Elevator shaft installation target recognition method, device, equipment and storage medium

Abstract

The present application relates to an elevator shaft installation target recognition method, device, computer device, storage medium, and computer program product. The method includes: collecting an image of the shaft sidewall; inputting the shaft sidewall image into a trained brick wall recognition model to obtain the brick wall recognition result of the shaft sidewall image output by the trained brick wall recognition model; determining the brick wall distribution form of the shaft sidewall area corresponding to the shaft sidewall image according to the brick wall recognition result; and determining whether there is an installation target in the shaft sidewall area according to the brick wall distribution form. The present application can, based on the characteristic that there is a specific brick wall distribution form in the shaft sidewall area where the installation target is located, use the easily recognizable brick wall as the recognition feature to recognize the installation target, and can effectively improve the accuracy of recognizing the installation target in the elevator shaft sidewall.

Description

Technical Field

[0001] This application relates to the technical field of elevators, and particularly to a method, device, computer device, storage medium, and computer program product for identifying installation targets in an elevator shaft. Background Art

[0002] During the installation of an elevator, specific devices usually need to be installed on corresponding installation targets in the elevator shaft. For example, most elevator guide rail brackets need to be installed on the concrete ring beams in the elevator shaft. Although the positions of installation targets such as ring beams are marked in construction drawings, there are usually large errors between the markings in the drawings and the actual environment of the elevator shaft. If the installation is positioned according to the height marked in the drawings during the installation process, it is easy to miss the position of the installation target in the shaft, resulting in inaccurate installation positions and ultimately affecting the installation quality of elevator devices. Therefore, during the elevator installation process, the installation targets in the elevator shaft are usually detected again to determine their actual positions.

[0003] However, due to various factors that may affect the appearance of installation targets during the construction of the elevator shaft, even the same type of installation target often has multiple different appearance manifestations in the actual elevator shaft, making it difficult to directly identify the installation target using traditional image recognition technology. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a method, device, computer device, computer-readable storage medium, and computer program product for accurately identifying installation targets in an elevator shaft.

[0005] In a first aspect, this application provides a method for identifying an installation target in an elevator shaft. The method includes:

[0006] Collect an image of the shaft sidewall;

[0007] Input the image of the shaft sidewall into a trained brick wall recognition model, and obtain the brick wall recognition result of the image of the shaft sidewall output by the trained brick wall recognition model;

[0008] According to the brick wall recognition result, determine the brick wall distribution form of the shaft sidewall area corresponding to the image of the shaft sidewall;

[0009] According to the brick wall distribution form, determine whether there is an installation target in the shaft sidewall area.

[0010] In one of the embodiments, the step of determining whether there is an installation target in the shaft sidewall area according to the brick wall distribution form includes:

[0011] If the distribution form of the brick wall includes a non-brick wall area in the image of the shaft side wall and a brick wall area exists on both sides of the non-brick wall area in the height direction, it is determined that there is an installation target in the shaft side wall area.

[0012] In one embodiment, the method further includes:

[0013] In the case where there is no installation target in the shaft side wall area, the camera that captures the image of the shaft side wall moves in the height direction and continues to collect the image of the shaft side wall and identify the installation target until it is determined that there is an installation target in the shaft side wall area.

[0014] In one embodiment, the method further includes:

[0015] In the case where there is an installation target in the shaft side wall area, it is judged whether the distribution form of the brick wall is a specified brick wall distribution form according to the brick wall recognition result; if so, the center position information of the installation target is obtained according to the height information of the camera that captures the image of the shaft side wall.

[0016] In one embodiment, the method further includes:

[0017] If not, the camera moves in the height direction and continues to collect the image of the shaft side wall and judge the specified brick wall distribution form until it is judged that the distribution form of the brick wall is the specified brick wall distribution form.

[0018] In one embodiment, the method further includes:

[0019] According to the reference amplitude range corresponding to the installation target, the distance between the camera that captures the image of the shaft side wall and the shaft side wall is adjusted so that the amplitude of the shaft side wall area corresponding to the image of the shaft side wall is greater than the maximum reference amplitude of the installation target.

[0020] In one embodiment, the method further includes:

[0021] The image of the shaft side wall includes images of at least two side walls of the shaft; the determining whether there is an installation target in the shaft side wall area according to the distribution form of the brick wall includes: judging whether there is an installation target in the shaft side wall area according to the distribution form of the brick wall in the shaft side wall areas corresponding to the images of the shaft side walls corresponding to different side walls.

[0022] In a second aspect, the present application also provides an elevator shaft installation target recognition device. The device includes:

[0023] An image acquisition module, configured to acquire an image of the shaft side wall;

[0024] An identification module, configured to input the shaft wall image into a trained brick wall identification model, and obtain a brick wall identification result of the shaft wall image output by the trained brick wall identification model;

[0025] A processing module, configured to determine a brick wall distribution form of a shaft wall area corresponding to the shaft wall image according to the brick wall identification result;

[0026] A judgment module, configured to determine whether there is an installation target in the shaft wall area according to the brick wall distribution form.

[0027] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the following steps are implemented:

[0028] Collect a shaft wall image; input the shaft wall image into a trained brick wall identification model, and obtain a brick wall identification result of the shaft wall image output by the trained brick wall identification model; determine a brick wall distribution form of a shaft wall area corresponding to the shaft wall image according to the brick wall identification result; determine whether there is an installation target in the shaft wall area according to the brick wall distribution form.

[0029] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0030] Collect a shaft wall image; input the shaft wall image into a trained brick wall identification model, and obtain a brick wall identification result of the shaft wall image output by the trained brick wall identification model; determine a brick wall distribution form of a shaft wall area corresponding to the shaft wall image according to the brick wall identification result; determine whether there is an installation target in the shaft wall area according to the brick wall distribution form.

[0031] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0032] Collect a shaft wall image; input the shaft wall image into a trained brick wall identification model, and obtain a brick wall identification result of the shaft wall image output by the trained brick wall identification model; determine a brick wall distribution form of a shaft wall area corresponding to the shaft wall image according to the brick wall identification result; determine whether there is an installation target in the shaft wall area according to the brick wall distribution form.

[0033] The above elevator shaft installation target recognition method, device, computer equipment, storage medium and computer program product collect the shaft wall images, input the shaft wall images into the brick wall recognition model, and confirm the brick wall distribution form in the shaft wall area according to the output brick wall recognition result, and then judge whether there is an installation target in the corresponding shaft wall area. Based on the characteristic that there is a specific brick wall distribution form in the shaft wall area where the installation target is located in the elevator shaft, it uses the easily recognizable brick wall as the recognition feature, and determines whether there is an installation target in the shaft wall area corresponding to the shaft wall image through the brick wall distribution form obtained by image recognition. This process does not need to directly recognize the installation target with a complicated appearance, and can improve the accuracy of installation target recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic flowchart of the elevator shaft installation target recognition method in one embodiment;

[0035] Figure 2 It is a schematic diagram of the shaft wall image collected in one embodiment;

[0036] Figure 3 It is the brick wall recognition result output in one embodiment;

[0037] Figure 4 It is a schematic diagram of the working mode of using the elevator shaft installation target recognition method to recognize the installation target in one embodiment;

[0038] Figure 5 It is a schematic diagram of the process of determining whether there is an installation target in the shaft wall area in one embodiment;

[0039] Figure 6 It is a schematic diagram of the data in the installation target recognition process in one embodiment;

[0040] Figure 7 It is a structural block diagram of the elevator shaft installation target recognition device in one embodiment;

[0041] Figure 8 It is an internal structure diagram of the computer equipment in one embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0043] In one embodiment, as Figure 1As shown, a method for identifying installation targets in an elevator hoistway is provided. In this embodiment, an example is given where this method is applied to a terminal. It can be understood that this method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0044] Step S101: Collect an image of the hoistway sidewall.

[0045] Specifically, in this step, a camera can be used to photograph the hoistway sidewall to obtain an image of the hoistway sidewall. Please refer to Figure 2 , which is a schematic diagram of this image of the hoistway sidewall.

[0046] Among them, the shooting position of the camera should be such that the hoistway sidewall area corresponding to the collected image of the hoistway sidewall has a larger amplitude in at least one direction than the amplitude of the installation target in the same direction. That is, when the camera shoots directly at the installation target, the installation target will not fill the image in at least one direction.

[0047] Step S102: Input the image of the hoistway sidewall into a trained brick wall recognition model to obtain the brick wall recognition result of the image of the hoistway sidewall output by the trained brick wall recognition model.

[0048] Specifically, the brick wall recognition model can obtain the ability to recognize the brick wall features in the image through deep learning training on pre-collected brick wall pictures of various forms. Input the image of the hoistway sidewall obtained in step S101 into this brick wall recognition model, and the brick walls included in the image of the hoistway sidewall can be recognized and the brick wall recognition result can be output. The brick wall recognition result can include information such as the contours and areas of the brick wall areas that conform to the brick wall features in the image.

[0049] Exemplarily, please refer to Figure 3 , which is a presentation form of the brick wall recognition result output by the brick wall recognition model, in which the contours of each brick wall area in the image of the hoistway sidewall are detected and marked.

[0050] Step S103: Determine the brick wall distribution form of the hoistway sidewall area corresponding to the image of the hoistway sidewall according to the brick wall recognition result.

[0051] Specifically, according to the brick wall recognition result obtained in step S102, the number, area, and location area of the brick wall areas existing in the image of the hoistway sidewall can be judged, and then the brick wall distribution form in this image can be obtained.

[0052] For example, in Figure 3In the well shaft sidewall image shown, according to the brick wall recognition result, it can be obtained that the image includes two discontinuous brick wall regions, which are located at the top and bottom of the image respectively, and are separated by a non-brick wall region. Further, the proportion of each brick wall region in the image can also be calculated to obtain a more specific result of the brick wall distribution form.

[0053] Step S104: Determine whether there is an installation target in the well shaft sidewall region according to the brick wall distribution form.

[0054] Among them, since there are differences in the appearance between the installation target in the elevator shaft and the brick wall, the installation target in the well shaft sidewall image will not be recognized as a brick wall region in step S102. Therefore, when there is a region in the well shaft sidewall image that is not recognized as a brick wall region (i.e., "non-brick wall region"), there may be an installation target. Further, since different types of installation targets in the elevator shaft usually have specific installation methods, the combination methods of different types of installation targets on the well shaft sidewall with the brick wall also have their own characteristics.

[0055] Based on this, for the installation target that needs to be recognized, its combination method with the brick wall can be predicted and the distribution characteristics of the brick wall around the installation target can be obtained. Furthermore, it can be determined whether there is an installation target to be recognized on the well shaft sidewall corresponding to the image according to whether the brick wall distribution method obtained in step S103 conforms to the predicted brick wall distribution characteristics.

[0056] In this embodiment, by collecting the well shaft sidewall image, inputting the well shaft sidewall image into the brick wall recognition model, and confirming the brick wall distribution form of the well shaft sidewall region according to the output brick wall recognition result, it is further determined whether there is an installation target in the corresponding well shaft sidewall region. Based on the characteristic that there is a specific brick wall distribution form in the well shaft sidewall region where the installation target is located in the elevator shaft, using the easily recognizable brick wall as the recognition feature, and determining whether there is an installation target in the well shaft sidewall region corresponding to the well shaft sidewall image through the brick wall distribution form obtained by image recognition, this process does not need to directly recognize the installation target with a complicated appearance, which can improve the accuracy of installation target recognition.

[0057] In one embodiment, taking the ring beam in the elevator shaft as the installation target, according to the brick wall distribution form in step S104, determining whether there is an installation target in the well shaft sidewall region may include:

[0058] If the brick wall distribution form includes that there is a non-brick wall region in the well shaft sidewall image and there is a brick wall region on both sides of the non-brick wall region in the height direction, it is determined that there is an installation target in the well shaft sidewall region.

[0059] Specifically, according to the characteristic that the ring beams in the elevator hoistway are arranged annularly on the hoistway sidewall, it can be known that in the area of the hoistway sidewall with ring beams, the distribution characteristics of the brick walls are on both sides of the ring beams in the height direction of the hoistway. Furthermore, in the image of the hoistway sidewall containing the ring beam, as long as there is a non-brick-wall area, and there is a brick-wall area on each side of the non-brick-wall area in the height direction of the hoistway, it can be considered that the non-brick-wall area in the image is the ring beam, that is, the installation target to be recognized, so as to infer that there is an installation target in the hoistway sidewall area corresponding to the image.

[0060] Exemplarily, as Figure 3 shown, there are brick-wall areas at the top and bottom of the image and a non-brick-wall area in the middle of the image, then according to the method in this embodiment, it can be determined that there is an installation target in the hoistway sidewall area corresponding to the image.

[0061] According to the setting characteristics of the ring beams in the elevator hoistway and their combination with the surrounding brick walls in this embodiment, the distribution form of the brick walls that should appear in the corresponding hoistway sidewall area in the case of having ring beams is obtained. Thus, it can be conveniently determined whether there is a ring beam in the hoistway sidewall area by judging whether the distribution form of the brick walls in the image of the hoistway sidewall area matches it.

[0062] In one embodiment, after judging whether there is an installation target in the hoistway sidewall area in step S104, the following steps may further be included:

[0063] In the case where there is no installation target in the hoistway sidewall area, make the camera for shooting the hoistway sidewall image move in the height direction and continue to collect the hoistway sidewall image and identify the installation target until it is determined that there is an installation target in the hoistway sidewall area.

[0064] Specifically, if the distribution form of the brick walls in the hoistway sidewall area in step S104 does not match the predicted brick wall distribution characteristics determined according to the installation target to be recognized, it can be considered that there is no installation target in this hoistway sidewall area.

[0065] For example, in the case where the ring beam is the installation target, if there is no non-brick-wall area in the image, or the distribution of the brick-wall area does not conform to the characteristic that there is a brick-wall area on both sides of the non-brick-wall area in the height direction, it can be considered that there is no installation target in this hoistway sidewall area.

[0066] In this case, the camera can be made to move along the height direction of the hoistway, and new hoistway sidewall images are collected and the installation target is identified at different heights of the hoistway according to steps S101 - 104 until reaching the height where the hoistway sidewall area with the installation target is located, and the search for the installation target is completed.

[0067] In this embodiment, by moving the camera along the height direction of the shaft and continuously collecting images and identifying the installation target, the camera can find the installation target by itself when the installation target is not found, which speeds up the detection speed of the installation target.

[0068] In one embodiment, in order to more accurately locate the position of the installation target in the shaft, after determining whether there is an installation target in the shaft sidewall area in step S104, the following steps may further be included:

[0069] When there is an installation target in the shaft sidewall area, judge whether the brick wall distribution form is the specified brick wall distribution form according to the brick wall recognition result; if so, obtain the central position information of the installation target according to the height information of the camera that captures the shaft sidewall image.

[0070] Specifically, the central position of the installation target can be determined first according to its shape, and then the brick wall distribution form that should appear in the shaft sidewall image captured when the camera is at the same height as the central position is determined and set as the specified brick wall distribution form.

[0071] For example, for an exemplary installation target, an example image can be collected at the height of its central position in advance, the brick wall recognition result of the image can be obtained using the brick wall recognition model, and then an example brick wall distribution form can be determined. By comparing the similarity between the brick wall distribution form in the shaft sidewall image and the example brick wall distribution form, it can be known whether the shaft sidewall image is captured at the height of the central position of the corresponding installation target. When the similarity reaches the allowable range, it can be considered that the brick wall distribution form of the shaft sidewall conforms to the specified brick wall distribution form, and thus the central position information of the installation target can be obtained according to the camera height information when the shaft sidewall image is captured.

[0072] On the other hand, the specified brick wall distribution form can also be determined according to the geometric relationship that the distribution of the brick wall area in the shaft sidewall image collected at the specified position of the installation target should conform to.

[0073] For example, taking the ring beam as the installation target, when there is an installation target in the shaft sidewall area, the shaft sidewall image will satisfy the distribution characteristics that the middle is a non-brick wall area and the upper and lower parts are both brick wall areas. Further, for the image captured at the height corresponding to the central position of the ring beam, the brick wall areas in the upper and lower parts should have the same area. Thus, by comparing the areas of the brick wall areas in the upper and lower parts of the shaft sidewall image respectively, it can be determined whether the image is captured at the height corresponding to the central position of the ring beam. When the area difference between the brick wall areas in the upper and lower parts is within the preset allowable range, it can be considered that the image conforms to the specified brick wall distribution form, and the central position information of the ring beam can be obtained according to the camera height information corresponding to the image.

[0074] In some other methods, based on the property that the center of the non-brick wall area in the image of the hoistway sidewall collected at the height corresponding to the center position of the ring beam coincides with the center of the image, it is possible to determine whether the image is collected at the height corresponding to the center position of the ring beam by calculating the distance between the center coordinates of the non-brick wall area in the image of the hoistway sidewall and the center point of the image. When the distance between the two falls within the preset allowable range, it is considered that the image conforms to the specified brick wall distribution form, and the center position information of the ring beam can be obtained according to the camera height information corresponding to the image.

[0075] Furthermore, in actual operation, due to the limitations of image acquisition conditions and image recognition accuracy, using image recognition technology may not be able to obtain a result that exactly matches the example brick wall distribution form or the above geometric relationship, and a relatively large allowable range needs to be set. To obtain a more accurate recognition result of the center position within this relatively large allowable range, during the actual recognition process, the camera can also be moved within the height range where the installation target can be photographed and the images of the hoistway sidewall are continuously collected. For each image of the hoistway sidewall, judge the approximation degree of the brick wall distribution form it reflects to the example distribution form, or calculate the gap between the brick wall distribution form and the above geometric relationship. Among them, within the preset allowable range, the image with the highest approximation degree to the example distribution form or the one that most conforms to the above geometric relationship is considered to correspond to the specified brick wall distribution form, and the center position information of the ring beam can be obtained according to the camera height information corresponding to the image.

[0076] In this embodiment, by presetting a specified brick wall distribution form corresponding to the center position of the installation target and comparing the brick wall distribution form in the image of the hoistway sidewall with it, it is possible to judge whether the acquisition height of the image is the height where the center position of the installation target is located according to the comparison result. It can obtain a more accurate positioning of the installation target, thereby improving the accuracy of the subsequent installation process and ensuring the installation quality of elevator devices.

[0077] In one embodiment, in order to more accurately position the installation target in the hoistway, after judging whether there is an installation target in the hoistway sidewall area in step S104, the following steps may further be included:

[0078] When there is an installation target in the hoistway sidewall area, judge whether the brick wall distribution form is the specified brick wall distribution form according to the brick wall recognition result; if not, move the camera in the height direction and continue to collect the images of the hoistway sidewall and judge the specified brick wall distribution form until it is judged that the brick wall distribution form is the specified brick wall distribution form.

[0079] Specifically, if it is determined that the brick wall distribution form in the shaft wall image does not conform to the specified brick wall distribution form according to the above method, it can be considered that the image is not collected at the height corresponding to the center position of the installation target. In this case, the camera is moved along the height direction of the shaft, and new shaft wall images are collected at different heights of the shaft according to the above steps, and the brick wall distribution form therein is matched with the specified brick wall distribution form until the brick wall distribution form in the image conforms to the specified brick wall distribution form, and its height is the height corresponding to the center position of the installation target.

[0080] In this embodiment, by moving the camera along the height direction of the shaft, continuously collecting images and determining whether the brick wall distribution form is the specified brick wall distribution form, the camera can automatically find the height of the center position of the installation target, improving the efficiency of obtaining the accurate position of the installation target.

[0081] In one embodiment, the method may further include: adjusting the distance between the camera for shooting the shaft wall image and the shaft wall according to the reference amplitude range corresponding to the installation target, so that the amplitude of the shaft wall area corresponding to the shaft wall image is greater than the maximum reference amplitude of the installation target.

[0082] Specifically, since different installation targets have different sizes, in order to more accurately identify the installation target, the corresponding shooting distance can be determined according to different installation targets, so that the field of view of the camera can simultaneously encompass the installation target and the surrounding brick walls in at least one direction.

[0083] Based on this, the size of the installation target can be estimated in advance according to the construction standard corresponding to the installation target to be identified, and the reference amplitude range in the height direction can be obtained. Further, according to the field of view size of the specific camera used, the distance between the camera and the shaft wall is adjusted so that the amplitude of the shaft wall that the camera can shoot in the height direction is greater than the maximum value of the reference amplitude range of the installation target, that is, its maximum reference amplitude. Thus, when the installation target appears in the shaft wall image, it will not occupy the entire image space at least in the height direction, and the surrounding brick wall area will also appear in the image. Furthermore, by identifying the brick wall area in the image according to the above method, the identification of the installation target can be indirectly completed.

[0084] In this embodiment, the distance between the camera and the shaft wall can be adjusted according to the amplitude of the installation target, so that the installation target does not occupy the entire image range, thereby ensuring that the camera can collect an effective image that can contain the brick wall area and can be used for the above identification method, improving the reliability of the identification process.

[0085] In one embodiment, the hoistway sidewall image of the method includes images of at least two sidewalls of the hoistway; determining whether there is an installation target in the hoistway sidewall area according to the brick wall distribution form includes: judging whether there is an installation target in the hoistway sidewall area according to the brick wall distribution form of the hoistway sidewall area corresponding to the hoistway sidewall images corresponding to different sidewalls.

[0086] Specifically, since there may be different types of installation targets with similar local structures such as ring beams and lintel beams of door openings on the hoistway sidewall at the same time, when using a camera with a narrow field of view to collect and identify images of one sidewall of the hoistway, confusion may occur between different types of installation targets. Therefore, it is necessary to first select a suitable hoistway sidewall for collection according to the distribution position of the installation target before image collection.

[0087] To avoid analyzing and selecting the hoistway sidewall before each collection, in this embodiment, multiple cameras or a movable camera can be used to collect images of at least two sidewalls of the hoistway at the same height, and identify the installation target for each hoistway sidewall image collected at this height during subsequent processing.

[0088] Furthermore, if the ring beam is used as the installation target, when an installation target is identified in the sub-hoistway sidewall area corresponding to each hoistway sidewall image, it is determined that there is a ring beam in the hoistway sidewall area. If the lintel beam of the door opening is used as the installation target, when an installation target is identified in the sub-hoistway sidewall area corresponding to only one side of the hoistway sidewall image and no installation target is identified in the sub-hoistway sidewall areas in other directions, it is determined that there is a lintel beam of the door opening in the hoistway sidewall area.

[0089] Further, for installation targets distributed in a ring shape such as ring beams, the center position of each hoistway sidewall image can also be judged, and the corresponding height of the center position of the installation target can be obtained by synthesizing the judgment results of each image.

[0090] This embodiment can distinguish installation targets with similar local structures but different setting methods, avoid the process of analyzing and selecting the hoistway sidewall in advance, and improve the recognition efficiency of the installation target.

[0091] In a specific embodiment, taking the ring beam in the elevator hoistway as the installation target, the ring beams in the same hoistway can be identified according to the following process, and the height where the center position of each ring beam is located can be determined:

[0092] First, according to the construction standard of the ring beam, it can be known that its reference amplitude range in the height direction is 350 - 500 mm. According to this reference amplitude range, as Figure 4As shown in the figure, the distance D1 between the first camera with a viewing angle of α and the shaft wall is adjusted so that the camera can collect the shaft wall range with a height amplitude greater than 500 mm in one shot. Similarly, the distance D2 between the second camera with a viewing angle of β and the shaft wall can be adjusted so that it can collect the shaft wall range with a height amplitude greater than 500 mm in one shot.

[0093] Then, the first camera and the second camera are moved synchronously along the height direction of the shaft. For example, they are moved from the bottom to the top of the shaft. During the movement, image acquisition is continuously performed on the first shaft wall and the second shaft wall respectively, and the installation target is identified in the acquired shaft wall images according to the steps S101 - 105 in the above method until there is an installation target in the images collected by the first camera and the second camera. The corresponding installation target in this image is the first ring beam encountered during the movement of the camera from the bottom to the top of the shaft. Then, according to step S106 in the above method, it is judged whether the brick wall distribution form in the shaft wall image conforms to the specified brick wall distribution form.

[0094] Specifically, as Figure 5 shown, in this embodiment, the shaft wall image is first divided into upper, middle, and lower three regions. Then, after identifying each brick wall region (i.e., the recognition frame marked as "brick"), it is judged whether there are brick wall regions in both the upper and lower regions, and further judge the distribution relationship between the non - brick wall region and the brick wall region in the image, so as to determine that its distribution relationship conforms to the brick wall distribution form corresponding to the ring beam.

[0095] Furthermore, the center point coordinates of the image itself can be determined first, and then the center point coordinates of the non - brick wall region in the image are determined. According to the distance L1 between the two coordinates in the height direction and the amplitude L2 of the image in the height direction, the matching degree can be calculated according to the following formula:

[0096] Matching degree = (1 - L1 / L2) * 100%

[0097] Calculated in the above manner, Figure 5 the matching degree value corresponding to the shaft wall image shown in the figure is 57.8% ("concreate confidence" marked in the figure).

[0098] Among them, in this embodiment, during the movement of the first camera and the second camera relative to the movement of the shaft, the installation target recognition and the calculation of the matching degree value are performed on the acquired shaft wall images in real - time, and the average value of the matching degree values of the two shaft wall images is used as the matching degree at this height.

[0099] Please refer to Figure 6, which is a data schematic diagram of the installation target recognition process, where (a) refers to the change process of the matching degree in the installation target recognition process, and (b) refers to the change process of the distance between the camera and the center position of the installation target in the installation target recognition process.

[0100] As Figure 6 shown, the camera starts to move from the 0th second. At this time, its distance from the center position of the ring beam is about 1200 mm. Since the images collected by the camera in a period of time after starting to move do not contain the installation target, the corresponding matching degree is 0 from the 0th to the 5th second. After the 5th second, the camera moves to a position about 800 mm from the center position of the ring beam. At this time, the installation target appears in the image, and the matching degree value can be calculated based on it. As time goes by, the height distance between the camera and the center position of the ring beam becomes smaller and smaller, and the corresponding matching degree becomes higher and higher. At about 16 seconds, the matching degree reaches the highest value. At this time, it can be considered that the camera has moved to the height corresponding to the center position of the ring beam, and the height of the camera can be recorded to locate the center position of the ring beam.

[0101] Make the camera continue to move in the same direction in the hoistway and repeat the above steps to identify all the ring beams in the hoistway and obtain the height where the center position of each ring beam is located.

[0102] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps does not have a strict order limit, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily have to be executed at the same time, but can be executed at different times. The execution order of these steps or stages does not necessarily have to be sequential, but can be executed alternately or in turn with at least some of the steps or stages in other steps or other steps.

[0103] Based on the same inventive concept, the embodiments of the present application also provide an elevator hoistway installation target recognition device for implementing the elevator hoistway installation target recognition method involved above. The implementation solutions provided by this device to solve problems are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more embodiments of the elevator hoistway installation target recognition device provided below can refer to the limitations on the elevator hoistway installation target recognition method in the above text, and will not be repeated here.

[0104] In one embodiment, as Figure 7 shown, an elevator hoistway installation target recognition device 700 is provided, including:

[0105] The image acquisition module 701 is configured to acquire an image of the well shaft sidewall.

[0106] The recognition module 702 is configured to input the well shaft sidewall image into a trained brick wall recognition model, and obtain the brick wall recognition result of the well shaft sidewall image output by the trained brick wall recognition model.

[0107] The processing module 703 is configured to determine the brick wall distribution form of the well shaft sidewall area corresponding to the well shaft sidewall image according to the brick wall recognition result.

[0108] The judgment module 704 is configured to determine whether there is an installation target in the well shaft sidewall area according to the brick wall distribution form.

[0109] In one embodiment, the judgment module 704 is further configured to determine that there is an installation target in the well shaft sidewall area if the brick wall distribution form includes a non-brick wall area in the well shaft sidewall image and a brick wall area exists on both sides of the non-brick wall area in the height direction.

[0110] In one embodiment, the judgment module 704 is further configured to, when there is no installation target in the well shaft sidewall area, move the camera that captures the well shaft sidewall image in the height direction and continue to acquire the well shaft sidewall image and recognize the installation target until it is determined that there is an installation target in the well shaft sidewall area.

[0111] In one embodiment, the device further includes a central position judgment module, which is configured to, when there is an installation target in the well shaft sidewall area, judge whether the brick wall distribution form is a specified brick wall distribution form according to the brick wall recognition result; if so, obtain the central position information of the installation target according to the height information of the camera that captures the well shaft sidewall image.

[0112] In one embodiment, the central position judgment module is further configured to, when there is an installation target in the well shaft sidewall area, judge whether the brick wall distribution form is a specified brick wall distribution form according to the brick wall recognition result; if not, move the camera in the height direction and continue to acquire the well shaft sidewall image and judge the specified brick wall distribution form until it is judged that the brick wall distribution form is the specified brick wall distribution form.

[0113] In one embodiment, the image acquisition module 701 is further configured to adjust the distance between the camera that captures the well shaft sidewall image and the well shaft sidewall according to the reference amplitude range corresponding to the installation target, so that the amplitude of the well shaft sidewall area corresponding to the well shaft sidewall image is greater than the maximum reference amplitude of the installation target.

[0114] In one embodiment, the hoistway sidewall image includes images of at least two sidewalls of the hoistway; the determination module is further configured to: determine whether there is an installation target in the hoistway sidewall area according to the brick wall distribution forms of the hoistway sidewall areas corresponding to the hoistway sidewall images corresponding to different sidewalls.

[0115] Each module in the above elevator hoistway installation target recognition device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor in the computer device in hardware form or be independent of the processor, or can be stored in the memory in the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0116] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 8 shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements an elevator hoistway installation target recognition method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the outer shell of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0117] Those skilled in the art can understand that Figure 8 the structure shown in

[0118] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0119] Collect an image of the wellbore sidewall; input the wellbore sidewall image into a trained brick wall recognition model to obtain the brick wall recognition result of the wellbore sidewall image output by the trained brick wall recognition model; determine the brick wall distribution form of the wellbore sidewall area corresponding to the wellbore sidewall image according to the brick wall recognition result; determine whether there is an installation target in the wellbore sidewall area according to the brick wall distribution form.

[0120] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0121] Determine whether there is an installation target in the wellbore sidewall area according to the brick wall distribution form. If the brick wall distribution form includes a non-brick wall area in the wellbore sidewall image and there is a brick wall area on both sides of the non-brick wall area in the height direction, it is determined that there is an installation target in the wellbore sidewall area.

[0122] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0123] Determine whether there is an installation target in the wellbore sidewall area according to the brick wall distribution form. In the case where there is no installation target in the wellbore sidewall area, move the camera that captures the wellbore sidewall image in the height direction and continue to collect the wellbore sidewall image and identify the installation target until it is determined that there is an installation target in the wellbore sidewall area.

[0124] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0125] In the case where there is an installation target in the wellbore sidewall area, judge whether the brick wall distribution form is a specified brick wall distribution form according to the brick wall recognition result; if so, obtain the center position information of the installation target according to the height information of the camera that captures the wellbore sidewall image.

[0126] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0127] In the case where there is an installation target in the wellbore sidewall area, judge whether the brick wall distribution form is a specified brick wall distribution form according to the brick wall recognition result; if not, move the camera in the height direction and continue to collect the wellbore sidewall image and judge the specified brick wall distribution form until it is judged that the brick wall distribution form is a specified brick wall distribution form.

[0128] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0129] Adjust the distance between the camera for capturing the image of the shaft wall and the shaft wall according to the reference amplitude range corresponding to the installation target; so that the amplitude of the shaft wall area corresponding to the shaft wall image is greater than the maximum reference amplitude of the installation target.

[0130] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0131] Collect an image of the shaft wall; input the shaft wall image into a trained brick wall recognition model to obtain the brick wall recognition result of the shaft wall image output by the trained brick wall recognition model; determine the brick wall distribution form of the shaft wall area corresponding to the shaft wall image according to the brick wall recognition result; determine whether there is an installation target in the shaft wall area according to the brick wall distribution form.

[0132] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0133] Determine whether there is an installation target in the shaft wall area according to the brick wall distribution form. In the case where there is no installation target in the shaft wall area, move the camera for capturing the shaft wall image in the height direction and continue to collect the shaft wall image and identify the installation target until it is determined that there is an installation target in the shaft wall area.

[0134] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0135] In the case where there is an installation target in the shaft wall area, determine whether the brick wall distribution form is a specified brick wall distribution form according to the brick wall recognition result; if so, obtain the center position information of the installation target according to the height information of the camera for capturing the shaft wall image.

[0136] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0137] In the case where there is an installation target in the shaft wall area, determine whether the brick wall distribution form is a specified brick wall distribution form according to the brick wall recognition result; if not, move the camera in the height direction and continue to collect the shaft wall image and judge the specified brick wall distribution form until it is judged that the brick wall distribution form is the specified brick wall distribution form.

[0138] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0139] Adjust the distance between the camera for capturing the image of the shaft wall and the shaft wall according to the reference amplitude range corresponding to the installation target; so that the amplitude of the shaft wall area corresponding to the shaft wall image is greater than the maximum reference amplitude of the installation target.

[0140] In one embodiment, a computer program product is provided, including a computer program which, when executed by a processor, implements the following steps:

[0141] Collect an image of the side wall of the shaft; input the image of the side wall of the shaft into a trained brick wall recognition model to obtain the brick wall recognition result of the image of the side wall of the shaft output by the trained brick wall recognition model; determine the brick wall distribution form of the side wall area of the shaft corresponding to the image of the side wall of the shaft according to the brick wall recognition result; determine whether there is an installation target in the side wall area of the shaft according to the brick wall distribution form.

[0142] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0143] Determine whether there is an installation target in the side wall area of the shaft according to the brick wall distribution form. If the brick wall distribution form includes a non-brick wall area in the image of the side wall of the shaft and there is a brick wall area on both sides of the non-brick wall area in the height direction, it is determined that there is an installation target in the side wall area of the shaft.

[0144] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0145] Determine whether there is an installation target in the side wall area of the shaft according to the brick wall distribution form. In the case where there is no installation target in the side wall area of the shaft, move the camera that captures the image of the side wall of the shaft in the height direction and continue to collect the image of the side wall of the shaft and identify the installation target until it is determined that there is an installation target in the side wall area of the shaft.

[0146] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0147] In the case where there is an installation target in the side wall area of the shaft, determine whether the brick wall distribution form is a specified brick wall distribution form according to the brick wall recognition result; if so, obtain the center position information of the installation target according to the height information of the camera that captures the image of the side wall of the shaft.

[0148] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0149] In the case where there is an installation target in the side wall area of the shaft, determine whether the brick wall distribution form is a specified brick wall distribution form according to the brick wall recognition result; if not, move the camera in the height direction and continue to collect the image of the side wall of the shaft and judge the specified brick wall distribution form until it is judged that the brick wall distribution form is a specified brick wall distribution form.

[0150] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0151] Adjust the distance between the camera for capturing the image of the shaft sidewall and the shaft sidewall according to the reference amplitude range corresponding to the installation target, so that the amplitude of the shaft sidewall area corresponding to the shaft sidewall image is greater than the maximum reference amplitude of the installation target.

[0152] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the various embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAM), magnetoresistive random access memories (MRAM), ferroelectric random access memories (FRAM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memory (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the various embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the various embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logics, data processing logics based on quantum computing, etc., without limitation.

[0153] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0154] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. An elevator hoistway installation target recognition method, characterized in that, The method includes: Collecting an image of the well shaft side wall; Inputting the well shaft side wall image into a trained brick wall recognition model to obtain the brick wall recognition result of the well shaft side wall image output by the trained brick wall recognition model; Determining the brick wall distribution form of the well shaft side wall area corresponding to the well shaft side wall image according to the brick wall recognition result; Determining whether there is an installation target in the well shaft side wall area according to the brick wall distribution form; 2. The method according to claim 1, wherein The determining whether there is an installation target in the well shaft side wall area according to the brick wall distribution form includes: If the brick wall distribution form includes a non-brick wall area in the well shaft side wall image and there is a brick wall area on both sides of the non-brick wall area in the height direction, it is determined that there is an installation target in the well shaft side wall area.

3. The method according to claim 1 or 2, characterized in that, The method further includes: In the case where there is no installation target in the well shaft side wall area, moving the camera that captures the well shaft side wall image in the height direction and continuing to collect the well shaft side wall image and recognize the installation target until it is determined that there is an installation target in the well shaft side wall area.

4. The method according to claim 1, wherein The method further includes: In the case where there is an installation target in the well shaft side wall area, judging whether the brick wall distribution form is a specified brick wall distribution form according to the brick wall recognition result; If so, obtaining the center position information of the installation target according to the height information of the camera that captures the well shaft side wall image.

5. The method according to claim 4, wherein The method further includes: If not, moving the camera in the height direction and continuing to collect the well shaft side wall image and judge the specified brick wall distribution form until it is judged that the brick wall distribution form is the specified brick wall distribution form.

6. The method according to claim 1, wherein The method further includes: Adjusting the distance between the camera that captures the well shaft side wall image and the well shaft side wall according to the reference amplitude range corresponding to the installation target, so that the amplitude of the well shaft side wall area corresponding to the well shaft side wall image is greater than the maximum reference amplitude of the installation target.

7. The method according to claim 1, characterized in that, The well shaft side wall image includes images of at least two side walls of the well shaft; The determining whether there is an installation target in the well shaft side wall area according to the brick wall distribution form includes: Judging whether there is an installation target in the well shaft side wall area according to the brick wall distribution forms of the well shaft side wall areas corresponding to the well shaft side wall images corresponding to different side walls.

8. An elevator shaft installation target recognition device, characterized in that, The device includes: An image acquisition module for collecting an image of the well shaft side wall; A recognition module for inputting the well shaft side wall image into a trained brick wall recognition model to obtain the brick wall recognition result of the well shaft side wall image output by the trained brick wall recognition model; A processing module for determining the brick wall distribution form of the well shaft side wall area corresponding to the well shaft side wall image according to the brick wall recognition result; A judgment module for determining whether there is an installation target in the well shaft side wall area according to the brick wall distribution form.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images