Method and device for recognizing hooking state of shackle based on image recognition
Through image recognition technology, the inner image of the hook and loop is obtained in real time, boundary features and objects are identified, and the hook and loop system hanging status is determined, which solves the problem of large hook and loop detection errors in high-altitude operations and improves safety.
Patent Information
- Application Number
- CN202411331089.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-24
- Publication Date
- 2025-01-10
AI Technical Summary
When moving, high-altitude workers have negligent or environmental reasons, the detection error of hook and loop system is large, the accuracy is low, and personal safety is endangered.
Using an image recognition method, the image inside the hook and loop is obtained in real time through the camera, the boundary features and objects of the hook and loop are identified, and the area where the hook and loop is blocked by the object is determined. If the object blocks the first and second hook and loop boundaries, it is determined as a system. Hang state, otherwise it is not hanging.
It improves the accuracy of hook and loop detection, avoids hook and loop detection errors in high-altitude operations, and enhances personal safety guarantees.
Smart Images
Figure CN119295761A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of image recognition, and in particular to a method and device for identifying a hook and loop hanging state based on image recognition. Background Art
[0002] When working at height, the user should fasten the safety belt to his body, and fix the other end by hanging the metal safety hook on the safety rope to the connector of the firm fixed end (fixed frame or safety rope) above to ensure the user's personal safety.
[0003] However, in actual applications, aerial workers often forget to hook the hook ring on the high-altitude connector due to negligence or because it is troublesome to move at high altitude, which endangers the personal safety of the user; and it is difficult for ground management personnel to find and remind them in time, which has become a major cause of high-altitude fall safety accidents. The current hook ring determines whether it is in a hooked state mainly by detecting whether there is an object inside the hook ring. However, since aerial workers need to move frequently at high altitudes, the hooked object may be in the blind spot of detection during the movement, or only the existence of an object in the hook ring is identified, but the hook ring is not hung on the hook ring. Invalid hanging situation, resulting in large errors and low accuracy in hook ring detection. Summary of the invention
[0004] The present invention provides a method and device for identifying the hook and loop hanging state based on an image, so as to solve the technical problem in the prior art that the detection error of the hook and loop hanging state is large and the accuracy is low when the aerial workers move.
[0005] In order to solve the above technical problems, an embodiment of the present invention provides a method for identifying the state of a hook and loop based on image recognition, which is applied to the hook and loop, comprising:
[0006] The image of the inner side of the hook ring is obtained in real time through a camera; wherein the camera is arranged on one side of the hook ring;
[0007] Recognize the image, obtain the boundary features of the hook and the object in the image, and determine the area of the hook blocked by the object according to the boundary features of the hook; wherein the boundary features include a first hook boundary and a second hook boundary;
[0008] When the objects in the area block the first hook boundary and the second hook boundary, the hook is determined to be in a tied state; otherwise, the hook is determined to be in an untied state.
[0009] As a preferred solution, the real-time acquisition of the image of the inner side of the hook ring by a camera specifically includes:
[0010] Through a camera arranged at one side of the hook ring, an image of the inner side of the hook ring is acquired once every preset time.
[0011] As a preferred solution, before acquiring the boundary features and objects of the hook and loop in the image, the method specifically includes:
[0012] recognizing the image;
[0013] If no other objects except the hook in the image can be identified, it is determined that the hook is in an untied state.
[0014] As a preferred solution, the obtaining of boundary features and objects of the hook and loop in the image specifically includes:
[0015] When it is recognized that there is an object in the image, the upper boundary and the lower boundary of the hook in the image are identified, and the upper boundary is used as the first boundary feature and the lower boundary is used as the second boundary feature.
[0016] As a preferred solution, determining the area of the hook blocked by the object according to the boundary features of the hook specifically includes:
[0017] According to the boundary features of the hook ring, determining whether there is a disconnected position between the first boundary feature and the second boundary feature;
[0018] If there is and the object is in the disconnected position, the position is regarded as the area where the hook is blocked by the object;
[0019] If not, it is determined that the carabiner is in an untied state.
[0020] As a preferred solution, before determining the hook ring to be in the hanging state, the method further includes:
[0021] Acquire the depth feature of the object;
[0022] Determining whether the object is in close contact with the hook ring according to the capacitive sensing in the hook ring;
[0023] If the object is in close contact with the hook, a first actual width of the object is calculated according to the depth feature of the object, and when the first actual width is greater than a preset threshold, the hook is determined to be in a valid hanging state;
[0024] If the object is not close to the hook, the second actual width of the object is calculated based on the depth feature of the object and the distance from the camera to the hook, and when the second actual width is greater than a preset threshold, the hook is determined to be in a valid hanging state.
[0025] As a preferred solution, calculating the first actual width of the object according to the depth feature of the object specifically includes:
[0026] Acquire the horizontal length and the vertical length of the object in the image according to the depth feature of the object;
[0027] When the transverse length is equal to the longitudinal length, the inner wall height of the hook ring is used as the first actual width of the object;
[0028] When the transverse length is not equal to the longitudinal length, the actual width of the object is calculated based on the inner wall height of the hook ring and the transverse length and longitudinal length of the object as the first actual width.
[0029] Accordingly, the present invention also provides a hook and loop hanging state recognition device based on image recognition, comprising: an image acquisition module, an image recognition module and a hanging state module;
[0030] The image acquisition module is used to acquire the image of the inner side of the hook ring in real time through a camera; wherein the camera is arranged on one side of the hook ring;
[0031] The image recognition module is used to recognize the image, obtain the boundary features of the hook and loop and the object in the image, and determine the area of the hook and loop blocked by the object according to the boundary features of the hook and loop; wherein the boundary features include a first hook and loop boundary and a second hook and loop boundary;
[0032] The hook state module is used to determine the hook as being in a hook state when the objects in the area block the first hook boundary and the second hook boundary; otherwise, the hook is determined to be in an unhooked state.
[0033] Correspondingly, the present invention also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the hook and loop hanging state recognition method based on image recognition as described in any one of the above.
[0034] Correspondingly, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the hook and loop hanging state recognition method based on image recognition as described in any one of the above.
[0035] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:
[0036] The technical solution of the present invention obtains the image of the inner side of the hook ring in real time through the camera, and recognizes the image, so as to obtain the boundary features and objects of the hook ring in the image, determine the area of the hook ring blocked by the object, and then after the objects in the area block the first hook ring boundary and the second hook ring boundary, the hook ring is determined to be in a hung state, otherwise it is in an untied state, thereby avoiding the problem of low accuracy caused by using the existing detection of objects in the hook ring as a condition for judging whether the hook ring is in a hung state during aerial work and movement. At the same time, combined with the boundary features of the hook ring, it can further avoid the situation where the hook ring ineffectively hooks the object, thereby improving the accuracy of hook ring detection. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Figure 1 : A flowchart of a method for identifying a hook and loop hanging state based on image recognition provided by an embodiment of the present invention;
[0038] Figure 2 : A schematic diagram of an image of a hook and loop in an original state provided by an embodiment of the present invention;
[0039] Figure 3 : A schematic diagram of a hook provided by an embodiment of the present invention having an object passing through it;
[0040] Figure 4 : A schematic diagram of the depth estimation principle provided by an embodiment of the present invention;
[0041] Figure 5 : A structural diagram of a hook and loop hanging state recognition device based on image recognition provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0043] Embodiment 1
[0044] Please refer to Figure 1 , a method for identifying the state of a hook and loop based on image recognition provided by an embodiment of the present invention, applied to a hook and loop, comprises the following steps S101-S103:
[0045] Step S101: acquiring the image of the inner side of the hook ring in real time through a camera; wherein the camera is arranged on one side of the hook ring.
[0046] As a preferred solution of this embodiment, the real-time acquisition of the image of the inner side of the hook ring by a camera specifically includes:
[0047] Through a camera arranged at one side of the hook ring, an image of the inner side of the hook ring is acquired once every preset time.
[0048] In this embodiment, a detection device is provided in the hook, and the detection device integrates a micro camera, a microprocessor MCU, a communication module, an antenna, a power module, etc. The detection device is provided on one side of the hook, and by installing a micro camera on one side of the hook, when the hook is in a natural state of hanging a rope, the side of the hook with the micro camera automatically faces downward, and the other side without the micro camera installed will automatically hang on the rope (or other hooked objects), so that the camera can directly obtain the image on the other side of the hook.
[0049] Step S102: Identify the image, obtain boundary features of the hook and the object in the image, and determine the area of the hook blocked by the object based on the boundary features of the hook; wherein the boundary features include a first hook boundary and a second hook boundary.
[0050] As a preferred solution of this embodiment, before acquiring the boundary features and objects of the hook and loop in the image, the method specifically includes:
[0051] The image is identified; if no other objects except the hook are identified in the image, it is determined that the hook is in an untied state.
[0052] In this embodiment, when there is no object hooked in the hook ring (during the startup process), an image in this original state is captured, such as Figure 2 In the original state photo, according to the perspective principle, the image of the hook is an "hourglass-shaped" figure, and the boundary of the hook is clear, continuous, and complete without interruption; the hook image (the "hourglass-shaped" part) is complete without any obstruction or defect.
[0053] In this embodiment, regardless of whether there are other object images in the photo, as long as the upper and lower boundaries of the hook (i.e., the boundary features) are clear, continuous, complete, and without interruption; and the hook image (the "hourglass-shaped" part) is complete without any obstruction or defect, this situation can be determined as there is no hook in the hook and "the hook is not effectively hooked."
[0054] As a preferred solution of this embodiment, the obtaining of boundary features and objects of the hook and loop in the image specifically includes:
[0055] When it is recognized that there is an object in the image, the upper boundary and the lower boundary of the hook in the image are identified, and the upper boundary is used as the first boundary feature and the lower boundary is used as the second boundary feature.
[0056] In this embodiment, when an object is recognized in the image, it means that the hook may be hooked on the corresponding hooking object, and the boundary features of the hook can be further obtained, that is, the upper and lower boundaries of the hook are obtained, and the upper boundary is used as the first boundary feature, and the lower boundary is used as the second boundary feature.
[0057] As a preferred solution of this embodiment, determining the area of the hook blocked by the object according to the boundary features of the hook specifically includes:
[0058] According to the boundary features of the hook, determine whether there is a disconnected position between the first boundary feature and the second boundary feature; if there is and the object is at the disconnected position, use the position as the area where the hook is blocked by the object; if not, determine that the hook is in an untied state.
[0059] In this embodiment, by analyzing the boundary features of the hook, it is possible to determine whether there is a disconnection between the first boundary feature and the second boundary feature. If there is a disconnection, it means that an object may have passed through the upper boundary or the lower boundary of the hook, that is, the hook may be in a hanging state.
[0060] In this embodiment, when the hook is working, a working photo of the hook state is taken once per second. If there is an object in the hook but it does not penetrate the hook, in the image of an object that intersects with the hook but does not penetrate the hook, even if its upper and lower boundary red lines are blocked, they will not be blocked by the same object at the same time, only one line will be blocked, and it is also possible that both red lines are not blocked. When there are other object images in the photo, but the upper and lower boundary lines in the hook are not blocked by the same object at the same time, that is, a certain object only blocks one line, or does not block one line, this situation can be determined as there is an object in the hook and "not effectively hooked".
[0061] In this embodiment, when the hook is working, a working photo of the hook is taken once per second. If there is an object penetrating the hook, both the upper and lower boundary lines of the hook will be blocked by the same object at the same time, and the boundary lines will be discontinuous; when both the upper and lower boundary lines of the hook in the photo are blocked by the same object at the same time, and the boundary lines are discontinuous, this situation can be determined as there is an object in the hook and "there is a hook".
[0062] Step S103: When the objects in the area block the first hook boundary and the second hook boundary, the hook is determined to be in a tied state; otherwise, the hook is determined to be in an untied state.
[0063] As a preferred solution of this embodiment, before determining the hook ring as the hanging state, the method further includes:
[0064] Acquire the depth feature of the object; determine whether the object is in close contact with the hook according to the capacitive sensing in the hook; if the object is in close contact with the hook, calculate the first actual width of the object according to the depth feature of the object, and determine the hook as a valid hanging state when the first actual width is greater than a preset threshold; if the object is not in close contact with the hook, calculate the second actual width of the object according to the depth feature of the object and the distance from the camera to the hook, and determine the hook as a valid hanging state when the second actual width is greater than a preset threshold.
[0065] As a preferred solution of this embodiment, calculating the first actual width of the object according to the depth feature of the object specifically includes:
[0066] According to the depth feature of the object, the horizontal length and the vertical length of the object in the image are obtained; when the horizontal length is equal to the vertical length, the inner wall height of the hook ring is used as the first actual width of the object; when the horizontal length is not equal to the vertical length, the actual width of the object is calculated according to the inner wall height of the hook ring combined with the horizontal length and the vertical length of the object as the first actual width.
[0067] In this embodiment, when an object is found in the hook in the image, and the objects in the area block the first hook boundary and the second hook boundary, it is necessary to use depth estimation technology to estimate the thickness of the hook (the actual width of the object) to avoid the hook being too thin and insufficient in strength, which will result in the inability to withstand the normal hanging tension requirements of the safety belt.
[0068] It should be noted that, usually, the height (i.e., thickness) of the inner wall of the hook ring is substantially the same. According to the principle of image transmission, the hook ring image will be an "hourglass-shaped" figure, and the boundaries of the hook ring are two parabolas.
[0069] In this embodiment, when the object is close to the inner wall of the hook ring, a plane coordinate system is established on the "center line" of the hook ring image: the horizontal axis of the coordinate system is on the "center line", and the length of any object image that intersects with the hook ring on the horizontal axis is called the horizontal length; the origin of the coordinate system is located at the midpoint of the line segment of the horizontal length of the object; the vertical axis is perpendicular to the "center line", and the length of the line segment sandwiched by the upper and lower boundary red lines of the hook ring is called the longitudinal length. According to the principle of image transmission, any longitudinal length is equal to the height of the inner wall of the hook ring.
[0070] Furthermore, if the horizontal length is equal to the vertical length, the actual size of the object's actual width (thickness) is roughly the same, which is the actual height of the inner wall of the hook ring (even if there is some error, it can meet the engineering requirements). If the horizontal length is not equal to the vertical length, the actual width (thickness) of the object can be converted by the "height of the inner wall of the hook ring (ring height)" associated with the vertical length, and the actual width of the object in the ring can be known, wherein the conversion formula is:
[0071]
[0072] For example, Figure 3 As shown, in general, the average height of the hook is about 10 mm. If line segment ab = 10 mm, cd = 25 mm, then according to the transmission diagram principle, the actual height of the hook at ab and cd is 10 mm (vertical height). If the horizontal length of the green object = 1.2 × vertical length, then: If the horizontal length of the blue object = 0.9 × vertical length, then:
[0073] When the object is inside the hook ring but not close to the inner wall of the hook ring, as shown in the figure, AH is the distance from the center line of the ring wall to the camera, which has been measured before leaving the factory (the corresponding distance of the center line position); BC is the height of the hook ring; AJ is the distance from the center line of the object inside the ring to the camera, which can be measured by monocular vision depth estimation technology. Combined with the above-mentioned "object close to the inner wall of the hook ring" solution method, according to the characteristics of similar triangles, the actual width of the object inside the ring can be obtained. DE.
[0074]
[0075] If line segment AH = 100 mm, AJ = 70 mm, hook height is about 10 mm, horizontal length = 1.2 × vertical length, then the actual width of the object in the hook is:
[0076]
[0077] In this embodiment, when an object is found in the hook loop in the image, and the objects in the area block the first hook loop boundary and the second hook loop boundary, if the width of the object is close to (or greater than) the preset threshold, preferably, the preset threshold can be the height of the inner wall of the hook loop (this size can be adjusted according to the actual calculation coefficient), it can be determined that the hook loop is effectively hooked; if the width of the object is much smaller than the preset threshold, it can be determined that the hook loop is invalidly hooked.
[0078] In this embodiment, a (small-sized, low-energy-consuming, flash-equipped) miniature camera is installed on one side of the hook ring. First, an original photo without a hook is taken when there is no hook in the hook ring during the device (start-up process). Then, a working image is taken once a second in the working state, and the working image is compared and analyzed with the original image. The focus is on analyzing whether the upper and lower boundary lines of the hourglass-shaped part of the hook ring image are successively blocked by the image of the same object, so as to determine whether there is a penetrating hook object in the working state. At the same time, with the help of depth estimation technology, the actual size of the width of the object in the ring is estimated to determine whether the hook ring is effectively hooked. Thus, a reliable and effective detection of objects in the hook ring is achieved with small volume and low energy consumption, without any sense, in the entire region (in the trench), and in all categories (objects).
[0079] Implementing the above embodiments has the following effects:
[0080] The technical solution of the present invention obtains the image of the inner side of the hook ring in real time through the camera, and recognizes the image, so as to obtain the boundary features and objects of the hook ring in the image, determine the area of the hook ring blocked by the object, and then after the objects in the area block the first hook ring boundary and the second hook ring boundary, the hook ring is determined to be in a hung state, otherwise it is in an untied state, thereby avoiding the problem of low accuracy caused by using the existing detection of objects in the hook ring as a condition for judging whether the hook ring is in a hung state during aerial work and movement. At the same time, combined with the boundary features of the hook ring, it can further avoid the situation where the hook ring ineffectively hooks the object, thereby improving the accuracy of hook ring detection.
[0081] Embodiment 2
[0082] See also Figure 5 , which is a hook and loop hanging state recognition device based on image recognition provided by the present invention, comprising: an image acquisition module 201, an image recognition module 202 and a hanging state module 203;
[0083] The image acquisition module 201 is used to acquire the image of the inner side of the hook ring in real time through a camera; wherein the camera is arranged on one side of the hook ring;
[0084] The image recognition module 202 is used to recognize the image, obtain the boundary features of the hook and the object in the image, and determine the area of the hook blocked by the object according to the boundary features of the hook; wherein the boundary features include a first hook boundary and a second hook boundary;
[0085] The hook state module 203 is used to determine the hook as being in a hook state when the objects in the area block the first hook boundary and the second hook boundary; otherwise, the hook is determined to be in an unhooked state.
[0086] As a preferred solution, the real-time acquisition of the image of the inner side of the hook ring by a camera specifically includes:
[0087] Through a camera arranged at one side of the hook ring, an image of the inner side of the hook ring is acquired once every preset time.
[0088] As a preferred solution, before acquiring the boundary features and objects of the hook and loop in the image, the method specifically includes:
[0089] recognizing the image;
[0090] If no other objects except the hook in the image can be identified, it is determined that the hook is in an untied state.
[0091] As a preferred solution, the obtaining of boundary features and objects of the hook and loop in the image specifically includes:
[0092] When it is recognized that there is an object in the image, the upper boundary and the lower boundary of the hook in the image are identified, and the upper boundary is used as the first boundary feature and the lower boundary is used as the second boundary feature.
[0093] As a preferred solution, determining the area of the hook blocked by the object according to the boundary features of the hook specifically includes:
[0094] According to the boundary features of the hook ring, determining whether there is a disconnected position between the first boundary feature and the second boundary feature;
[0095] If there is and the object is in the disconnected position, the position is regarded as the area where the hook is blocked by the object;
[0096] If not, it is determined that the carabiner is in an untied state.
[0097] As a preferred solution, before determining the hook ring to be in the hanging state, the method further includes:
[0098] Acquire the depth feature of the object;
[0099] Determining whether the object is in close contact with the hook ring according to the capacitive sensing in the hook ring;
[0100] If the object is in close contact with the hook, a first actual width of the object is calculated according to the depth feature of the object, and when the first actual width is greater than a preset threshold, the hook is determined to be in a valid hanging state;
[0101] If the object is not close to the hook, the second actual width of the object is calculated based on the depth feature of the object and the distance from the camera to the hook, and when the second actual width is greater than a preset threshold, the hook is determined to be in a valid hanging state.
[0102] As a preferred solution, calculating the first actual width of the object according to the depth feature of the object specifically includes:
[0103] Acquire the horizontal length and the vertical length of the object in the image according to the depth feature of the object;
[0104] When the transverse length is equal to the longitudinal length, the inner wall height of the hook ring is used as the first actual width of the object;
[0105] When the transverse length is not equal to the longitudinal length, the actual width of the object is calculated based on the inner wall height of the hook ring and the transverse length and longitudinal length of the object as the first actual width.
[0106] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.
[0107] Implementing the above embodiments has the following effects:
[0108] The technical solution of the present invention obtains the image of the inner side of the hook ring in real time through the camera, and recognizes the image, so as to obtain the boundary features and objects of the hook ring in the image, determine the area of the hook ring blocked by the object, and then after the objects in the area block the first hook ring boundary and the second hook ring boundary, the hook ring is determined to be in a hung state, otherwise it is in an untied state, thereby avoiding the problem of low accuracy caused by using the existing detection of objects in the hook ring as a condition for judging whether the hook ring is in a hung state during aerial work and movement. At the same time, combined with the boundary features of the hook ring, it can further avoid the situation where the hook ring ineffectively hooks the object, thereby improving the accuracy of hook ring detection.
[0109] Embodiment 3
[0110] Correspondingly, the present invention also provides a terminal device, comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the hook and loop hanging state recognition method based on image recognition as described in any one of the above embodiments.
[0111] The terminal device of this embodiment includes: a processor, a memory, and a computer program and a computer instruction stored in the memory and executable on the processor. When the processor executes the computer program, each step in the above-mentioned embodiment 1 is implemented, for example: Figure 1 Alternatively, the processor implements the functions of each module / unit in the above device embodiment, such as the tethering status module 203, when executing the computer program.
[0112] Exemplarily, the computer program may be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments that can perform specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device. For example, the shackle state module 203 is used to determine the shackle as a shackle state when the objects in the area block the first shackle boundary and the second shackle boundary; otherwise, the shackle is determined to be an unshackle state.
[0113] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram is merely an example of a terminal device and does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown in the diagram, or may combine certain components, or different components. For example, the terminal device may also include an input / output device, a network access device, a bus, etc.
[0114] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and various interfaces and lines are used to connect various parts of the entire terminal device.
[0115] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile terminal, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Med ia Card, SMC), a secure digital (SecureDi gita l, SD) card, a flash card (F l ash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0116] Wherein, if the module / unit integrated in the terminal device 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 such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-On l yMemory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.
[0117] Embodiment 4
[0118] Correspondingly, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the hook and loop hanging state recognition method based on image recognition as described in any one of the above embodiments.
[0119] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.
Claims
1. A method for identifying the state of a hook and loop based on image recognition, characterized in that: Applications: Hook and loop, including: The image of the inner side of the hook ring is obtained in real time through a camera; wherein the camera is arranged on one side of the hook ring; Recognize the image, obtain the boundary features of the hook and the object in the image, and determine the area of the hook blocked by the object according to the boundary features of the hook; wherein the boundary features include a first hook boundary and a second hook boundary; When the objects in the area block the first hook boundary and the second hook boundary, the hook is determined to be in a tied state; otherwise, the hook is determined to be in an untied state.
2. The method for identifying the hook and loop state based on image recognition according to claim 1, characterized in that: The real-time acquisition of the image of the inner side of the hook ring by the camera specifically includes: Through a camera arranged at one side of the hook ring, an image of the inner side of the hook ring is acquired once every preset time.
3. The method for identifying the hook and loop state based on image recognition according to claim 1, characterized in that: Before acquiring the boundary features and objects of the hook loop in the image, the method specifically includes: recognizing the image; If no other objects except the hook in the image can be identified, it is determined that the hook is in an untied state.
4. The method for identifying the hook and loop state based on image recognition as claimed in claim 3, characterized in that: The obtaining of boundary features and objects of the hook loop in the image specifically includes: When it is recognized that there is an object in the image, the upper boundary and the lower boundary of the hook in the image are identified, and the upper boundary is used as the first boundary feature and the lower boundary is used as the second boundary feature.
5. The method for identifying the hook and loop state based on image recognition as claimed in claim 4, characterized in that: The determining, according to the boundary features of the hook, the area of the hook blocked by the object specifically includes: According to the boundary features of the hook ring, determining whether there is a disconnected position between the first boundary feature and the second boundary feature; If there is and the object is in the disconnected position, the position is regarded as the area where the hook is blocked by the object; If not, it is determined that the carabiner is in an untied state.
6. The method for identifying the hook and loop state based on image recognition according to claim 1, characterized in that: Before determining the hook ring as the hanging state, the method further includes: Acquire the depth feature of the object; Determining whether the object is in close contact with the hook ring according to the capacitive sensing in the hook ring; If the object is in close contact with the hook, a first actual width of the object is calculated according to the depth feature of the object, and when the first actual width is greater than a preset threshold, the hook is determined to be in a valid hanging state; If the object is not close to the hook, the second actual width of the object is calculated based on the depth feature of the object and the distance from the camera to the hook, and when the second actual width is greater than a preset threshold, the hook is determined to be in a valid hanging state.
7. A method for identifying the state of a hook and loop based on image recognition as claimed in claim 6, characterized in that: The calculating, according to the depth feature of the object, a first actual width of the object specifically includes: Acquire the horizontal length and the vertical length of the object in the image according to the depth feature of the object; When the transverse length is equal to the longitudinal length, the inner wall height of the hook ring is used as the first actual width of the object; When the transverse length is not equal to the longitudinal length, the actual width of the object is calculated based on the inner wall height of the hook ring and the transverse length and longitudinal length of the object as the first actual width.
8. A hook and loop hanging state recognition device based on image recognition, characterized in that: include: Image acquisition module, image recognition module and hanging status module; The image acquisition module is used to acquire the image of the inner side of the hook ring in real time through a camera; wherein the camera is arranged on one side of the hook ring; The image recognition module is used to recognize the image, obtain the boundary features of the hook and loop and the object in the image, and determine the area of the hook and loop blocked by the object according to the boundary features of the hook and loop; wherein the boundary features include a first hook and loop boundary and a second hook and loop boundary; The hook state module is used to determine the hook as being in a hook state when the objects in the area block the first hook boundary and the second hook boundary; otherwise, the hook is determined to be in an unhooked state.
9. A terminal device, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for identifying the hook and loop hanging state based on image recognition as described in any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the hook and loop hanging state recognition method based on image recognition as described in any one of claims 1 to 7.