Bed wetting detection method and device based on multi-band infrared imaging, terminal and medium

Abstract

This invention discloses a method, device, terminal, and medium for bedwetting detection based on multi-band infrared imaging, relating to the biomedical field. The method involves acquiring single-channel grayscale images of the object to be monitored from infrared cameras at various preset bands; assigning pixel values ​​to the single-channel grayscale images corresponding to each preset band to determine a pseudo-color composite image; calculating the ratio of the single-channel grayscale images corresponding to each preset band to determine a ratio image; and classifying the pseudo-color composite image and the ratio image to determine the bedwetting detection result. Because this invention uses single-channel grayscale images acquired by an infrared camera to detect bedwetting, it eliminates the need to place the detection device in a humid environment. Therefore, it effectively solves the problem of existing technologies that attach humidity sensors to underwear or diapers for bedwetting detection, making the humidity sensors susceptible to wear or corrosion and compromising the reliability of the detection results.

Description

Technical Field

[0001] This invention relates to the field of biomedicine, and more particularly to a method, device, terminal, and medium for detecting bedwetting based on multi-band infrared imaging. Background Technology

[0002] Bedwetting (enuresis) refers to involuntary urination during sleep, commonly seen in children and the elderly. Undetected bedwetting can lead to skin irritation, redness, itching, and even ulceration, increasing the risk of infection. Bedwetting detection can promptly remind caregivers to change clothes and sheets, ensuring hygiene and reducing the burden of care.

[0003] Existing bedwetting detection solutions mainly use humidity sensors, which are fixed to underwear or diapers by clamping or attaching, or by integrating electrodes directly into fabrics such as diapers or underwear. However, in both of these methods, the humidity sensors operate in humid environments for extended periods, making it difficult to guarantee their lifespan and reliability.

[0004] Therefore, existing technologies still need improvement and development. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a method, device, terminal and medium for bedwetting detection based on multi-band infrared imaging, which addresses the above-mentioned defects of the prior art. The aim is to solve the problem that the existing technology attaches the humidity sensor to underwear or diapers for bedwetting detection, making the humidity sensor susceptible to wear or corrosion and making it difficult to guarantee the reliability of the detection results.

[0006] The technical solution adopted by this invention to solve the problem is as follows:

[0007] In a first aspect, embodiments of the present invention provide a method for detecting bedwetting based on multi-band infrared imaging, wherein the method includes:

[0008] Acquire single-channel grayscale images of the monitored object captured by the infrared camera in each preset band;

[0009] Pixel values ​​are assigned to the single-channel grayscale images corresponding to each preset band to determine the pseudo-color composite image;

[0010] The ratio of the single-channel grayscale images corresponding to each preset band is calculated to determine the ratio image;

[0011] The bedwetting detection result is determined by classifying the pseudo-color composite image and the ratio image.

[0012] In one implementation method, pixel values ​​are assigned to the single-channel grayscale images corresponding to each preset band to determine the pseudo-color composite image, including:

[0013] The pixel values ​​of the single-channel grayscale image corresponding to the first preset band are assigned as red channel pixel values, the pixel values ​​of the single-channel grayscale image corresponding to the second preset band are assigned as green channel pixel values, and the pixel values ​​of the single-channel grayscale image corresponding to the third preset band are assigned as blue channel pixel values, thereby determining the pseudo-color composite image.

[0014] In one implementation method, the ratio of the single-channel grayscale images corresponding to each preset band is calculated to determine the ratio image, including:

[0015] Perform pixel registration on each of the single-channel grayscale images to determine the pixel registration image corresponding to each band;

[0016] The ratio image is determined by calculating the ratio of pixel values ​​at the same position in each pixel registration image.

[0017] In one implementation method, pixel registration is performed on each of the single-channel grayscale images to determine the pixel registration image corresponding to each preset band, including:

[0018] An optical flow algorithm is used to calculate the pixel displacement field between each single-channel grayscale image to determine each displacement vector.

[0019] The pixel-registered image is determined by remapping the single-channel grayscale images according to the displacement vectors.

[0020] In one implementation method, determining the ratio image involves calculating a ratio based on the pixel values ​​at the same position in each pixel registration image, including:

[0021] Obtain the water body absorption spectrum curve, and determine the absorption coefficient corresponding to each preset band based on the water body absorption spectrum curve.

[0022] The pixel registration image corresponding to the preset band with the smallest absorption coefficient is used as the first pixel registration image;

[0023] The pixel registration image corresponding to the preset band with the largest absorption coefficient is used as the second pixel registration image;

[0024] The ratio image is determined by calculating the ratio of pixel values ​​at the same position in the first pixel registration image and the second pixel registration image.

[0025] In one implementation method, determining the ratio image by calculating the ratio of pixel values ​​at the same position in the first pixel registration image and the second pixel registration image includes:

[0026] The ratio image is determined by calculating the ratio of pixel values ​​at the same position in the first pixel registration image and the second pixel registration image using a ratio calculation formula, wherein the ratio calculation formula is expressed as follows:

[0027] ,

[0028] The ratio image, Register the image for the first pixel. Register the image for the second pixel. These are the pixel coordinates.

[0029] In one implementation method, classifying the pseudo-color composite image and the ratio image to determine the bedwetting detection result includes:

[0030] The pseudo-color composite image is classified to determine the first classification result;

[0031] The ratio image is classified to determine the second classification result;

[0032] The bedwetting test result is determined based on the first classification result and the second classification result.

[0033] Secondly, embodiments of the present invention also provide a bedwetting detection device based on multi-band infrared imaging, wherein the bedwetting detection device based on multi-band infrared imaging includes: an image acquisition device and an image processing module, wherein the image acquisition device includes a support, a camera, and an infrared light plate, the camera is fixed on the support and located directly above the object to be monitored, and the infrared light plate is fixed on the camera; the image processing module includes:

[0034] The data acquisition module is used to acquire single-channel grayscale images of the monitored object collected by the infrared camera in each preset band.

[0035] The image synthesis module is used to assign pixel values ​​to the single-channel grayscale images corresponding to each preset band to determine the pseudo-color synthesized image;

[0036] The ratio calculation module is used to calculate the ratio of the single-channel grayscale image corresponding to each preset band and determine the ratio image.

[0037] The bedwetting detection module is used to classify the pseudo-color composite image and the ratio image to determine the bedwetting detection result.

[0038] Thirdly, embodiments of the present invention also provide a terminal, the terminal including a memory and one or more processors; the memory stores one or more programs; the programs include instructions for executing the bedwetting detection method based on multi-band infrared imaging as described above; the processor is used to execute the programs.

[0039] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a plurality of instructions, wherein the instructions are adapted to be loaded and executed by a processor to implement any of the above-described methods for detecting bedwetting based on multi-band infrared imaging.

[0040] The beneficial effects of this invention are as follows: In this embodiment, the invention acquires single-channel grayscale images of the object to be monitored from infrared cameras at various preset wavelengths; assigns pixel values ​​to the single-channel grayscale images corresponding to each preset wavelength to determine a pseudo-color composite image; calculates the ratio of the single-channel grayscale images corresponding to each preset wavelength to determine a ratio image; and classifies the pseudo-color composite image and the ratio image to determine the bedwetting detection result. Since this invention uses single-channel grayscale images acquired by an infrared camera to detect bedwetting, it eliminates the need to place the detection device in a humid environment. Therefore, it effectively solves the problem in existing technologies where humidity sensors are attached to underwear or diapers for bedwetting detection, making the humidity sensors susceptible to wear or corrosion and compromising the reliability of the detection results. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a schematic flowchart of the bedwetting detection method based on multi-band infrared imaging provided in an embodiment of the present invention.

[0043] Figure 2 This is a flowchart illustrating a specific implementation method 1 provided in this embodiment of the invention.

[0044] Figure 3 This is a flowchart illustrating a specific implementation method 2 provided in this embodiment of the invention.

[0045] Figure 4 This is a schematic diagram of the internal modules of the bedwetting detection device based on multi-band infrared imaging provided in an embodiment of the present invention.

[0046] Figure 5This is a schematic diagram of the image acquisition device of the bedwetting detection device based on multi-band infrared imaging provided in an embodiment of the present invention.

[0047] Figure 6 This is a schematic diagram of the image processing module of the bedwetting detection device based on multi-band infrared imaging provided in an embodiment of the present invention.

[0048] Figure 7 This is a schematic diagram of the terminal provided in an embodiment of the present invention. Detailed Implementation

[0049] This invention discloses a method, device, terminal, and medium for detecting bedwetting based on multi-band infrared imaging. To make the objectives, technical solutions, and effects of this invention clearer and more explicit, the invention is 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 for explaining the invention and are not intended to limit the invention.

[0050] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0051] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0052] Bedwetting (enuresis) refers to involuntary urination during sleep, commonly seen in children and the elderly. Undetected bedwetting can lead to skin irritation, redness, itching, and even ulceration, increasing the risk of infection. Bedwetting detection can promptly remind caregivers to change clothes and sheets, ensuring hygiene and reducing the burden of care.

[0053] Existing bedwetting detection solutions mainly use humidity sensors, which are fixed to underwear or diapers by clamping or attaching, or by integrating electrodes directly into fabrics such as diapers or underwear. However, in both of these methods, the humidity sensors operate in humid environments for extended periods, making it difficult to guarantee their lifespan and reliability.

[0054] To address the aforementioned shortcomings of existing technologies, this invention provides a bedwetting detection method based on multi-band infrared imaging. The method involves acquiring single-channel grayscale images of the object to be monitored from infrared cameras at various preset wavelengths; assigning pixel values ​​to the single-channel grayscale images corresponding to each preset wavelength to determine a pseudo-color composite image; calculating the ratio of the single-channel grayscale images corresponding to each preset wavelength to determine a ratio image; and classifying the pseudo-color composite image and the ratio image to determine the bedwetting detection result. Since this invention uses single-channel grayscale images acquired by an infrared camera to detect bedwetting, it eliminates the need to place the detection device in a humid environment. Therefore, it effectively solves the problem of existing technologies that attach humidity sensors to underwear or diapers for bedwetting detection, making the humidity sensors susceptible to wear or corrosion and compromising the reliability of the detection results.

[0055] Exemplary method:

[0056] like Figure 1 As shown, the method includes:

[0057] Step S100: Obtain the single-channel grayscale image corresponding to the object to be monitored, which is captured by the infrared camera in each preset band;

[0058] An image acquisition device is used to acquire single-channel grayscale images of the monitored object under infrared light of various preset wavelengths. The image acquisition device includes a support, an infrared light source panel, a camera, and a computing or control device. The infrared light source panel is mounted on the camera and is used to illuminate the object with infrared light of different preset wavelengths. Each wavelength of the infrared light is short-wavelength and meets safety standards. The center of the infrared light source panel is hollow, and the camera is fixed at the center of the panel. The camera is fixed on the support, positioned directly above the monitored object, and is used to acquire the single-channel grayscale image corresponding to the monitored object.

[0059] The objects to be detected are beds, tabletops, or various fabrics that may come into contact with urine. Since water absorbs light of different wavelengths to varying degrees, the physical property of urine's significant absorption characteristics in the short-wave infrared band is utilized to provide multi-dimensional information for subsequent analysis. A short-wave infrared camera acquires single-channel grayscale images of the object in each preset wavelength band: when the infrared light is in the first preset wavelength band, the infrared camera acquires the single-channel grayscale image corresponding to the first preset wavelength band; when the infrared light is in the second preset wavelength band, the infrared camera acquires the single-channel grayscale image corresponding to the second preset wavelength band, and so on. The number of preset wavelength bands and wavelengths can be set according to actual needs. Because the infrared camera maintains a certain distance from the object when acquiring single-channel grayscale images, it does not need to be placed close to the object, enabling non-contact, full-coverage, and real-time detection. It also offers advantages such as wide coverage and high user comfort, significantly improving the comfort, reliability, and intelligence level of the bedwetting monitoring system.

[0060] Step S200: Assign pixel values ​​to the single-channel grayscale images corresponding to each preset band to determine the pseudo-color composite image.

[0061] The single-channel grayscale images corresponding to each preset band are fused by assigning pixel values ​​to obtain a pseudo-color composite image. The pixel value assignment method involves assigning the pixel value of a specific channel in the pseudo-color composite image to the single-channel grayscale image corresponding to each preset band. Each preset band corresponds to one channel. Because the preset bands respond differently to moisture, the urine-soaked area will exhibit a more pronounced color difference in the fused pseudo-color composite image, thereby enhancing its visual distinction from the background and providing auxiliary information for subsequent identification and analysis.

[0062] In one implementation, pixel values ​​are assigned to the single-channel grayscale images corresponding to each preset band to determine the pseudo-color composite image, including:

[0063] Step S201: Assign the pixel value of the single-channel grayscale image corresponding to the first preset band to the red channel pixel value, assign the pixel value of the single-channel grayscale image corresponding to the second preset band to the green channel pixel value, and assign the pixel value of the single-channel grayscale image corresponding to the third preset band to the blue channel pixel value to determine the pseudo-color composite image.

[0064] The number of preset bands is set to three: a first preset band, a second preset band, and a third preset band. The single-channel grayscale image corresponding to the first preset band is assigned to the red channel (R channel) of the pseudo-color composite image; the single-channel grayscale image corresponding to the second preset band is assigned to the green channel (G channel) of the pseudo-color composite image; and the single-channel grayscale image corresponding to the third preset band is assigned to the blue channel (B channel) of the pseudo-color composite image, resulting in the fused pseudo-color composite image. The preset bands can be set to 1200nm, 1400nm, and 1500nm. The first, second, and third preset bands are different from each other and can each correspond to any one of the aforementioned bands; there is no specific restriction.

[0065] Step S300: Calculate the ratio of the single-channel grayscale images corresponding to each preset band to determine the ratio image.

[0066] Different preset wavelengths of light are absorbed by water to varying degrees. A ratio image is obtained by calculating the ratio of the single-channel grayscale images corresponding to each preset wavelength. This ratio image reflects the magnitude of the pixel value differences between preset wavelengths, amplifying the degree of light absorption by water across different wavelengths, thereby enhancing the numerical contrast of the wetted area.

[0067] In one implementation, the ratio calculation of the single-channel grayscale images corresponding to each preset band is performed to determine the ratio image, including:

[0068] Step S301: Perform pixel registration on each of the single-channel grayscale images to determine the pixel registration image corresponding to each band;

[0069] Step S302: Calculate the ratio of pixel values ​​at the same position in each pixel registration image to determine the ratio image.

[0070] The single-channel grayscale images corresponding to different preset wavelength bands were captured at different times. At different times, the object to be detected may move, causing the pixel positions of the same object in the single-channel grayscale images corresponding to different preset wavelength bands to differ. To accurately compare the pixel differences of the same object in single-channel grayscale images of different preset wavelength bands, such as... Figure 2 As shown, pixel registration is performed on each single-channel grayscale image to obtain the pixel registration image corresponding to each single-channel grayscale image. Then, the ratio of pixel values ​​at the same position in each pixel registration image is calculated to obtain a ratio image. This allows the ratio image to accurately reflect the response differences of different preset bands on the same item, thereby improving the accuracy of subsequent detection results.

[0071] In one implementation, pixel registration is performed on each of the single-channel grayscale images to determine the pixel-registered image corresponding to each preset band, including:

[0072] Step S3011: Calculate the pixel displacement field between each single-channel grayscale image using an optical flow algorithm, and determine each displacement vector;

[0073] Step S3012: Perform pixel remapping on each of the single-channel grayscale images according to each of the displacement vectors to determine the pixel registration image.

[0074] During the acquisition of each single-channel grayscale image, local misalignment may occur due to object displacement, imaging errors, or viewing angle differences. The pixel displacement field is a vector field describing the displacement of each pixel in the image from its initial position to the target. An optical flow algorithm is used to calculate the pixel displacement field (including the horizontal component) between each single-channel grayscale image. and vertical components The displacement vectors of each pixel are obtained. Based on the displacement vectors of each pixel, the pixels in each single-channel grayscale image are remapped to obtain the pixel registration image corresponding to each single-channel grayscale image.

[0075] In one implementation, pixel registration of each of the single-channel grayscale images to determine the pixel registration image corresponding to each preset band further includes: sorting the single-channel grayscale images according to the acquisition order of each single-channel grayscale image to determine the image sequence; using an optical flow algorithm to calculate the pixel displacement field between each single-channel grayscale image based on the image sequence to determine the displacement vector corresponding to each single-channel grayscale image; and performing pixel remapping on the single-channel grayscale images according to the displacement vector to determine the pixel registration image.

[0076] The specific implementation is as follows: The single-channel grayscale images are sorted according to their acquisition order, with the first acquired image listed first. Based on the image sequence, adjacent single-channel grayscale images are selected sequentially. The single-channel grayscale image with the smaller sequence number is designated as the first single-channel grayscale image, and the single-channel grayscale image with the larger sequence number is designated as the second single-channel grayscale image. An optical flow algorithm is used to calculate the pixel displacement field based on the first and second single-channel grayscale images, obtaining the displacement vector of the second single-channel grayscale image relative to the first single-channel grayscale image. Pixel remapping is then performed on the pixels in the second single-channel grayscale image based on the displacement vector to obtain a pixel-registered image. The Farneback optical flow algorithm can be used.

[0077] For example, suppose the acquisition sequence consists of single-channel grayscale images corresponding to preset wavelengths of 1200nm, 1400nm, and 1500nm, respectively. First, register the single-channel grayscale images corresponding to the preset wavelengths of 1200nm and 1400nm: use the single-channel grayscale image corresponding to the preset wavelength of 1200nm as the reference image and the single-channel grayscale image corresponding to the preset wavelength of 1400nm as the target image. Calculate the displacement vector based on the reference image and the target image, and then remap the pixels of the target image according to the displacement vector to obtain the pixels corresponding to the target image. The image to be registered is (i.e., the pixel registration image corresponding to the single-channel grayscale image of the 1400nm band); then, the pixel registration image corresponding to the preset 1400nm band or the single-channel grayscale image corresponding to the preset 1200nm band is selected as the reference image, and the single-channel grayscale image corresponding to the preset 1500nm band is used as the target image for registration: the displacement vector is calculated according to the reference image and the target image, and the pixel remapping of the target image is performed according to the displacement vector to obtain the pixel registration image corresponding to the target image (i.e., the pixel registration image corresponding to the preset 1500nm band).

[0078] In one implementation, a ratio image is determined by calculating the ratio of pixel values ​​at the same position in each pixel registration image, including:

[0079] Step S3021: Obtain the water body absorption spectrum curve, and determine the absorption coefficient corresponding to each preset band based on the water body absorption spectrum curve.

[0080] Step S3022: The pixel registration image corresponding to the preset band with the smallest absorption coefficient is taken as the first pixel registration image;

[0081] Step S3023: The pixel registration image corresponding to the preset band with the largest absorption coefficient is used as the second pixel registration image;

[0082] Step S3024: Calculate the ratio of pixel values ​​at the same position in the first pixel registration image and the second pixel registration image to determine the ratio image.

[0083] The water absorption spectrum curve reflects the degree to which infrared light of different wavelengths is absorbed by water (usually expressed by the absorption coefficient; the larger the absorption coefficient, the stronger the absorption). Based on the water absorption spectrum curve, the absorption coefficients corresponding to each preset wavelength band are obtained. The pixel registration image corresponding to the preset wavelength band with the smallest absorption coefficient is used as the first pixel registration image, and the pixel registration image corresponding to the preset wavelength band with the largest absorption coefficient is used as the second pixel registration image. A ratio calculation is performed on the pixels at the same position in the first and second pixel registration images to obtain a ratio image, thereby enhancing the numerical contrast of the urine-soaked area.

[0084] The process of determining a ratio image by calculating the ratio of pixel values ​​at the same position in the first pixel registration image and the second pixel registration image includes:

[0085] A ratio image is determined by calculating the ratio of pixel values ​​at the same position in the first pixel registration image and the second pixel registration image using a ratio calculation formula. The ratio calculation formula is expressed as follows:

[0086] ,

[0087] The ratio image, Register the image for the first pixel. Register the image for the second pixel. These are the pixel coordinates.

[0088] Because different wavelengths of infrared light have varying absorption responses to moisture, there are significant differences in brightness and color between the urine-wet areas in the first and second pixel registration images, while the differences are minimal in the non-urine-wet areas. By calculating the pixel ratios of the first and second pixel registration images, the regions showing difference (urine-wet areas) are highlighted. Since the non-urine-wet areas in both images are largely similar, the ratio calculation can eliminate the influence of patterns and textures in other non-urine-wet areas on the final image.

[0089] For example, among the three wavelength bands of 1200nm, 1400nm, and 1500nm, the 1500nm band shows a stronger response to moisture absorption, while the 1200nm band shows a relatively weaker response. Therefore, the pixel registration image corresponding to the 1500nm band is used as the second pixel registration image, and the pixel registration image corresponding to the 1200nm band is used as the first pixel registration image. Substituting the first and second pixel registration images into the ratio formula above yields the ratio image. The ratio image amplifies the moisture difference while eliminating the influence of patterns and textures in other non-urine-wet areas on the final image, making the urine-wet area appear as a darker area in the final image.

[0090] In one implementation, a ratio image can also be determined by calculating the ratios of pixel values ​​in each channel of the pseudo-color composite image. Specifically, this includes: performing pixel registration on each channel of the pseudo-color composite image to determine the pixel-registered pseudo-color composite image; and calculating the ratios of the pixel-registered pseudo-color composite image to determine the ratio image. Figure 3 As shown.

[0091] The process involves pixel registration of each channel pixel in the pseudo-color composite image to determine the pixel-registered pseudo-color composite image. This includes: calculating the pixel displacement field corresponding to each channel pixel in the pseudo-color composite image using an optical flow algorithm to determine the displacement vector corresponding to each channel pixel; and performing pixel remapping on each channel pixel based on each displacement vector to determine the registered pseudo-color composite image.

[0092] The ratio calculation of the pseudo-color composite image after pixel registration is performed to determine the ratio image, including: determining the first channel and the second channel based on the absorption coefficient corresponding to the preset band in the water absorption spectrum curve, wherein the first channel is the channel corresponding to the pseudo-color composite image assigned to the single-channel grayscale image of the preset band with the smallest absorption coefficient, and the second channel is the channel corresponding to the pseudo-color composite image assigned to the single-channel grayscale image of the preset band with the largest absorption coefficient; and determining the ratio image by calculating the ratio based on the pixel values ​​corresponding to the first channel and the pixel values ​​corresponding to the second channel using the ratio calculation formula.

[0093] Step S400: Classify the pseudo-color composite image and the ratio image to determine the bedwetting detection result.

[0094] In pseudo-color composite images, wet areas exhibit noticeable color differences. Detection results can be obtained based on the pseudo-color image. However, considering that the detection results of the pseudo-color image may be affected by patterns and textures in non-wet areas, leading to errors, a ratio image is used to obtain the corresponding detection results. By combining the detection results of the pseudo-color image and the ratio image, an accurate bedwetting detection result is obtained, facilitating judgment by nursing staff or subsequent system responses. Specifically, classifying the pseudo-color composite image and the ratio image to determine the bedwetting detection result includes: classifying the pseudo-color composite image to determine a first classification result; classifying the ratio image to determine a second classification result; and determining the bedwetting detection result based on the first and second classification results. K-means clustering algorithms can be used to classify the pixel values ​​of the pseudo-color composite image and the ratio image, achieving automatic segmentation between wet and non-wet areas.

[0095] Based on the above embodiments, the present invention also provides a bedwetting detection device based on multi-band infrared imaging, such as... Figure 4 As shown, the device includes: an image acquisition device 01 and an image processing module 02, wherein, as... Figure 5 As shown, the image acquisition device 01 includes a bracket 11, a camera 12, and an infrared light panel 13. The camera 12 is fixed on the bracket 11 and located directly above the object to be monitored. The infrared light panel 13 is fixed on the camera 12. Figure 6As shown, the image processing module 02 includes:

[0096] Data acquisition module 21 is used to acquire single-channel grayscale images of the monitored object collected by the infrared camera in each preset band.

[0097] Image synthesis module 22 is used to assign pixel values ​​to the single-channel grayscale images corresponding to each preset band to determine the pseudo-color synthesized image;

[0098] The ratio calculation module 23 is used to calculate the ratio of the single-channel grayscale image corresponding to each preset band and determine the ratio image.

[0099] The bedwetting detection module 24 is used to classify the pseudo-color composite image and the ratio image to determine the bedwetting detection result.

[0100] Image acquisition device 01 is used to acquire single-channel grayscale images of the object to be monitored under infrared light of various preset wavelengths. Image acquisition device 01 includes a bracket 11, an infrared light plate 13, a camera 12, and a computing or control device. The infrared light plate 13 is mounted on the camera 12 and is used to illuminate infrared light of different preset wavelengths. Each wavelength of the infrared light is short-wavelength and meets safety standards. The center of the infrared light plate 13 is hollow, and the camera 12 is fixed at the center of the infrared light plate 13. The camera 12 is fixed on the bracket 11, located directly above the object to be monitored, and is used to acquire single-channel grayscale images corresponding to the object to be monitored.

[0101] Based on the above embodiments, the present invention also provides a terminal, the principle block diagram of which can be as follows: Figure 7 As shown, the terminal includes a processor, memory, network interface, and display screen connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a bedwetting detection method based on multi-band infrared imaging. The display screen can be an LCD screen or an e-ink screen.

[0102] Those skilled in the art will understand that Figure 7 The schematic diagram shown is only a partial structural diagram related to the present invention and does not constitute a limitation on the terminal to which the present invention is applied. A specific terminal may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0103] In one implementation, the terminal's memory stores one or more programs, and these programs are configured to be executed by one or more processors, and the programs contain instructions for performing a bedwetting detection method based on multi-band infrared imaging.

[0104] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0105] In summary, this invention discloses a method, device, terminal, and medium for bedwetting detection based on multi-band infrared imaging. The method involves acquiring single-channel grayscale images of the object to be monitored from infrared cameras at various preset wavelengths; assigning pixel values ​​to the single-channel grayscale images corresponding to each preset wavelength to determine a pseudo-color composite image; calculating the ratio of the single-channel grayscale images corresponding to each preset wavelength to determine a ratio image; and classifying the pseudo-color composite image and the ratio image to determine the bedwetting detection result. Because this invention uses single-channel grayscale images acquired by an infrared camera to detect bedwetting, it eliminates the need to place the detection device in a humid environment. Therefore, it effectively solves the problem of existing technologies that attach humidity sensors to underwear or diapers for bedwetting detection, making the humidity sensors susceptible to wear or corrosion and compromising the reliability of the detection results.

[0106] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A method for urine bed detection based on multi-band infrared imaging, characterized in that, The method comprises: acquiring single-channel gray images corresponding to the to-be-monitored object collected by the infrared camera at each preset waveband; assigning pixel values to the single-channel gray images corresponding to each preset waveband to determine a pseudo-color composite image; performing ratio calculation on the single-channel gray images corresponding to each preset waveband to determine a ratio image; classifying according to the pseudo-color composite image and the ratio image to determine a urine bed detection result; performing ratio calculation on the single-channel gray images corresponding to each preset waveband to determine a ratio image, comprising: performing pixel registration on each single-channel gray image to determine a pixel-registered image corresponding to each waveband; performing ratio calculation on pixel values at the same position in each pixel-registered image to determine the ratio image; performing pixel registration on each single-channel gray image to determine a pixel-registered image corresponding to each preset waveband, comprising: calculating pixel displacement fields between the single-channel gray images by using an optical flow algorithm to determine displacement vectors; performing pixel remapping on the single-channel gray images according to the displacement vectors to determine the pixel-registered image; performing ratio calculation on pixel values at the same position in each pixel-registered image to determine a ratio image, comprising: acquiring a water body absorption spectrum curve, and determining absorption coefficients corresponding to each preset waveband according to the water body absorption spectrum curve; taking the pixel-registered image corresponding to the preset waveband with the smallest absorption coefficient as a first pixel-registered image; taking the pixel-registered image corresponding to the preset waveband with the largest absorption coefficient as a second pixel-registered image; performing ratio calculation on pixel values at the same position in the first pixel-registered image and the second pixel-registered image to determine the ratio image.

2. The multi-band infrared imaging based urine bed detection method of claim 1, wherein, assigning pixel values to the single-channel gray images corresponding to each preset waveband to determine a pseudo-color composite image, comprising: assigning pixel values of the single-channel gray image corresponding to a first preset waveband as red channel pixel values, assigning pixel values of the single-channel gray image corresponding to a second preset waveband as green channel pixel values, and assigning pixel values of the single-channel gray image corresponding to a third preset waveband as blue channel pixel values to determine the pseudo-color composite image.

3. The multi-band infrared imaging based urine bed detection method of claim 1, wherein, performing ratio calculation on pixel values at the same position in the first pixel-registered image and the second pixel-registered image to determine the ratio image, comprising: performing ratio calculation on pixel values at the same position in the first pixel-registered image and the second pixel-registered image according to a ratio calculation formula to determine the ratio image, wherein the ratio calculation formula is represented as: ， is the ratio image, is the first pixel registration image, is the second pixel registration image, is the pixel point coordinate.

4. The multi-band infrared imaging based urine bed detection method of claim 1, wherein, classifying according to the pseudo-color composite image and the ratio image to determine a urine bed detection result, comprising: classifying the pseudo-color composite image to determine a first classification result; classifying the ratio image to determine a second classification result; determining the urine bed detection result according to the first classification result and the second classification result.

5. A multi-band infrared imaging based bed wetting detection apparatus, characterized in that, The device is used to implement the urine bed detection method based on multi-band infrared imaging according to any one of claims 1-4, and the device comprises an image acquisition device and an image processing module, wherein the image acquisition device comprises a support, a camera and an infrared light lamp plate, the camera is fixed on the support and located directly above the object to be monitored, and the infrared light lamp plate is fixed on the camera; the image processing module comprises: a data acquisition module configured to acquire single-channel grayscale images of the object to be monitored collected by the infrared camera at each preset waveband; an image synthesis module configured to assign pixel values to the single-channel grayscale images corresponding to each preset waveband to determine a pseudo-color composite image; a ratio calculation module configured to perform ratio calculation on the single-channel grayscale images corresponding to each preset waveband to determine a ratio image; a urine bed detection module configured to classify according to the pseudo-color composite image and the ratio image to determine a urine bed detection result.

6. A terminal, characterized by comprising: The terminal comprises a memory and one or more processors; the memory stores one or more programs; the programs contain instructions for executing the urine bed detection method based on multi-band infrared imaging according to any one of claims 1-4; and the processors are configured to execute the programs.

7. A computer-readable storage medium storing a plurality of instructions thereon, characterized in that, The instructions are loaded and executed by the processor to implement the steps of the urine bed detection method based on multi-band infrared imaging according to any one of claims 1-4.

Images