A method and device for detecting bedding coverage

Abstract

This application provides a method and apparatus for detecting bedding coverage, relating to the field of thermal imaging technology, which can improve the accuracy of bedding coverage detection. The method includes: acquiring a thermal imaging image of an infrared detection area; performing human posture recognition on the thermal imaging image to obtain the human posture recognition result of the target human body; if the human posture recognition result of the target human body is a lying position, determining the human body region corresponding to the target human body in the thermal imaging image; and using the ratio between the number of pixels in the human body region with a temperature value less than a temperature threshold and the total number of pixels in the human body region as the bedding coverage rate of the target human body.

Description

Technical Field

[0001] This application relates to the field of thermal imaging technology, and in particular to a method and apparatus for detecting bedding coverage. Background Technology

[0002] When a person is asleep, due to the suitability of the sleep environment or personal sleep habits, they may unconsciously kick off the covers. Without the warmth of a blanket, they may catch a cold. Infants and young children are more likely to kick off their covers and get sick.

[0003] Existing technology provides an alarm that uses a temperature detector. Based on the temperature signal detected by the temperature detector located on the person being monitored, if the person kicks off the blanket, the temperature detected by the temperature detector will drop because there is no blanket to keep them warm. At this time, the alarm will sound an alarm to the caregiver's device.

[0004] However, this method cannot detect immediately whether the subject has kicked off the covers. By the time it issues an alarm, the subject's body temperature has already dropped for some time, and those with poor health may have already caught a chill. Furthermore, this method requires the subject to wear certain detection equipment, which can cause discomfort and disrupt sleep. Summary of the Invention

[0005] This application provides a method and apparatus for detecting bedding coverage, which improves the accuracy of bedding coverage detection.

[0006] In a first aspect, embodiments of this application provide a method for detecting bedding coverage, the method comprising: acquiring a thermal imaging image of an infrared detection area; performing human posture recognition on the thermal imaging image to obtain the human posture recognition result of the target human body; when the human posture recognition result of the target human body is a lying posture, determining the human body region corresponding to the target human body in the thermal imaging image; and using the ratio between the number of pixels in the human body region whose temperature value is less than a temperature threshold and the total number of pixels in the human body region as the bedding coverage rate of the target human body.

[0007] The bedding coverage detection method provided in this application has at least the following beneficial effects: Firstly, this method can detect the number of all pixels within a human body area whose temperature is below a threshold. These pixels can constitute the area within the human body area covered by bedding. Therefore, this application can calculate the bedding coverage of the target human body relatively accurately by utilizing the temperature values ​​of each pixel within the entire human body area. Secondly, this method is based on thermal imaging images and is not affected by light intensity. It can detect bedding coverage both day and night, and has higher practicality and universality.

[0008] In some embodiments, the temperature threshold is determined as follows: the maximum body temperature of the target human body is determined based on the temperature values ​​of each pixel within the human body region; the ambient temperature is determined based on the temperature values ​​of each pixel in other regions of the thermal imaging image besides the human body region; and the temperature threshold is determined based on the ambient temperature and the maximum body temperature of the target human body.

[0009] In some embodiments, the temperature threshold satisfies the following relationship:

[0010]

[0011] Among them, T h T is the temperature threshold. v For ambient temperature, T m It is the highest temperature in the human body.

[0012] In some embodiments, the method further includes: determining that the target person has kicked off the blanket when the blanket coverage rate is less than or equal to a preset blanket coverage rate threshold; or determining that the target person has not kicked off the blanket when the blanket coverage rate is greater than the preset blanket coverage rate threshold.

[0013] In some embodiments, the method further includes: issuing an alarm message when the bedding coverage rate is less than or equal to a preset bedding coverage rate threshold and the ambient temperature of the infrared detection area is lower than a preset ambient temperature, the alarm message being used to alert the target human body to the situation of kicking off the bedding.

[0014] Secondly, a device for detecting bedding coverage is provided. The device includes: an acquisition unit for acquiring a thermal imaging image of an infrared detection area; an identification unit for performing human posture recognition on the thermal imaging image to acquire the human posture recognition result of the target human body; and a processing unit for determining the human body region corresponding to the target human body in the thermal imaging image when the human posture recognition result of the target human body is a lying position; and using the ratio between the number of pixels in the human body region with a temperature value less than a temperature threshold and the total number of pixels in the human body region as the bedding coverage rate of the target human body.

[0015] In some embodiments, the processing unit is specifically configured to: determine the maximum body temperature of the target human body based on the temperature values ​​of each pixel point within the human body region; determine the ambient temperature based on the temperature values ​​of each pixel point in other regions of the thermal imaging image besides the human body region; and determine a temperature threshold based on the ambient temperature and the maximum body temperature of the target human body.

[0016] In some embodiments, the temperature threshold satisfies the following relationship:

[0017]

[0018] Among them, T hT is the temperature threshold. v For ambient temperature, T m It is the highest temperature in the human body.

[0019] In some embodiments, the processing unit is further configured to: determine that the target human body has kicked off the blanket when the blanket coverage rate is less than or equal to a preset blanket coverage rate threshold; or determine that the target human body has not kicked off the blanket when the blanket coverage rate is greater than the preset blanket coverage rate threshold.

[0020] In some embodiments, the bedding coverage detection device further includes an alarm unit, which is used to issue an alarm message when the bedding coverage is less than or equal to a preset bedding coverage threshold and the ambient temperature of the infrared detection area is lower than a preset ambient temperature. The alarm message is used to indicate that the target human body has kicked off the bedding.

[0021] In some embodiments, the acquisition unit is specifically used to: acquire level data obtained by infrared detection of the infrared detection area; perform resolution conversion processing on the level data according to the resolution of the thermal imaging device to obtain the original thermal imaging image of the infrared detection area; and perform homogenization processing, noise reduction processing, filtering processing and enhancement processing on the original thermal imaging image in sequence to obtain the thermal imaging image of the infrared detection area.

[0022] Thirdly, a bedding coverage detection device is provided, the device comprising: one or more processors and one or more memories; wherein the one or more memories are used to store computer program code, the computer program code including computer instructions, and when the one or more processors execute the computer instructions, the bedding coverage detection device performs the method provided in any of the first aspects above.

[0023] Fourthly, a computer-readable storage medium is provided, comprising computer instructions that, when executed on a computer, cause the computer to perform the method provided in any of the first aspects above.

[0024] Fifthly, a computer program product containing computer instructions is provided, which, when executed on a computer, causes the computer to perform any of the methods provided in the first aspect above.

[0025] The technical effects of any of the possible solutions in the second to fifth aspects mentioned above can be referred to the corresponding beneficial effects analysis in the first aspect, and will not be repeated here. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of the composition of a thermal imaging device provided in an embodiment of this application;

[0027] Figure 2This is a schematic diagram illustrating the deployment of a thermal imaging device according to an embodiment of this application;

[0028] Figure 3 A schematic diagram of a smart home system provided in an embodiment of this application;

[0029] Figure 4 A schematic diagram of another smart home system provided in an embodiment of this application;

[0030] Figure 5 A flowchart illustrating a method for detecting bedding coverage provided in an embodiment of this application;

[0031] Figure 6 A flowchart illustrating another method for detecting bedding coverage provided in an embodiment of this application;

[0032] Figure 7 A flowchart of an algorithm for generating thermal imaging images provided in an embodiment of this application;

[0033] Figure 8 This is a schematic diagram of a human body region in a thermal imaging image provided in an embodiment of this application;

[0034] Figure 9 A schematic diagram of a convolution-pooling unit provided in an embodiment of this application;

[0035] Figure 10 A schematic diagram illustrating the composition of a pose recognition model provided in an embodiment of this application;

[0036] Figure 11 A flowchart illustrating another method for detecting bedding coverage provided in an embodiment of this application;

[0037] Figure 12 A flowchart illustrating another method for detecting bedding coverage provided in an embodiment of this application;

[0038] Figure 13 A schematic diagram illustrating the composition of a bedding coverage detection device provided in an embodiment of this application;

[0039] Figure 14 This is a schematic diagram of the hardware structure of a bedding coverage detection device provided in an embodiment of this application. Detailed Implementation

[0040] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0041] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0042] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "connected" and "linked" should be interpreted broadly, for example, as a fixed connection, a detachable connection, or an integral connection. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances. Furthermore, when describing pipelines, the terms "connected" and "linked" as used in this application have the meaning of establishing electrical connection. The specific meaning needs to be understood in conjunction with the context.

[0043] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0044] To facilitate understanding, we will first provide a brief introduction and explanation of some terms or basic concepts of technology involved in the embodiments of the present invention.

[0045] Existing technology provides a method for determining blanket-kicking behavior based on thermal imaging technology. This method identifies the location of joint points in each thermal imaging image; determines the temperature value of each joint point location based on its grayscale value; and determines whether blanket-kicking behavior has occurred based on the number of target thermal imaging images with a temperature value lower than a first preset threshold.

[0046] The aforementioned prior art determines the bedding coverage of a target human body based on the temperature value of the joint position of the target human body in the thermal imaging image, which is less than a temperature threshold, and thus determines whether the target human body has kicked off the blanket.

[0047] In view of this, embodiments of this application provide a method for detecting bedding coverage, which involves acquiring a thermal imaging image of an infrared detection area; determining the human body region corresponding to the target human body in the thermal imaging image; and determining the bedding coverage of the target human body based on the number of pixels in the human body region whose temperature values ​​are less than a temperature threshold and the total number of pixels in the human body region.

[0048] The technical solution provided in this application extracts the human body region corresponding to the target human body from the thermal imaging image within the infrared detection area, and then determines the bedding coverage rate of the target human body based on the temperature values ​​of each pixel in the human body region. Unlike existing methods that determine the bedding coverage of the target human body solely based on temperature values ​​below a temperature threshold at the joint positions of the target human body in the thermal imaging image, the method provided in this application can calculate the bedding coverage rate of the target human body more accurately. Furthermore, based on the bedding coverage rate, it is also possible to more accurately determine whether the target human body has kicked off the blankets.

[0049] Infrared thermal imaging technology is a technique that uses photoelectric technology to detect infrared signals in a specific band that emit thermal radiation from an object. This signal is then converted into images and graphics that can be distinguished by human vision, displaying the temperature distribution on the object's surface in different colors. Infrared thermal imaging technology allows humans to overcome visual barriers, enabling them to "see" the temperature distribution on an object's surface.

[0050] In this embodiment, the thermal imaging device is an infrared camera that can detect infrared energy (heat) non-contactly, convert it into an electrical signal, and generate a thermal image and temperature value. It can also calculate the temperature value. For example, the thermal imaging device can be a thermal imaging camera, an infrared thermal imager, a far-infrared thermal imager, a handheld thermal imager, or other devices that support infrared imaging.

[0051] For example, Figure 1 A schematic diagram of a thermal imaging device is shown. During the detection process, the detector can perform infrared detection on the target through a lens to obtain the target's raw data (i.e., electrical signals). The main control board can then generate a thermal image of the target based on the raw data. Optionally, the main control board can also calculate the target's temperature value based on the raw data.

[0052] Furthermore, in practical use, the deployment of thermal imaging equipment needs to be tailored to the specific purpose. For example, when caring for young children, the elderly, or patients, the thermal imaging equipment can be deployed at a suitable location and angle within their bedroom, ensuring the bed is within the infrared detection area of ​​the equipment. This will allow the thermal imaging image acquired within the detection area to show the sleeping child, elderly person, or patient. For example,... Figure 2 As shown, thermal imaging equipment can be deployed on home appliances (such as air conditioners) in the bedroom.

[0053] like Figure 3As shown, this application provides a smart home system based on a home environment. The system includes a thermal imaging device, a server, and smart home devices. The server can establish connections with both the smart home devices and the thermal imaging device to enable communication. It should be understood that the connection method can be wireless or wireless connection, and is not limited thereto. In some embodiments, the smart home devices can also directly connect to the thermal imaging device.

[0054] For example, the server in this application embodiment can be a device with data processing and data storage capabilities. For example, it can be a single server, a server cluster consisting of multiple servers, or a cloud computing service center; there is no limitation thereto. Optionally, the server...

[0055] For example, the smart home devices in this application embodiment can be devices that can access a home wireless local area network, such as televisions, smart speakers, water heaters, cameras, air conditioners, refrigerators, smart curtains, table lamps, chandeliers, rice cookers, and security devices (such as smart electronic locks). The smart home devices may also include a wireless fidelity (WIFI) module to enable access to the home wireless local area network.

[0056] In some embodiments, such as Figure 4 As shown, Figure 3 The system shown may also include terminal devices. Terminal devices can be mobile phones, tablets, desktops, laptops, handheld computers, notebook computers, ultra-mobile personal computers (UMPCs), netbooks, as well as cellular phones, personal digital assistants (PDAs), augmented reality (AR) / virtual reality (VR) devices, etc. This disclosure does not impose any special limitations on the specific form of the terminal device. It can interact with users through one or more methods such as a keyboard, touchpad, touchscreen, remote control, voice interaction, or handwriting devices.

[0057] When the server detects that a target person has kicked the blanket, it can send an alarm message to the terminal device so that the terminal device can promptly remind the user that the target person has kicked the blanket.

[0058] The subject of the test method for bedding coverage provided in this application embodiment is a bedding coverage detection device, or it can be a functional module and / or functional entity in the bedding coverage detection device that can realize the bedding coverage detection method. The specific implementation can be determined according to actual usage requirements, and this embodiment of the invention does not limit it.

[0059] In some embodiments, the bedding coverage detection device provided in this application can be the one described above. Figure 3 The thermal imaging device in the system shown above Figure 3 The smart home devices in the system shown above Figure 3 The system shown can be a server, or other device connected to the thermal imaging equipment and capable of data processing. When the thermal imaging equipment is integrated into a smart home device, the bedding coverage detection device provided in this application can also be used for smart home devices that integrate thermal imaging equipment.

[0060] In the following embodiments, the method for detecting bedding coverage using a thermal imaging device is used as an example. The specific process of the bedding coverage detection method is described below with reference to the accompanying drawings.

[0061] like Figure 5 As shown in the figure, this application provides a method for detecting bedding coverage.

[0062] S101. Acquire thermal imaging images of the infrared detection area.

[0063] The infrared detection area refers to the area that thermal imaging equipment can detect.

[0064] Based on thermal imaging equipment pre-deployed in areas where bedding coverage needs to be detected (such as areas where children, the elderly, or patients sleep), the thermal imaging equipment can obtain thermal imaging images of the areas where bedding coverage needs to be detected, namely, thermal imaging images of the aforementioned infrared detection areas.

[0065] Therefore, if a person appears within the infrared detection area, the thermal imaging image will include the person's thermal image. Thus, the bedding coverage of the target person can be detected based on this thermal imaging image.

[0066] In one implementation, such as Figure 6 As shown, step S101 can be specifically implemented as follows:

[0067] S1011. Obtain the level data obtained by infrared detection of the infrared detection area.

[0068] Specifically, the electromagnetic signal received by the thermal imaging device, reflected back after contacting an object within the infrared detection area by the electromagnetic waves emitted by the thermal imaging device, is converted into a 16-bit level signal. It should be understood that because the thermal imaging device can emit electromagnetic waves for an extended period, the aforementioned level data can be generated in multiple frames.

[0069] In addition, level data obtained from detection within the infrared detection area can be acquired at a fixed frequency.

[0070] The fixed frequency can be 10 milliseconds / time, 50 milliseconds / time, 0.01 seconds / time, or other reasonable frequencies. Thermal imaging data refers to the detection of an infrared detection area and the reception of the level data of that area.

[0071] S1012. Based on the resolution of the thermal imaging device, perform resolution conversion processing on the level data to obtain the original thermal imaging image of the infrared detection area.

[0072] After obtaining the level data of the infrared detection area at the current moment, the level data at the current moment can be restored into an image size matrix with the same resolution as the thermal imaging device, based on the resolution of the thermal imaging device, to obtain the original thermal imaging image of the infrared detection area at the current moment.

[0073] S1013. The original thermal imaging image is subjected to homogenization, noise reduction, filtering and enhancement processes in sequence to obtain the thermal imaging image of the infrared detection area.

[0074] The following section provides a detailed explanation of the processing operations for the original thermal imaging images.

[0075] 1. Homogenization treatment

[0076] After obtaining the original thermal image of the infrared detection area at the current moment, the original thermal image can be homogenized to generate a clearer infrared thermal image.

[0077] The homogenization process includes one or more of the following: removal of defective spots, correction, and removal of the lid.

[0078] Understandably, thermal imaging images differ from other images (such as color images) in that they contain significant noise. The most noticeable noise is called bad pixels, which are pixels in a thermal imaging image whose grayscale values ​​are significantly different from those of their surrounding pixels. If these bad pixels are not identified and removed, the denoising effect of the thermal imaging image will be affected. Therefore, it is necessary to remove bad pixels from the original thermal imaging image.

[0079] In some embodiments, the bad pixel removal process is performed by replacing the average value of the nine neighboring non-bad pixels around the bad pixel.

[0080] Due to current limitations in technology and software, thermal imaging equipment cannot automatically adjust its detection parameters based on external temperature and humidity. Therefore, after the thermal imaging equipment has been running for a period of time, or when the user observes changes in external temperature or humidity, it is necessary to use a shield to cover the lens and adjust the detection parameters according to the existing environment to achieve suitable detection results. Without adjusting the detection parameters using a shield, irregular gray backgrounds or horizontal and vertical stripes will appear during thermal imaging, necessitating correction processing of the original thermal image.

[0081] In some embodiments, the correction process employs a two-point correction method to process the original thermal imaging image. This two-point correction method transforms the response characteristic curves of all detection units into a single, identical response characteristic curve through rotation and translation. After correction, under uniform radiation input, the output electrical signals of each detection unit are identical, thereby eliminating the non-uniformity noise of the original thermal imaging image. This not only compensates for the gain coefficient of the thermal imaging device but also corrects the bias coefficient.

[0082] In some embodiments, the process of the above two-point correction method can satisfy the following formula (1):

[0083] Y=A(XB) Formula (1)

[0084] Where Y is the corrected level data, X is the original level data, B is the original baffle data, and A is the sensitivity correction coefficient.

[0085] After correction processing, the original thermal image will be more uniform.

[0086] In some embodiments, after removing bad pixels and correcting the original thermal imaging image, the original thermal imaging image may also be subjected to a process to remove the lid.

[0087] For thermal imaging equipment, a single calibration based on a reference radiation source can usually effectively compensate for the system response inhomogeneities introduced by the optical system, detector, and post-processing circuitry. However, with the switching of the field of view, focusing, and the influence of factors such as ambient temperature, shock, and vibration, the inhomogeneities introduced by the optical system can change significantly. This often results in thermal images output by the equipment exhibiting a dark center and bright edges and corners, a phenomenon known as the "pot lid effect." The pot lid effect is essentially a result of the ineffective compensation for the inhomogeneities introduced by the optical system of the thermal imaging equipment; it is a specific type of noise introduced by the optical system.

[0088] The purpose of removing the "pot lid" effect from the original thermal imaging image is to avoid the phenomenon of a dark center and bright edges and corners in the thermal imaging image, thereby improving the uniformity of the thermal imaging image.

[0089] After the above-mentioned processes of removing bad pixels, correction, and removing the lid, a relatively uniform original thermal imaging image can be obtained.

[0090] 2. Noise Reduction Processing

[0091] After homogenizing the original thermal image, further noise reduction processing can be performed. Noise reduction of the original thermal image can be divided into temporal noise reduction and spatial noise reduction.

[0092] Optionally, temporal noise reduction employs a multi-frame filtering method, performing low-pass filtering on corresponding pixels at the same location across multiple consecutive frames. Temporal noise reduction can also be understood as a noise reduction operation.

[0093] Low-pass filtering is a filtering method that allows low-frequency signals to pass through normally, while blocking or attenuating high-frequency signals exceeding a set threshold. However, the degree of blocking or attenuation varies depending on the frequency and the specific filtering procedure (purpose). Simply put, low-pass filtering sets a frequency point; signals with frequencies higher than this point cannot pass through. In digital signals, this frequency point is the cutoff frequency. When the frequency exceeds this cutoff frequency, all signals are assigned a value of 0. Because this process allows low-frequency signals to pass through while restricting high-frequency signals, it aims to eliminate noise, interference, and texture.

[0094] Optionally, spatial noise reduction employs Gaussian filtering to ensure image smoothness. Spatial noise reduction can also be understood as the removal of vertical stripes.

[0095] Gaussian filtering is a linear smoothing filter suitable for eliminating Gaussian noise and widely used in image processing noise reduction. Simply put, Gaussian filtering is a weighted average process applied to the entire image; the value of each pixel is obtained by weighting its own value and the values ​​of its neighboring pixels.

[0096] The specific operation of Gaussian filtering is as follows: scan each pixel in the thermal imaging image with a template (or convolution, mask), and replace the value of the central pixel of the template with the weighted average gray value of the pixels in the neighborhood determined by the template.

[0097] Low-pass filtering and Gaussian filtering of the original thermal imaging image can improve the signal-to-noise ratio of the original thermal imaging image, making it easier to extract.

[0098] The noise reduction and vertical stripe removal operations described above can be understood as performing uniformity correction on the original thermal imaging image. Compared to non-uniformity correction, noise reduction and vertical stripe removal focus more on processing the image itself, while non-uniformity correction processes the detector of the thermal imaging device.

[0099] 3. Filtering

[0100] After homogenizing and denoising the original thermal imaging image, further filtering can be performed on the original thermal imaging image.

[0101] Optionally, filtering may include bilateral filtering.

[0102] Bilateral filtering is a non-linear filtering method that combines spatial proximity and pixel value similarity in an image. It considers both spatial information and grayscale similarity to achieve edge-preserving noise reduction, and is characterized by its simplicity, non-iterative nature, and locality. Applying bilateral filtering to the original thermal imaging image yields the base layer image of the thermal imaging image.

[0103] The advantage of bilateral filtering is its ability to preserve edges. While Gaussian filtering for noise reduction significantly blurs edges and doesn't effectively preserve high-frequency details, bilateral filtering, as the name suggests, adds a Gaussian variance (sigma⁻d) to Gaussian filtering. This variance is based on a spatially distributed Gaussian filtering function, so near edges, distant pixels don't significantly affect the pixel values ​​at the edges, thus preserving the pixel values ​​near the edges.

[0104] However, because it preserves too much high-frequency information, bilateral filtering cannot completely remove high-frequency noise in the image; it can only effectively filter low-frequency information. Therefore, after obtaining the base layer image of the thermal imaging image by bilateral filtering of the original thermal imaging image, enhancement processing is still required on the base layer image.

[0105] 4. Enhanced processing

[0106] After homogenizing, denoising, and filtering the original thermal imaging image to obtain the base layer image, further enhancement processing can be performed on the base layer image of the thermal imaging image.

[0107] Enhancing the base layer image of a thermal imaging image can include the following two aspects.

[0108] On one hand, differential processing can be performed on the base layer image of the thermal imaging image to separate high-frequency data from the base layer image, thereby obtaining the detail layer image of the thermal imaging image. Then, high-frequency magnification processing can be performed on the detail layer image of the thermal imaging image to obtain the enhanced detail layer image of the thermal imaging image.

[0109] On the other hand, histogram processing can be performed on the base layer image of the thermal imaging image to improve the contrast of the thermal imaging image, so as to obtain the base layer image of the enhanced thermal imaging image.

[0110] Histogram processing is used to improve the contrast of thermal imaging images. By homogenizing and denoising the original thermal imaging image, image homogenization and noise reduction are achieved. However, the details of the image cannot be observed intuitively, so histogram processing is required on the base layer image of the thermal imaging image.

[0111] Histogram processing is an image enhancement method that expands the dynamic range and enhances contrast of an image by distributing the probability of grayscale values ​​as evenly as possible. From one perspective, histogram processing reduces the original information of an image, primarily in grayscale. However, from an observational standpoint, full grayscale information can be detrimental to viewing. Histogram processing can stretch the grayscale values ​​of interest while compressing those of less interest, thus improving contrast.

[0112] In this embodiment, histogram processing employs a 14-bit to 8-bit conversion to remove and compress areas with few gray levels, stretch areas with many gray levels, and obtain the corresponding stretching coefficient using the gray level data from the previous frame, which is then applied to the image in the next frame. The stretching coefficient is replaced in real time to ensure the stretching effect.

[0113] Since the background and noise occupy a large number of gray levels, while the target has fewer gray levels, histogram equalization effectively increases the contrast of the background and noise while decreasing the contrast of the target. In this embodiment, simply performing histogram processing on the original thermal imaging image may result in flickering, excessive darkness, or excessive light. In such cases, a platform histogram equalization algorithm can be used. The platform histogram equalization algorithm modifies the image histogram by selecting an appropriate platform threshold, thereby moderately suppressing the background and noise.

[0114] When processing raw thermal imaging images using the platform histogram equalization algorithm, a peak smoothing parameter can be added. By changing the peak suppression width, the image stretching intensity can be altered. Smoothing and multi-frame processing are employed when acquiring the image's peak to avoid image oscillations caused by drastic peak changes. This approach effectively improves image contrast while maintaining image uniformity and preventing image flicker.

[0115] It should be noted that noise, such as impulse noise and salt noise, is inevitably introduced during the thermal imaging process. Due to the low contrast of thermal images, this noise often affects human pose detection and can lead to a high false alarm rate. In some cases, bright objects or noise points often appear in the background environment. Therefore, by combining the base layer image and detail layer image of the enhanced thermal image obtained from the above two aspects, a clearer thermal image of the infrared detection area at the current moment can be obtained.

[0116] The following is combined Figure 7 The flowchart of the thermal imaging image algorithm shown illustrates the imaging process of thermal imaging images in the embodiments of this application.

[0117] For example, after obtaining the original 16-bit level data of the infrared detection area at the current moment, the original 16-bit level data is converted into an image size matrix of equal resolution according to the resolution of the thermal imaging device, so as to obtain the original thermal imaging image of the infrared detection area at the current moment.

[0118] Furthermore, the original thermal imaging image was processed to remove bad pixels, perform correction processing, and remove the pot lid, resulting in a more uniform original thermal imaging image.

[0119] Furthermore, temporal and spatial denoising are performed on the relatively uniform original thermal imaging image to obtain a high signal-to-noise ratio original thermal imaging image. Temporal denoising employs multi-frame filtering, while spatial denoising uses Gaussian filtering.

[0120] Furthermore, the original thermal imaging image with high signal-to-noise ratio is subjected to bilateral filtering to obtain the base layer image of the thermal imaging image.

[0121] Furthermore, the base layer image of the thermal imaging image can be enhanced. This enhancement process can include two aspects.

[0122] On the one hand, the base layer image of the thermal imaging image can be processed by plateau histogram to improve the contrast of the thermal imaging image, thus obtaining an enhanced base layer image of the thermal imaging image.

[0123] On the other hand, differential processing can be performed on the base layer image of the thermal imaging image to separate high-frequency data and obtain the detail layer image of the thermal imaging image. Furthermore, the detail layer image of the thermal imaging image can be subjected to high-frequency magnification processing to obtain an enhanced detail layer image of the thermal imaging image.

[0124] Furthermore, by combining the base layer image and the detail layer image of the enhanced thermal imaging image, a clearer thermal imaging image can be obtained.

[0125] S102. If the target human body's posture recognition result is a lying position, determine the human body region corresponding to the target human body in the thermal imaging image.

[0126] The aforementioned target human body refers to a human body located within the infrared detection area. Therefore, the aforementioned human body area refers to the region within the thermal imaging image that contains the target human body.

[0127] For example, the aforementioned human body regions can be as follows: Figure 8 The rectangular area shown in 81, as... Figure 8 The elliptical region shown in 82 or as shown in the image Figure 8 The irregular region shown in 83. Figure 8 81 in Figure 8 82 and Figure 8 The human body regions shown in 83 all contain thermal imaging images of the target human body.

[0128] It should be understood that the aforementioned human body region can also be a region of other shapes divided in the thermal imaging image, which contains the thermal imaging image of the target human body. The bedding coverage detection device can extract a region containing the target human body from the acquired thermal imaging image in a pre-set shape. The specific shape and size of the human body region are not limited in the embodiments of this application.

[0129] In some embodiments, before determining the human body region corresponding to the target human body in the thermal imaging image, human posture recognition can be performed on the thermal imaging image of the infrared detection area to obtain the human posture recognition result of the target human body. Further, if the human posture recognition result of the target human body is a supine position, the human body region corresponding to the target human body in the acquired thermal imaging image is determined.

[0130] It should be noted that when the target human body is sleeping or lying down to rest, it is necessary to confirm whether the target human body is covered with bedding for warmth. At this time, the human body area corresponding to the target human body in the thermal imaging image can be determined, thereby determining the bedding coverage rate of the target human body.

[0131] In this embodiment, the instantaneous posture of a human body can be categorized as supine or non-suppressive. For example, the thermal imaging image of a target human body in similar postures such as supine, lateral, or prone can all be identified as supine. The thermal imaging image of a target human body in postures other than supine, such as standing, walking, kneeling, sitting upright, or leaning back, can all be identified as non-suppressive.

[0132] Therefore, if the target human body's posture recognition result is a lying position, it can be assumed that it is necessary to confirm whether the target human body is covered with bedding for warmth, and bedding coverage detection is required to determine the human body region corresponding to the target human body in the thermal imaging image.

[0133] Alternatively, if the target human's posture recognition result is not in a supine position, it can be assumed that there is no need to perform bedding coverage detection. Therefore, the relevant steps of bedding coverage detection can be omitted, thereby reducing unnecessary processing and alleviating the computational burden.

[0134] As an optional implementation, after acquiring the thermal imaging image within the infrared detection area, the acquired thermal imaging image can be input into a pre-trained posture recognition model to obtain the posture recognition result of the target human body in the thermal imaging image.

[0135] Optionally, the above pose recognition model can be built based on a convolutional neural network (CNN) architecture.

[0136] Convolutional neural networks (CNNs) are a type of feedforward neural network that incorporates convolutional computations and has a deep structure; they are one of the representative algorithms in deep learning. Generally, a CNN consists of an input layer, hidden layers, and an output layer.

[0137] The input layer of a convolutional neural network can process multidimensional data. The hidden layers of a convolutional neural network include one or more convolutional layers, one or more pooling layers, and one or more fully-connected layers.

[0138] The function of a convolutional layer is to extract features from the input data. A convolutional layer contains multiple convolutional kernels (filters), each corresponding to multiple weight coefficients and a bias vector, similar to a neuron in a feedforward neural network. Each neuron in a convolutional layer is connected to multiple neurons in a region located in close proximity in the previous layer. The size of this region depends on the size of the convolutional kernel and is also called the "receptive field".

[0139] Convolutional layers are typically followed by pooling layers. This allows the output data, after feature extraction in the convolutional layers, to be passed to the pooling layers for selection and information filtering. For example, ... Figure 9 As shown, each pooling layer and one or more convolutional layers connected before it can form a convolution-pooling unit.

[0140] Each node in a fully connected layer is connected to all nodes in the previous layer to synthesize the acquired features. It is usually built at the end of the hidden layers of a convolutional neural network and only transmits signals to other fully connected layers. The fully connected layer acts as a "classifier" in the entire convolutional neural network.

[0141] The output layer of a convolutional neural network has the same structure and working principle as the output layer of a traditional feedforward neural network. For example, in a convolutional neural network for image classification, the output layer uses a logistic function or a normalized exponential function (softmax function) to output classification labels, such as people, scenery, and objects.

[0142] Optional, such as Figure 10 As shown, the pose recognition model can be sequentially connected to an input layer, a first convolutional layer, a first pooling layer, a second convolutional layer, a max pooling layer, a fully connected layer, and an output layer.

[0143] In the pose recognition model provided in this application embodiment, the input layer is single-channel, generating feature images of size 32×32. The first convolutional layer has 32 channels, generating 32 5×5 feature images. The first pooling layer has 22 channels, generating 22 7×7 feature images. The second convolutional layer has 32 channels, generating 32 3×3 feature images. The max pooling layer has 32 channels, generating 32 2×2 feature images. The fully connected layer can form 128 neurons. The output layer is connected to the fully connected layer, and the output of the output layer is the pose recognition result "reclining" or "non-reclining".

[0144] In some embodiments, the pre-trained pose recognition model described above can be learned using the YOLOv5 (you only look once v5) algorithm.

[0145] YOLOv5 is a novel object detection method characterized by both rapid detection and high accuracy. It features fast inference speed and a compact network structure, enabling effective inference on single or multiple images. In this embodiment, the YOLOv5 algorithm can be used to quickly and conveniently train the aforementioned pose recognition model.

[0146] Furthermore, a training sample set for the pose recognition model can be obtained. This training sample set can include a large number of samples corresponding to different human bodies, including thermal imaging images of the human body in different usage environments, at different distances and angles between the target human body and the thermal imaging device, and in different postures (lying down, not lying down) and movements. In addition, each sample is assigned a pose label, which represents the actual pose of the target human body in the thermal imaging image.

[0147] Furthermore, based on the aforementioned training sample set, the pose recognition model to be trained can be trained to obtain a trained pose recognition model.

[0148] S103. The ratio between the number of pixels with a temperature value less than the temperature threshold within the human body area and the total number of pixels within the human body area is used as the bedding coverage rate of the target human body.

[0149] In this context, a pixel is the smallest unit in an image. A pixel can be considered an indivisible unit or element within the entire image. A complete image is composed of multiple small squares (pixels), each with a specific location and assigned color value. The color and position of these squares determine the overall pattern and size of the image.

[0150] In addition, the temperature value mentioned above refers to the radiation temperature of the surface of the object being measured in the thermal imaging image, or it can be the actual temperature of the surface of the object being measured.

[0151] The temperature value that can be directly read from a thermal imaging image is the radiant temperature of the surface of the object being measured. By processing the radiant temperature read directly from the thermal imaging image, the true temperature of the surface of the object being measured in the thermal imaging image can be obtained.

[0152] The specific method for calculating the true temperature is explained below.

[0153] Thermal imaging equipment's detector converts received infrared thermal radiation energy into electrical signals. After amplification, shaping, and analog-to-digital conversion, these signals become digital signals, which are then used to generate thermal images. The grayscale value of each point in the thermal image corresponds to the radiation energy emitted from that point on the object being measured and reflected back to the thermal imaging equipment. However, the temperature value read from the thermal image is the radiation temperature T of the object's surface. r The actual temperature T0 is not the true temperature. The true temperature T0 is equal to the true temperature of a blackbody radiating the same energy. Therefore, in actual testing, if the true temperature is to be used, the thermal imaging equipment must first be calibrated using a high-precision blackbody to find the correspondence between the blackbody temperature and the output voltage of the photoelectric conversion device of the thermal imaging equipment (represented as grayscale in the thermal image).

[0154] A blackbody is an object that can absorb radiation of any wavelength at any temperature.

[0155] In some embodiments, a blackbody is used to perform temperature correction for the thermal imaging device to ensure the temperature measurement accuracy of the thermal imaging device.

[0156] For example, if the temperature of a blackbody is 37 degrees Celsius, and a thermal imaging device measures the temperature of the blackbody and obtains a temperature value of 37.1 degrees Celsius, then it can be said that there is an error in the temperature measurement by the thermal imaging device, and the error is 0.1 degrees Celsius.

[0157] The Stefan-Boltzmann law states that the radiance of a blackbody satisfies the following formula (2):

[0158] E b =σT 4 Formula (2)

[0159] Among them, E b Let σ be the blackbody's radiant output, σ be the blackbody's total radiant power, and T be the blackbody's thermodynamic temperature. That is, the total radiant power of various wavelengths emitted per unit area of ​​the blackbody's surface is proportional to the fourth power of its thermodynamic temperature T.

[0160] At the same temperature, the power radiated by a real object within the same wavelength range is always less than the power radiated by a blackbody. In other words, the monochromatic radiant exitance E(λ, T) of a real object is less than the monochromatic radiant exitance Eblackbody. b (λ, T). We compare E(λ, T) with E b The ratio of (λ, T) is called the monochromatic emissivity ε(λ) of the object. ε(λ) represents the degree to which the radiation of the actual object approaches that of a blackbody, and can be expressed by the following formula (3):

[0161]

[0162] Transforming formula (3), we obtain the following formula (4):

[0163] E(λ,T)=ε(λ)E b (λ, T) Formula (4)

[0164] Integrating both sides of equation (4), we obtain the following equation (5):

[0165]

[0166] If the monochromatic blackness ε(λ) of an object is a constant that does not change with wavelength λ, i.e., ε(λ) = ε, then such an object is called a gray body. Combining the following formulas (6) and (7):

[0167]

[0168]

[0169] The following formula (8) can be obtained:

[0170] E(T)=εE b (T) Formula (8)

[0171] Combining formula (8) with formula (2) above, we can obtain the following formula (9):

[0172] E b =εσT 4 Formula (9)

[0173] The thermal radiation of a real object in the infrared wavelength range can be approximated as gray body radiation. ε is defined as the emissivity of an object, representing the ratio of the object's emissivity to that of a blackbody under the same temperature and measurement conditions.

[0174] The irradiance applied to the thermal imaging device can be obtained by the following formula (10):

[0175] E λ =A0d -2 [T aλ ε λ L bλ (T0)+τ αλ (1-α λ )L bλ (T u )+ε aλ L bλ (T a )] Formula (10)

[0176] Where, ε λ αλ is the surface emissivity, αλ is the surface absorptivity, and τ is the surface emissivity. αλ ε represents the spectral transmittance of the atmosphere. αλ T is the atmospheric emissivity, T0 is the surface temperature of the object being measured, and T u For ambient temperature, T a Let A0 be the atmospheric temperature and d be the distance between the target and the thermal imaging device. Typically, A0d... -2 Let A0 be a constant, and let A0 be the visible area of ​​the target corresponding to the minimum spatial angle of the thermal imaging device. Thermal imaging devices typically operate within a very narrow spectral range, such as 8µm-14µm or 3µm-5µm. λ ,αλ,τ αλ It can generally be considered independent of λ. The response voltage of the thermal imaging device can be obtained by the following formula (11):

[0177]

[0178] Among them, A R Let K be the area of ​​the lens of the thermal imaging device, and assume that K is represented by the following formula (12):

[0179] K = A R A0d -2 Formula (12)

[0180] Combine the following formula (13):

[0181]

[0182] Then formula (11) can be transformed into the following formula (14):

[0183] V S =K{τ a [εf(T0)+(1-α)f(T u )]+ε a f(T a )} Formula (14)

[0184] According to Planck's radiation law, the following formula (15) is obtained:

[0185]

[0186] The true temperature of the surface of the object being measured can be obtained by the following formula (16):

[0187]

[0188] The value of n varies depending on the wavelength of the thermal imaging equipment used. When using an indium antimonide (InSb) detector, the 3–5 μm wavelength range is used, and the value of n is 8.68. When using a mercury cadmium telluride (HgCdTe) detector, the 8–14 μm wavelength range is used, and the value of n is 4.09.

[0189] In actual testing, if the surface being tested satisfies the gray body approximation, i.e., ε = α, and if the atmospheric ε is considered to be... a =α a =1-τ a Then formula (15) can be transformed into the following formula (17):

[0190]

[0191] Formula (16) can be transformed into the following formula (18):

[0192]

[0193] Formula (18) is the formula for calculating the true surface temperature of the gray body.

[0194] When measuring temperature at close range, the effect of atmospheric transmittance is ignored, i.e., τ a =1, then formula (15) can be transformed into the following formula (19):

[0195]

[0196] In summary, if the emissivity of the surface of the object being measured is obtained, the true temperature of the surface of the object being measured can be calculated using the above formula (18) or formula (19), as well as the detected radiation temperature and ambient temperature.

[0197] Furthermore, the aforementioned bedding coverage rate reflects the extent to which a target human body within the infrared detection area is covered by bedding. It should be understood that a lower bedding coverage rate indicates that fewer parts of the target human body are covered by bedding, and consequently, a higher probability that the target human body will catch a cold or become ill.

[0198] It should be noted that in thermal imaging images, because the portion of the human body covered by bedding largely blocks heat, its surface temperature will appear lower than the surface temperature of the uncovered portion. Therefore, a reasonable temperature threshold can be set based on the actual detection of thermal imaging images, allowing images with temperatures below this threshold to be considered images of a human body covered by bedding. Thus, pixels with temperatures below the temperature threshold are the pixels in the image of the area of ​​the target human body covered by bedding.

[0199] Furthermore, the bedding coverage rate of the target human body can be calculated as the ratio between the number of pixels with a temperature value lower than the temperature threshold within the human body area and the total number of pixels within the human body area.

[0200] The bedding coverage detection method provided in this application has at least the following beneficial effects: Firstly, this method can detect the number of all pixels within a human body area that are below a temperature threshold. These pixels can constitute the area within the human body area covered by bedding. Therefore, compared with existing methods that determine the bedding coverage of a target human body solely based on temperature values ​​below a temperature threshold at the joint positions of the target human body in thermal imaging images, the method provided in this application can calculate the bedding coverage of the target human body more accurately. Secondly, this method is based on thermal imaging images and is not affected by light intensity, allowing for bedding coverage detection both day and night, thus possessing higher practicality and universality.

[0201] In some embodiments, based on Figure 5 The method for testing bedding coverage shown is as follows: Figure 11 As shown, the method may further include the following steps:

[0202] S104. When the bedding coverage rate is less than or equal to the preset bedding coverage rate threshold, determine if the target person kicks off the bedding.

[0203] The aforementioned bedding coverage threshold is a preset bedding coverage value based on actual conditions.

[0204] according to Figure 5As described in the illustrated embodiments regarding bedding coverage, a lower bedding coverage rate indicates fewer body parts of the target person are covered by bedding, thus increasing the probability of the target person catching a cold. Therefore, a reasonable bedding coverage rate threshold can be set based on actual conditions and the way the body is divided, so that when the bedding coverage rate is less than or equal to the preset bedding coverage threshold, it can be determined that the target person has kicked off the bedding.

[0205] In some embodiments, an alarm message is issued when the bedding coverage rate is less than or equal to a preset bedding coverage rate threshold and the ambient temperature of the infrared detection area is lower than a preset ambient temperature.

[0206] The ambient temperature refers to the temperature of the environment in which the target person is located, that is, the temperature of the area outside the human body area within the infrared detection zone. The alarm message is used to alert the target person that they have kicked off the blanket.

[0207] It should be understood that the aforementioned ambient temperature can be the radiation temperature read directly from the thermal imaging image, or it can be the actual temperature obtained from the thermal imaging image based on the radiation temperature.

[0208] In addition, the preset ambient temperature can be a temperature value set according to the specific situation of the target human body, so that when the target human body kicks off the blanket and the ambient temperature of the infrared detection area is lower than the preset ambient temperature, the target human body may catch a cold and get sick due to the low temperature.

[0209] Optional, based on Figure 3 or Figure 4 The system shown can send an alarm message to a terminal device when the bedding coverage rate is less than or equal to a preset bedding coverage rate threshold and the ambient temperature in the infrared detection area is lower than a preset ambient temperature. The alarm message may include preset alarm sounds, alarm indicator lights, and other alarm signals. The terminal device can be a mobile phone, smartwatch, smart bracelet, or other personal device carried by the guardian or emergency contact corresponding to the target person.

[0210] S105. When the bedding coverage rate is greater than the preset bedding coverage rate threshold, determine that the target person has not kicked off the bedding.

[0211] according to Figure 5 As can be seen from the description of the bedding coverage rate in the illustrated embodiment, the higher the bedding coverage rate, the more body parts of the target human being are covered by bedding. Therefore, when the bedding coverage rate is greater than the preset bedding coverage rate threshold, it can be determined that the target human being has not kicked off the bedding.

[0212] Figure 11The illustrated embodiment offers at least the following benefits: By setting a reasonable bedding coverage threshold, the system can more accurately determine whether a target person is kicking off the covers based on the currently obtained bedding coverage rate. Furthermore, when the bedding coverage rate is less than or equal to the preset bedding coverage threshold, and the ambient temperature in the infrared detection area is lower than the preset ambient temperature, an alarm can be issued to promptly notify the target person's guardian, reducing the likelihood of the target person catching a cold or becoming ill.

[0213] Optionally, embodiments of this application also provide a method for determining a temperature threshold, such as... Figure 12 As shown, the method includes the following steps:

[0214] S201. Determine the highest body temperature of the target human body based on the temperature values ​​of each pixel within the human body area.

[0215] As an alternative implementation, the head region of the target human body can be cropped from the thermal imaging image of the human body region, and the highest temperature of the target human body can be determined based on the temperature value of each pixel in the head region.

[0216] It should be noted that, since the head is usually the part of the human body with the highest temperature, the head area of ​​the target human body can be directly cropped from the human body area, and the highest temperature of the target human body can be determined based on the thermal imaging image of the head area.

[0217] For example, the average temperature of each pixel in the thermal imaging image of the head region of the target human body can be used as the highest temperature of the target human body.

[0218] S202. Determine the ambient temperature based on the temperature values ​​of each pixel in the areas other than the human body region in the thermal imaging image.

[0219] Among them, ambient temperature refers to the temperature of the environment in which the target human body is located, that is, the temperature of the area outside the human body area within the infrared detection area.

[0220] Optionally, the average temperature of each pixel in the thermal imaging image, excluding the human body area, can be used as the current ambient temperature.

[0221] For example, in actual calculations, in order to eliminate detection errors and make the obtained ambient temperature more accurate and representative, the top 10% of pixels with the highest temperature values ​​and the bottom 10% of pixels with the lowest temperature values ​​can be removed from all pixels in the areas other than the human body area in all thermal imaging images. The average temperature value of the remaining pixels can then be used as the current ambient temperature.

[0222] S203. Determine the temperature threshold based on the ambient temperature and the highest body temperature of the target human body.

[0223] Optionally, the temperature threshold can satisfy the following relationship:

[0224]

[0225] Among them, T h T is the temperature threshold. v For ambient temperature, T m It is the highest temperature in the human body.

[0226] It should be understood that Figure 12 The method for determining the temperature threshold shown is only one possible implementation. In the actual application of this application, a reasonable temperature threshold can be set according to the actual detection of the thermal imaging image.

[0227] The foregoing primarily describes the solution provided in this application from a methodological perspective. It is understood that the bedding coverage detection device, in order to achieve the aforementioned functions, includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the algorithmic steps of the examples described in the embodiments disclosed herein, the present invention can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0228] This application can divide the bedding coverage detection device into functional modules based on the above method example. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0229] Figure 13 This diagram illustrates the composition of a bedding coverage detection device according to an embodiment of this application. Figure 13 As shown, the bedding coverage detection device 1000 includes an acquisition unit 1001, an identification unit 1002, and a processing unit 1003. Optionally, the bedding coverage detection device 1000 may also include an alarm unit 1004.

[0230] The acquisition unit 1001 is used to acquire thermal imaging images of the infrared detection area.

[0231] The recognition unit 1002 is used to perform human posture recognition on thermal imaging images and obtain the human posture recognition results of the target human body.

[0232] The processing unit 1003 is used to determine the human body region corresponding to the target human body in the thermal imaging image when the human body posture recognition result of the target human body is a lying position; and to use the ratio between the number of pixels with a temperature value less than a temperature threshold in the human body region and the total number of pixels in the human body region as the bedding coverage rate of the target human body.

[0233] In some embodiments, the processing unit 1003 is specifically configured to: determine the highest temperature of the target human body based on the temperature values ​​of each pixel point within the human body region; determine the ambient temperature based on the temperature values ​​of each pixel point in other regions of the thermal imaging image besides the human body region; and determine a temperature threshold based on the ambient temperature and the highest temperature of the target human body.

[0234] In some embodiments, the temperature threshold satisfies the following relationship:

[0235]

[0236] Among them, T h T is the temperature threshold. v For ambient temperature, T m It is the highest temperature in the human body.

[0237] In some embodiments, the processing unit 1003 is further configured to: determine that the target human body has kicked off the blanket when the blanket coverage rate is less than or equal to a preset blanket coverage rate threshold; or determine that the target human body has not kicked off the blanket when the blanket coverage rate is greater than the preset blanket coverage rate threshold.

[0238] In some embodiments, the bedding coverage detection device 1000 further includes an alarm unit 1004, which is used to issue an alarm message when the bedding coverage is less than or equal to a preset bedding coverage threshold and the ambient temperature of the infrared detection area is lower than a preset ambient temperature. The alarm message is used to indicate that the target human body has kicked off the bedding.

[0239] In some embodiments, the acquisition unit 1001 is specifically used to: acquire level data obtained by infrared detection of the infrared detection area; perform resolution conversion processing on the level data according to the resolution of the thermal imaging device to obtain the original thermal imaging image of the infrared detection area; and perform homogenization processing, noise reduction processing, filtering processing and enhancement processing on the original thermal imaging image in sequence to obtain the thermal imaging image of the infrared detection area.

[0240] Figure 13 The units within can also be called modules; for example, a processing unit can be called a processing module. Additionally, in... Figure 13 In the embodiments shown, the names of the various units may not be the same as those shown in the figures. For example, the acquisition unit may also be called the communication unit.

[0241] Figure 13 If the various units in the process are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. Storage media for storing computer software products include: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0242] This application also provides a hardware structure diagram of a bedding coverage detection device, as shown in the embodiment. Figure 14 As shown, the bedding coverage detection device 2000 includes a processor 2001, and optionally, a memory 2002 and a transceiver 2003 connected to the processor 2001. The processor 2001, memory 2002 and transceiver 2003 are connected via a bus 2004.

[0243] Processor 2001 may be a central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. Processor 2001 may also be any other device with processing capabilities, such as a circuit, device, or software module. Processor 2001 may also include multiple CPUs, and processor 2001 may be a single-core processor or a multi-core processor. Here, "processor" may refer to one or more devices, circuits, or processing cores used to process data (e.g., computer program instructions).

[0244] The memory 2002 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or it may be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer. This application embodiment does not impose any limitations on this. The memory 2002 may exist independently or may be integrated with the processor 2001. The memory 2002 may contain computer program code. The processor 2001 is used to execute the computer program code stored in the memory 2002, thereby implementing the method provided in this application embodiment.

[0245] The transceiver 2003 can be used to communicate with other devices or communication networks (such as Ethernet, radioaccess network (RAN), wireless local area networks (WLAN), etc.). The transceiver 2003 can be a module, circuit, transceiver, or any device capable of enabling communication.

[0246] Bus 2004 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Bus 2004 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 14 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0247] This application also provides a computer-readable storage medium including computer-executable instructions that, when run on a computer, cause the computer to perform any of the methods provided in the above embodiments.

[0248] This application also provides a computer program product containing computer execution instructions, which, when run on a computer, causes the computer to perform any of the methods provided in the above embodiments.

[0249] This application also provides a chip, including a processor and an interface. The processor is coupled to a memory through the interface. When the processor executes a computer program in the memory or computer execution instructions, any of the methods provided in the above embodiments are executed.

[0250] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer-executable instructions. When these computer-executable instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer-executable instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer-executable instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks, SSDs).

[0251] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, the disclosure, and the appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0252] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

[0253] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for detecting bedding coverage, characterized in that, The method includes: Acquire thermal imaging images of the infrared detection area; Perform human posture recognition on the thermal imaging image to obtain the human posture recognition result of the target human body; If the human posture recognition result of the target human body is a lying position, determine the human body region corresponding to the target human body in the thermal imaging image; The highest body temperature of the target human body is determined based on the temperature values ​​of each pixel within the human body area. The ambient temperature is determined based on the temperature values ​​of each pixel in the areas other than the human body region in the thermal imaging image. A temperature threshold is determined based on the ambient temperature and the highest body temperature of the target human body; wherein the temperature threshold satisfies: Among them, T h For the temperature threshold, T v T represents the ambient temperature. m This refers to the highest temperature of the human body. The ratio between the number of pixels with a temperature value less than a temperature threshold within the human body area and the total number of pixels within the human body area is used as the bedding coverage rate of the target human body. When the bedding coverage rate is less than or equal to a preset bedding coverage rate threshold, it is determined that the target human body has kicked off the bedding.

2. The method according to claim 1, characterized in that, The method further includes: When the bedding coverage rate is greater than the preset bedding coverage rate threshold, it is determined that the target person has not kicked off the bedding.

3. The method according to claim 1, characterized in that, The method further includes: When the bedding coverage rate is less than or equal to a preset bedding coverage rate threshold, and the ambient temperature of the infrared detection area is lower than a preset ambient temperature, an alarm message is issued. The alarm message is used to indicate that the target person has kicked off the bedding.

4. The method according to claim 1, characterized in that, The acquisition of thermal imaging images of the infrared detection area includes: Acquire the level data obtained by performing infrared detection on the infrared detection area; Based on the resolution of the thermal imaging device, the level data is processed by resolution conversion to obtain the original thermal imaging image of the infrared detection area; The original thermal imaging image is subjected to homogenization, noise reduction, filtering, and enhancement processes in sequence to obtain the thermal imaging image of the infrared detection area.

5. A device for detecting bedding coverage, characterized in that, The device includes: The acquisition unit is used to acquire thermal imaging images of the infrared detection area; The recognition unit is used to perform human posture recognition on the thermal imaging image and obtain the human posture recognition result of the target human body. The processing unit is used to determine the human body region corresponding to the target human body in the thermal imaging image when the human body posture recognition result of the target human body is a lying position. The highest body temperature of the target human body is determined based on the temperature values ​​of each pixel within the human body area. The ambient temperature is determined based on the temperature values ​​of each pixel in the areas other than the human body region in the thermal imaging image. A temperature threshold is determined based on the ambient temperature and the highest body temperature of the target human body; wherein the temperature threshold satisfies: Among them, T h For the temperature threshold, T v T represents the ambient temperature. m This refers to the highest temperature of the human body. The ratio between the number of pixels with a temperature value less than a temperature threshold within the human body area and the total number of pixels within the human body area is used as the bedding coverage rate of the target human body. When the bedding coverage rate is less than or equal to a preset bedding coverage rate threshold, it is determined that the target human body has kicked off the bedding.

6. The apparatus according to claim 5, characterized in that, The processing unit is further configured to: When the bedding coverage rate is greater than the preset bedding coverage rate threshold, it is determined that the target person has not kicked off the bedding.

7. The apparatus according to claim 5, characterized in that, The device also includes an alarm unit: The alarm unit is used to issue an alarm message when the bedding coverage rate is less than or equal to a preset bedding coverage rate threshold and the ambient temperature of the infrared detection area is lower than a preset ambient temperature. The alarm message is used to indicate that the target human body has kicked off the bedding.

Images