating whether it is safe. The security detection rules can be used to perform a security detection on the individual feature information included in the image set, so as to obtain a detection result indicating whether it is safe, that is, the detection result contains the detection information on whether all the people in the image set are safely riding the escalator.

[0061] In a specific embodiment, step S150 includes sub-steps: obtaining the movement characteristics of each individual marker in the adjacent monitoring images in the image set; determining whether the palm coordinate positions in each individual marker are located within the handrail coordinate area of the safety detection rule; determining whether the movement characteristics of each individual marker match the elevator operation parameters in the safety detection rule; if the palm coordinate positions of each individual marker are all located within the handrail coordinate area and the movement characteristics all match the elevator operation parameters, obtaining a safe detection result; if any one of the palm coordinate positions of the individual marker is not located within the handrail coordinate area or any one of the movement characteristics of the individual marker does not match the elevator operation parameters, obtaining an unsafe detection result.

[0062] Specifically, the movement characteristics corresponding to each individual marker in the adjacent monitoring images can be obtained. Specifically, the coordinate position differences of the same individual marker in two adjacent monitoring images can be obtained, and the movement characteristics can be calculated in sequence. For example, the vertex coordinate positions of the same individual marker in two adjacent monitoring images can be obtained, and the geometric distance between the vertex coordinate positions can be calculated. Dividing the geometric distance by the acquisition cycle time can obtain the vertex movement speed; obtaining the angle between the line connecting the subsequent vertex coordinate position and the previous vertex coordinate position and the horizontal line as the corresponding vertex movement direction. According to the above method, the vertex movement speed, vertex movement direction, center point movement speed, center point movement direction, palm movement speed, and palm movement direction of the individual marker in two adjacent monitoring images are calculated in sequence as the corresponding movement characteristics.

[0063] Further determine whether the palm coordinate positions in the individual marker are all located within the handrail coordinate area. The handrail coordinate area is also the coordinate range of the elevator handrail area in the bottom layer image template in the bottom layer image. If the palm coordinate position is located within the handrail coordinate area, it indicates that the position of the user's palm is placed at the elevator handrail; if the palm coordinate position is not located within the handrail coordinate area, it indicates that the position of the user's palm is not placed at the elevator handrail.

[0064] Determine whether the movement characteristics of each individual marker match the elevator operation parameters in the safety detection rule. The elevator operation parameters include the elevator operation speed and the elevator operation direction. Specifically, the difference coefficients between the palm movement speed, vertex movement speed, and center point movement speed in the movement characteristics and the elevator operation parameters can be calculated; the calculation process of the difference coefficient is shown in formula (2):

[0065]

[0066] where X is the calculated difference coefficient, e is the base of the natural logarithm, v d is the vertex movement speed, v z is the center point movement speed, v tis the elevator running speed, v s is the palm moving speed, ω is the angular difference between the palm moving direction and the center point moving direction, β is the angular difference between the vertex moving direction and the center point moving direction, and θ is the angular difference between the center point moving direction and the elevator running direction.

[0067] If the difference coefficient calculated based on a set of movement features meets the judgment condition in the safety detection rule: X ≤ X0 (X0 is the judgment threshold set in the judgment condition), it is obtained that the movement features of the individual label match the elevator operation parameters; if the above judgment condition in the safety detection rule is not met, it is obtained that the movement features of the individual label do not match the elevator operation parameters.

[0068] If the palm coordinate positions of each of the individual labels are all within the armrest coordinate area and the movement features of the individual labels all match the elevator operation parameters, a safe detection result is obtained; if any of the palm coordinate positions of the individual label is not within the armrest coordinate area or any of the movement features of the individual label does not match the elevator operation parameters, an unsafe detection result is obtained.

[0069] In a specific embodiment, after step S150, the following steps are further included: if the detection result is unsafe, the corresponding monitoring abnormal image is intercepted from the image set according to the detection result; the monitoring abnormal image is combined with the current time and the monitoring position information corresponding to the image acquisition device to generate the corresponding monitoring record information.

[0070] If the detection result is unsafe, the monitoring image to which the intercepted image whose palm coordinate position is not within the armrest coordinate area in the image set belongs is obtained according to the detection result as the corresponding monitoring abnormal image; or, the monitoring image to which the intercepted image whose movement features do not match the elevator operation parameters in the image set belongs is obtained according to the detection result as the corresponding monitoring abnormal image. That is, if the detection result is unsafe, one or more monitoring abnormal images can be obtained corresponding to the detection result.

[0071] In a specific embodiment, after step S150, the following steps are further included: if the detection result is unsafe, the monitoring prompt information is sent to the alarm for alarm prompt.

[0072] If the detection result is unsafe, the alarm in the area where the escalator is located corresponding to the detection result can be obtained, and the monitoring prompt information can be sent to the alarm corresponding to the detection result, so as to give an alarm prompt to the people taking the elevator through the alarm. One alarm is configured for each area where the escalator is located, and then, according to the corresponding relationship among the image acquisition device, the escalator and the alarm, the image acquisition device corresponding to the unsafe detection result can be determined, and further the alarm corresponding to the detection result can be determined. The monitoring prompt information can be voice prompt information, for example, the content is "Please hold the handrail firmly for the people taking the elevator".

[0073] In the elevator ride safety monitoring method disclosed in the above embodiment, the method includes: judging whether the infrared monitoring signal meets the safety monitoring conditions. If it meets, the image set collected by the image acquisition device is obtained, and the intercepted image is intercepted from the monitoring images therein. The intercepted image is subjected to individual recognition to obtain individual feature information and safety detection, so as to obtain the detection result of whether the person taking the elevator is safe. In the above elevator ride safety monitoring method, it is first judged whether there is a person entering the elevator to take a ride through the infrared monitoring signal, so as to specifically obtain the image set of the person taking the elevator and perform individual recognition and safety detection, without monitoring the ride situation of each elevator one by one; the above technical method realizes the intelligent monitoring of whether the person takes the elevator safely, and greatly improves the efficiency and accuracy of the safety monitoring of elevator rides.

[0074] An embodiment of the present invention further provides an elevator ride safety monitoring device, which can be configured in a management server and is used to execute any embodiment of the foregoing elevator ride safety monitoring method. Specifically, please refer to Figure 3 , Figure 3 which is a schematic block diagram of the elevator ride safety monitoring device provided by the embodiment of the present invention.

[0075] As Figure 3 shown, the elevator ride safety monitoring device 100 includes a detection signal judgment unit 110, an image set acquisition unit 120, an intercepted image acquisition unit 130, an individual feature information acquisition unit 140, and a detection result acquisition unit 150.

[0076] The detection signal judgment unit 110 is used to judge whether the infrared monitoring signal from the infrared sensor meets the preset safety monitoring conditions.

[0077] The image set acquisition unit 120 is used to, if the infrared monitoring signal meets the safety monitoring conditions, obtain the collected image set from the image acquisition device according to the preset acquisition strategy; the image set includes multiple monitoring images.

[0078] The intercepted image acquisition unit 130 is configured to intercept the monitoring images in the image set according to a preset image interception strategy to obtain corresponding intercepted images.

[0079] The individual feature information acquisition unit 140 is configured to perform individual recognition on the intercepted images respectively according to a preset individual recognition model to obtain individual feature information corresponding to the image set.

[0080] The detection result acquisition unit 150 is configured to perform a security detection on the individual feature information of the image set according to a preset security detection rule to obtain a detection result indicating whether it is safe.

[0081] In the elevator ride safety monitoring device provided by the embodiment of the present invention, the above elevator ride safety monitoring method is applied to judge whether the infrared monitoring signal meets the safety monitoring condition. If it meets, the image set collected by the image acquisition device is obtained, and the intercepted images are intercepted from the monitoring images therein. Individual recognition is performed on the intercepted images to obtain individual feature information and a security detection is performed to obtain a detection result indicating whether a person is safe when taking the elevator. In the above elevator ride safety monitoring method, it is first judged whether there is a person entering the elevator to take a ride through the infrared monitoring signal, so as to specifically obtain the image set when a person takes the elevator and perform individual recognition and security detection, without monitoring the ride situation of each elevator one by one; the above technical method realizes the intelligent monitoring of whether a person takes the elevator safely, and greatly improves the efficiency and accuracy of the safety monitoring of elevator rides.

[0082] The above elevator ride safety monitoring device can be implemented in the form of a computer program, and this computer program can run on a computer device as shown in Figure 4 shown.

[0083] Please refer to Figure 4 , Figure 4 which is a schematic block diagram of the computer device provided by the embodiment of the present invention. This computer device can be a management server for executing the elevator ride safety monitoring method to intelligently monitor whether a person takes the elevator safely.

[0084] Referring to Figure 4 , the computer device 500 includes a processor 502, a memory, and a communication interface 505 connected through a communication bus 501. Among them, the memory can include a storage medium 503 and an internal memory 504.

[0085] The storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 can be made to execute the elevator ride safety monitoring method. Among them, the storage medium 503 can be a volatile storage medium or a non-volatile storage medium.

[0086] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500.

[0087] The internal memory 504 provides an environment for the operation of the computer program 5032 in the storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can be caused to execute the elevator ride safety monitoring method.

[0088] The communication interface 505 is used for network communication, such as providing the transmission of data information, etc. Those skilled in the art can understand that Figure 4 the structure shown in is only a block diagram of some structures related to the solution of the present invention, and does not constitute a limitation on the computer device 500 to which the solution of the present invention is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0089] Among them, the processor 502 is used to run the computer program 5032 stored in the memory to implement the corresponding functions in the above elevator ride safety monitoring method.

[0090] Those skilled in the art can understand that Figure 4 the embodiments of the computer device shown in do not constitute a limitation on the specific composition of the computer device. In other embodiments, the computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements. For example, in some embodiments, the computer device may only include a memory and a processor. In such an embodiment, the structures and functions of the memory and the processor are the same as those in Figure 4 the shown embodiment and will not be elaborated here.

[0091] It should be understood that in the embodiments of the present invention, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0092] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium may be a volatile or non-volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps included in the above elevator ride safety monitoring method are implemented.

[0093] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described devices, apparatuses, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein. Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0094] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. Units with the same function can also be aggregated into a single unit. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed couplings or direct couplings or communication connections to each other can be indirect couplings or communication connections through some interfaces, devices, or units, or can be electrical, mechanical, or other forms of connection.

[0095] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present invention.

[0096] In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0097] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a computer-readable storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned computer-readable storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), magnetic disks, or optical discs that can store program codes.

[0098] As described above, the above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. An elevator ride safety monitoring method, characterized in that, The method is applied to a management server which establishes a network connection with an image acquisition device and an infrared sensor set at the entrance of an escalator to achieve data information transmission. The image acquisition device is arranged facing the escalator. The method includes: Judging whether an infrared monitoring signal from the infrared sensor meets a preset security monitoring condition; If the infrared monitoring signal meets the security monitoring condition, obtaining a set of acquired images from the image acquisition device according to a preset acquisition strategy; the set of images includes multiple monitoring images; Intercepting the monitoring images in the set of images according to a preset image intercepting strategy to obtain corresponding intercepted images; Individually identifying the intercepted images according to a preset individual recognition model to obtain individual feature information corresponding to the set of images; Performing a security detection on the individual feature information of the set of images according to a preset security detection rule to obtain a detection result of whether it is safe or not.

2. The elevator ride safety monitoring method according to claim 1, characterized in that, The judging whether an infrared monitoring signal from the infrared sensor meets a preset security monitoring condition includes: Judging whether the infrared monitoring signal has a signal interruption; If the infrared monitoring signal has a signal interruption, judging whether the signal interruption duration is greater than a preset duration in the security monitoring condition; If the signal interruption duration is greater than the preset duration, determining that the infrared monitoring signal meets the security monitoring condition; If the infrared monitoring signal does not have a signal interruption or the signal interruption duration is not greater than the preset duration, determining that the infrared monitoring signal does not meet the security monitoring condition.

3. The elevator ride safety monitoring method according to claim 2, wherein The intercepting the monitoring images in the set of images according to a preset image intercepting strategy to obtain corresponding intercepted images includes: Obtaining underlying pixels of each pixel point in the monitoring image that match a underlying image template of the image intercepting strategy; Calculating a pixel difference coefficient between each pixel point in the monitoring image and the corresponding underlying pixel; Obtaining pixel points in the monitoring image with a pixel difference coefficient greater than a coefficient threshold in the image intercepting strategy as alternative pixel points; Judging whether the connected area of each of the alternative pixel points is greater than an area threshold in the image intercepting strategy to obtain a corresponding area judgment result; Intercepting a combination of alternative pixel points with a connected area greater than the area threshold according to the area judgment result as the corresponding intercepted image.

4. The elevator ride safety monitoring method according to claim 2 or 3, characterized in that, The individually identifying the intercepted images according to a preset individual recognition model to obtain individual feature information corresponding to the set of images includes: Nesting the intercepted images according to a human body vector template in the individual recognition model to obtain a human body image that matches the human body vector template; Respectively extracting corresponding individual marking features from the human body image according to a marking feature rule in the individual recognition model; Generating individual marks corresponding to the individual marking features in each of the intercepted images; Extracting individual features corresponding to each of the individual marks from the intercepted images according to an individual feature extraction rule in the human body recognition model as the individual feature information.

5. The elevator ride safety monitoring method according to claim 2 or 3, characterized in that, Performing security detection on the individual feature information of the image set according to the preset security detection rules to obtain a detection result of whether it is safe, including: Obtaining the movement features of each individual marker in the adjacent monitoring images in the image set for the individual feature information; Judging whether the palm coordinate positions in each individual marker are within the handrail coordinate area of the security detection rules; Judging whether the movement features of each individual marker match the elevator operation parameters in the security detection rules; If the palm coordinate positions of each individual marker are all within the handrail coordinate area and the movement features all match the elevator operation parameters, obtaining a safe detection result; If the palm coordinate position of any one individual marker is not within the handrail coordinate area or any one movement feature of the individual marker does not match the elevator operation parameters, obtaining an unsafe detection result.

6. The elevator ride safety monitoring method according to claim 1, characterized in that, After performing security detection on the individual feature information of the image set according to the preset security detection rules to obtain a detection result of whether it is safe, it further includes: If the detection result is unsafe, intercepting the corresponding monitoring abnormal image from the image set according to the detection result; Combining the monitoring abnormal image with the current time and the monitoring position information corresponding to the image acquisition device to generate corresponding monitoring record information.

7. The elevator ride safety monitoring method according to claim 1 or 6, characterized in that, The management server is further communicatively connected to an alarm. After performing security detection on the individual feature information of the image set according to the preset security detection rules to obtain a detection result of whether it is safe, it further includes: If the detection result is unsafe, sending a monitoring prompt message to the alarm for alarm prompt.

8. An elevator ride safety monitoring device, characterized in that, The device is configured in a management server. The management server establishes a network connection with an image acquisition device and an infrared sensor arranged at the entrance of an escalator to achieve data information transmission. The image acquisition device is arranged facing the escalator. The device is used to execute the elevator ride safety monitoring method according to any one of claims 1-7. The device includes: A detection signal judgment unit for judging whether the infrared monitoring signal from the infrared sensor meets the preset security monitoring conditions; An image set acquisition unit for, if the infrared monitoring signal meets the security monitoring conditions, acquiring the acquired image set from the image acquisition device according to the preset acquisition strategy; the image set includes multiple monitoring images; An intercepted image acquisition unit for intercepting the monitoring images in the image set according to the preset image interception strategy to obtain corresponding intercepted images; An individual feature information acquisition unit for respectively performing individual recognition on the intercepted images according to the preset individual recognition model to obtain individual feature information corresponding to the image set; A detection result acquisition unit for performing security detection on the individual feature information of the image set according to the preset security detection rules to obtain a detection result of whether it is safe.

9. A computer device, characterized in that, The device includes a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete communication with each other through the communication bus; A memory for storing a computer program; A processor for implementing the steps of the elevator ride safety monitoring method according to any one of claims 1-7 when executing the program stored on the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program, when executed by the processor, implements the steps of the elevator ride safety monitoring method according to any one of claims 1-7.

Images