Indoor human body detection method, device and equipment and computer readable storage medium

Abstract

The invention relates to the technical field of smart home, and discloses an indoor human body detection method, device and equipment and a computer readable storage medium. The method comprises the steps that indoor infrared radiation signals are collected, and a heart rate value is determined based on the infrared radiation signals; if it is determined that the heart rate value is within the preset heart rate range, generating a thermal image based on the infrared radiation signal; and if the human body area is detected based on the thermal image, determining that a human body exists indoors. According to the method, the heart rate value and the thermal image are determined through the infrared radiation signal, whether the human body exists indoors or not is detected jointly based on the heart rate value and the thermal image, indoor heat source interference can be avoided, and the accuracy of indoor human body detection is improved.

Description

Technical Field

[0001] The present application relates to the field of smart home technology, and in particular to an indoor human body detection method, apparatus, device, and computer-readable storage medium. Background Art

[0002] With the development of science and technology, smart homes are gradually entering thousands of households. In the field of smart homes, it is usually necessary to detect whether there are people in the room, and then control or adjust various home appliances or furniture accordingly to suit the usage habits of people in the room.

[0003] However, in the current smart home field, indoor human body detection usually uses infrared sensors to receive indoor infrared radiation to determine the temperature, and then judge whether there is a human body in the room based on the temperature threshold. However, this detection method is easily interfered by indoor heat sources, resulting in a high false alarm rate. Summary of the Invention

[0004] In view of this, the purpose of this application is to overcome the deficiencies in the prior art and provide a method for indoor human detection, the method comprising:

[0005] Collecting infrared radiation signals in the room and extracting heart rate values from the infrared radiation signals;

[0006] If it is determined that the heart rate value is within a preset heart rate range, generating a thermal image based on the infrared radiation signal;

[0007] If a human body region is detected based on the thermal image, it is determined that a human body exists in the room.

[0008] In one embodiment, the step of extracting the heart rate value from the infrared radiation signal includes:

[0009] performing filtering processing on the infrared radiation signal to obtain a reference infrared signal;

[0010] Acquiring an indoor temperature, and obtaining a target infrared signal based on the indoor temperature and the reference infrared signal;

[0011] A heart rate value is extracted based on the target infrared signal.

[0012] In one embodiment, the step of obtaining a target infrared signal based on the indoor temperature and the reference infrared signal includes:

[0013] determining an ambient infrared radiation signal based on the indoor temperature and a preset indoor ambient emissivity;

[0014] Determining an environment reflected infrared signal based on the indoor temperature, a preset indoor environment emissivity, and a preset indoor environment reflectivity;

[0015] A target infrared signal is determined based on the reference infrared signal, the ambient infrared radiation signal and the ambient reflected infrared signal.

[0016] In one embodiment, the step of determining the heart rate value based on the target infrared signal includes:

[0017] performing spectrum analysis on the target infrared signal, and extracting heart rate frequency domain features from the target infrared signal;

[0018] Calculating a power spectrum density based on the heart rate frequency domain characteristics, and determining the heart rate wave frequency according to a peak value of the power spectrum density;

[0019] A heart rate value is calculated according to the heart rate wave frequency.

[0020] In one embodiment, before the step of determining that a human body exists in the room if a human body area is detected based on the thermal image, the following steps are included:

[0021] Segmenting the thermal image to obtain a foreground thermal image;

[0022] extracting temperature distribution features and geometric features of each heat concentration area in the foreground thermal image;

[0023] For each heat concentration area, whether the heat concentration area is a human body area is determined based on the temperature distribution characteristics and the geometric characteristics.

[0024] In one embodiment, the step of determining whether the heat concentration area is a human body area based on the temperature distribution characteristics and the geometric characteristics includes:

[0025] Based on the temperature distribution characteristics, determining the temperature mean corresponding to the heat concentration area;

[0026] If the temperature mean is within the preset human body temperature range, comparing the geometric feature with the preset human body geometric feature;

[0027] If the geometric features are the same as the preset human body geometric features, the heat concentration area is determined to be a human body area.

[0028] In one embodiment, the step of determining whether the heat concentration area is a human body area based on the temperature distribution characteristics and the geometric characteristics further includes:

[0029] If the temperature mean is not within the preset human body temperature range, or if the geometric feature is different from the preset human body geometric feature, it is determined that the heat concentration area is not a human body area.

[0030] The present application also provides an indoor human body detection device, the indoor human body detection device comprising:

[0031] A first determination module is used to collect infrared radiation signals in the room and extract a heart rate value from the infrared radiation signals;

[0032] a generating module, configured to generate a thermal image based on the infrared radiation signal if it is determined that the heart rate value is within a preset heart rate range;

[0033] The second determining module is configured to determine that a human body exists in the room if a human body area is detected based on the thermal image.

[0034] The present application also provides a computer device, which includes a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the above-mentioned indoor human body detection method.

[0035] The present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is run on a processor, the computer program executes the above-mentioned indoor human body detection method.

[0036] The embodiments of the present application have the following beneficial effects:

[0037] The present invention discloses an indoor human body detection method comprising: collecting infrared radiation signals indoors and extracting a heart rate value from the infrared radiation signals; if the heart rate value is determined to be within a preset heart rate range, generating a thermal image based on the infrared radiation signals; and if a human body region is detected based on the thermal image, determining the presence of a human body indoors. This method uses infrared radiation signals to determine the heart rate value and thermal image, and then uses these values to jointly detect the presence of a human body indoors. This method avoids interference from indoor heat sources and improves the accuracy of indoor human body detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] To more clearly illustrate the technical solution of this application, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of this application and should not be considered as limiting the scope of protection of this application. Those skilled in the art can also derive other relevant drawings based on these drawings without inventive effort.

[0039] Figure 1 This is a flow chart of the first embodiment of the indoor human body detection method provided by this application;

[0040] Figure 2 This is a flow chart of the second embodiment of the indoor human body detection method provided by this application;

[0041] Figure 3 This is a flow chart of the third embodiment of the indoor human body detection method provided by this application;

[0042] Figure 4 This is a flow chart of the fourth embodiment of the indoor human body detection method provided by this application;

[0043] Figure 5 This is a flowchart of the fifth embodiment of the indoor human body detection method provided by this application;

[0044] Figure 6 This is a flow chart of the sixth embodiment of the indoor human body detection method provided by this application;

[0045] Figure 7 This is a schematic diagram of the structure of the indoor human body detection device provided in this application. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments.

[0047] The components of the embodiments of the present application generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but rather merely represents selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative effort are within the scope of protection of the present application.

[0048] Hereinafter, the terms "including", "having" and their cognates, which may be used in various embodiments of the present application, are intended only to indicate specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or the possibility of adding one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items.

[0049] Furthermore, the terms “first,” “second,” “third,” etc., are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.

[0050] Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meaning as in the context of the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning unless clearly defined in the various embodiments of the present application.

[0051] It can be understood that the method of the present application is applied to an indoor human body detection system, which includes infrared sensors, central processors and other equipment to execute the indoor human body detection method.

[0052] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments may be combined with each other.

[0053] Please refer to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the indoor human body detection method provided by this application, the method comprising:

[0054] Step S101: Collect indoor infrared radiation signals and extract heart rate values from the infrared radiation signals.

[0055] In this embodiment, the indoor human detection system uses infrared sensors pre-installed indoors to collect infrared radiation signals. These signals include infrared signals emitted by objects and organisms within the indoor environment. The indoor human detection system pre-processes the infrared radiation signals collected by the infrared sensors to filter out the infrared radiation signals of organisms, and then extracts the heart rate value from the infrared radiation signals.

[0056] It is understandable that the infrared radiation signal of the organism may be the infrared radiation signal of the human body and / or the infrared radiation signal of the pet, and the indoor human detection system can measure the corresponding heart rate value of the organism based on the infrared radiation signal of the organism.

[0057] It should be noted that the collection of indoor infrared radiation signals can adopt a single-transmit single-receive mode or a multiple-transmit multiple-receive mode. The single-transmit single-receive mode collects indoor infrared radiation signals through one infrared sensor, but this will result in low accuracy of the collected infrared radiation signals. Therefore, it is preferably adopted a multiple-transmit multiple-receive mode. The multiple-transmit multiple-receive mode collects indoor infrared radiation signals through multiple infrared sensors synchronously, and then fuses the indoor infrared radiation signals synchronously collected by each infrared sensor to obtain the final infrared radiation signal, which can avoid omissions in collection and thereby improve the accuracy of the collected infrared radiation signals.

[0058] Step S102: If it is determined that the heart rate value is within a preset heart rate range, a thermal image is generated based on the infrared radiation signal.

[0059] In this embodiment, the indoor human detection system measures the corresponding heart rate of a living organism based on its infrared radiation signal and compares the heart rate with a preset heart rate range. If the heart rate is determined to be within the preset range, a thermal image is generated based on the infrared radiation signal. It will be understood that the preset heart rate range is the heart rate range of the human body. When the heart rate is within the preset range, the indoor human detection system determines that a human body may be present indoors. The system then generates a thermal image based on the infrared radiation signal to further determine whether a human body is present indoors based on the thermal image.

[0060] Step S103: If a human body area is detected based on the thermal image, it is determined that a human body exists in the room.

[0061] In this embodiment, after the indoor human body detection system generates a thermal image based on the infrared radiation signal, it processes the thermal image to determine whether a human body area is detected in the thermal image. If a human body area is detected in the thermal image, it is determined that a human body exists in the room.

[0062] The indoor human detection system of this embodiment collects infrared radiation signals from indoor environments and, based on these signals, generates a thermal image based on the infrared radiation signals if the heart rate value is determined to be within a preset heart rate range. If a human body area is detected based on the thermal image, the presence of a human body is determined to be indoors. This method uses infrared radiation signals to determine the heart rate value and thermal image, and then uses these two combined methods to detect the presence of a human body indoors. This method avoids interference from indoor heat sources and improves the accuracy of indoor human detection.

[0063] Please refer to Figure 2 , Figure 2 This is a flow chart of the second embodiment of the indoor human body detection method provided by this application. The difference between the second embodiment and the first embodiment is that the step of extracting the heart rate value from the infrared radiation signal includes:

[0064] Step S201 : filtering the infrared radiation signal to obtain a reference infrared signal.

[0065] In this embodiment, the indoor human detection system collects infrared radiation signals from the room using a pre-installed infrared sensor. The system then filters the infrared radiation signals to produce a reference infrared signal. It is understood that the infrared radiation signals collected by the infrared sensor may contain electromagnetic interference signals generated by electronic devices and appliances. In this case, filtering is required to remove the electromagnetic interference signals and produce a reference infrared signal.

[0066] For example, the frequency range of the electromagnetic interference signal is usually lower than the frequency range of the infrared radiation signal. Therefore, the electromagnetic interference signal with a frequency lower than the infrared signal can be filtered out by a high-pass filter, and a band-pass filter can be used to only allow signals in the frequency range of the infrared radiation signal to pass through, and the electromagnetic interference signals with frequency ranges lower and higher than the frequency range of the infrared radiation signal can be filtered out at the same time.

[0067] Step S202: Acquire the indoor temperature, and obtain a target infrared signal based on the indoor temperature and the reference infrared signal.

[0068] In this embodiment, after filtering out the electromagnetic interference signal and obtaining a reference infrared signal, the indoor human body detection system collects the indoor temperature through a temperature sensor pre-installed in the room, and obtains a target infrared signal based on the indoor temperature and the reference infrared signal. It should be noted that the reference infrared signal is the infrared radiation signal after filtering out the electromagnetic interference signal, which also includes the ambient infrared radiation signal, the ambient reflected infrared signal, and the biological infrared radiation signal. At this time, the indoor human body detection system needs to calculate the ambient infrared radiation signal and the ambient reflected infrared signal based on the indoor temperature, so as to remove the ambient infrared radiation signal and the ambient reflected infrared signal from the reference infrared signal. What remains is the biological infrared radiation signal, that is, the target infrared signal. In this way, the indoor human body detection system can subsequently determine the heart rate value based on the target infrared signal.

[0069] It should be noted that to improve the accuracy of the indoor temperature, multiple temperature sensors are installed indoors. The indoor temperature values collected by these sensors are averaged to obtain the indoor temperature. The ambient infrared radiation signal is the infrared signal radiated by different objects in the indoor environment, while the ambient reflected infrared signal is the infrared signal generated by objects in the indoor environment reflecting the infrared signals emitted by other objects.

[0070] It can be understood that by calculating the ambient infrared radiation signal and the ambient reflected infrared signal based on the indoor temperature, and removing the ambient infrared radiation signal and the ambient reflected infrared signal from the reference infrared signal to obtain the infrared radiation signal of the biological body, the interference of the ambient infrared radiation signal and the ambient reflected infrared signal in the infrared radiation signal used to calculate the heart rate value can be avoided, and the accuracy of the heart rate measurement can be improved.

[0071] Step S203: extracting the heart rate value based on the target infrared signal.

[0072] In this embodiment, after obtaining the target infrared signal, the indoor human body detection system performs operations such as feature extraction and power spectrum density calculation on the target infrared signal, and then extracts the heart rate value.

[0073] The indoor human body detection system of this embodiment first filters out the electromagnetic interference signal of the environment from the collected infrared radiation signal, then eliminates the environmental infrared radiation signal and the environmental reflected infrared signal to obtain the target infrared signal, and finally determines the heart rate value based on the target infrared signal, which can avoid interference from various environments and improve the accuracy of heart rate measurement.

[0074] Please refer to Figure 3 , Figure 3 This is a flow chart of the third embodiment of the indoor human detection method provided by the present application. The difference between the third embodiment and the first to second embodiments is that the step of obtaining the target infrared signal based on the indoor temperature and the reference infrared signal includes:

[0075] Step S301: determining an ambient infrared radiation signal based on the indoor temperature and a preset indoor ambient emissivity.

[0076] In this embodiment, after the indoor human detection system collects the indoor temperature, it calculates the ambient infrared radiation signal based on the indoor temperature and the preset indoor environmental emissivity. It should be noted that the preset indoor environmental emissivity includes the emissivity of objects such as walls and floors (e.g., approximately 0.92 for concrete and approximately 0.90 for wood), and the ambient infrared radiation signal includes the wall infrared radiation signal and the floor infrared radiation signal. The indoor human detection system calculates the wall infrared radiation signal based on the indoor temperature and the wall emissivity, and calculates the floor infrared radiation signal based on the indoor temperature and the floor emissivity.

[0077] Specifically, the formula for calculating the ambient infrared radiation signal is:

[0078] M env =ε env σT 4

[0079] Among them, M env is the ambient infrared radiation signal, ε env is the indoor environment emissivity (wall emissivity, floor emissivity, etc.), σ is the Stefan-Boltzmann constant, and T is the indoor temperature.

[0080] Step S302: determining an environment reflected infrared signal based on the indoor temperature, a preset indoor environment emissivity, and a preset indoor environment reflectivity.

[0081] In this embodiment, the indoor human body detection system determines the environment-reflected infrared signal based on the indoor temperature, the preset indoor environment emissivity, and the preset indoor environment reflectivity. It should be noted that the preset indoor environment reflectivity includes the reflectivity of objects such as walls and floors (reflectivity = 1-emissivity, such as approximately 0.08 for concrete and approximately 0.10 for wood). The environment-reflected infrared signal includes the wall-reflected infrared signal and the floor-reflected infrared signal. The indoor human body detection system calculates the wall infrared radiation signal based on the indoor temperature, the wall emissivity, and the wall reflectivity, and calculates the floor infrared radiation signal based on the indoor temperature, the floor emissivity, and the floor reflectivity.

[0082] Specifically, the formula for calculating the infrared signal reflected by the environment is:

[0083] M envr =ε envr ε env σT 4

[0084] Among them, M envr is the infrared signal reflected by the environment, ε envr is the indoor environment emissivity (wall reflectivity, floor reflectivity, etc.), ε env is the indoor environment emissivity (wall emissivity, floor emissivity, etc.), σ is the Stefan-Boltzmann constant, and T is the indoor temperature.

[0085] Step S303 : determining a target infrared signal based on the reference infrared signal, the ambient infrared radiation signal, and the ambient reflected infrared signal.

[0086] In this embodiment, after determining the ambient infrared radiation signal and the ambient reflected infrared signal, the indoor human body detection system subtracts the ambient infrared radiation signal and the ambient reflected infrared signal from the reference infrared signal to obtain the target infrared signal, which is the infrared radiation signal of the indoor biological body.

[0087] Specifically, the formula for calculating the target infrared signal is:

[0088] M org =MM envr -M env

[0089] Among them, M org is the target infrared signal, M is the reference infrared signal, and M env is the ambient infrared radiation signal, M envr It is the infrared signal reflected by the environment.

[0090] The indoor human body detection system of this embodiment calculates the ambient infrared radiation signal and the ambient reflected infrared signal based on the indoor temperature, and removes the ambient infrared radiation signal and the ambient reflected infrared signal from the reference infrared signal to obtain the infrared radiation signal of the biological body. This can avoid the interference of the ambient infrared radiation signal and the ambient reflected infrared signal in the infrared radiation signal used to calculate the heart rate value, and can improve the accuracy of the heart rate measurement.

[0091] Please refer to Figure 4 , Figure 4 This is a flow chart of the fourth embodiment of the indoor human body detection method provided by the present application. The fourth embodiment differs from the first to third embodiments in that the step of determining the heart rate value based on the target infrared signal includes:

[0092] Step S401 : performing spectrum analysis on the target infrared signal and extracting heart rate frequency domain features from the target infrared signal.

[0093] In this embodiment, after obtaining the target infrared signal, the indoor human detection system performs a Fourier transform on the target infrared signal, converting the target infrared signal from the time domain to the frequency domain to obtain a frequency-domain target infrared signal. The indoor human detection system then performs spectral analysis on the frequency-domain target infrared signal to extract heart rate frequency-domain features from the frequency domain. Heart rate frequency-domain features comprise frequency and amplitude components related to heart rate.

[0094] Step S402: Calculate the power spectrum density based on the heart rate frequency domain characteristics, and determine the heart rate wave frequency according to the peak value of the power spectrum density.

[0095] In this embodiment, the indoor human detection system calculates the power spectral density based on the heart rate frequency domain characteristics and determines the heart rate wave frequency based on the peak value of the power spectral density. Specifically, the main frequency peak of the power spectral density corresponds to the heart rate wave frequency, while the secondary peak of the power spectral density may correspond to the respiratory rate or motion artifacts. Therefore, after obtaining the power spectral density, the indoor human detection system extracts the main frequency peak of the power spectral density for analysis to determine the heart rate wave frequency.

[0096] Step S403: Calculate the heart rate value according to the heart rate wave frequency.

[0097] In this embodiment, after obtaining the heart rate wave frequency, the indoor human body detection system calculates the heart rate value based on the heart rate wave frequency. The heart rate value calculation formula is: heart rate value = (signal sampling frequency / heart rate wave period) * 60. The indoor human body detection system calculates the heart rate wave period based on the heart rate wave frequency, and then calculates the heart rate value based on the preset signal sampling frequency and heart rate wave period combined with the above formula.

[0098] The indoor human body detection system in this embodiment performs spectrum analysis on the target infrared signal, extracting heart rate frequency domain features from the target infrared signal; calculates the power spectrum density based on the heart rate frequency domain features, and determines the heart rate wave frequency based on the peak value of the power spectrum density; and calculates the heart rate value based on the heart rate wave frequency. Analyzing and determining the heart rate value based on the infrared radiation signal of the organism, which has been freed of interference from ambient infrared radiation signals and ambient reflected infrared signals, can improve the accuracy of heart rate measurement.

[0099] Please refer to Figure 5 , Figure 5 This is a flow chart of the fifth embodiment of the indoor human body detection method provided by the present application. The fifth embodiment differs from the first to fourth embodiments in that, before the step of determining the presence of a human body indoors if a human body area is detected based on a thermal image, the method includes:

[0100] Step S501 : Segment the thermal image to obtain a foreground thermal image.

[0101] In this embodiment, the indoor human body detection system generates a thermal image based on the collected infrared radiation signal, and performs segmentation processing on the thermal image to obtain a foreground thermal image.

[0102] Specifically, the indoor human body detection system first binarizes the thermal image to obtain a binary image, and then dilates (fills foreground holes) and erodes (removes background noise points) the binary image to obtain a target binary image; the indoor human body detection system divides the target binary image into multiple sub-areas, calculates the temperature threshold for each sub-area, and calculates the average value based on the temperature threshold of each sub-area to obtain the target temperature threshold; the indoor human body detection system obtains the temperature value corresponding to each pixel in the thermal image, determines the pixel whose temperature value is greater than the target temperature threshold as the foreground pixel, and then composes a foreground thermal image based on all foreground pixels.

[0103] Step S502 : extracting temperature distribution features and geometric features of each heat concentration area in the foreground thermal image.

[0104] In this embodiment, the indoor human detection system extracts temperature distribution and geometric features from each heat concentration region in the foreground thermal image. The foreground thermal image includes multiple heat concentration regions with temperatures greater than a target temperature threshold, each representing an object. For each heat concentration region, the indoor human detection system extracts the corresponding temperature distribution and geometric features.

[0105] Specifically, the indoor human detection system obtains the outline of the heat concentration area through threshold segmentation or edge detection (such as Canny), and then uses connected domain analysis (such as OpenCV's findContours) to identify each heat concentration area in the foreground thermal image, and then extracts the temperature distribution characteristics and geometric characteristics corresponding to each heat concentration area. The temperature distribution characteristics include: average temperature, temperature range, thermal center position, isotherm distribution, etc.; the geometric characteristics include height, width, area, etc.

[0106] Step S503 : for each heat concentration area, determine whether the heat concentration area is a human body area based on the temperature distribution characteristics and the geometric characteristics.

[0107] In this embodiment, the indoor human body detection system determines whether the heat concentration area is a human body area based on the temperature distribution characteristics and geometric characteristics of each heat concentration area; it can be understood that the foreground thermal image includes multiple heat concentration areas, and each heat concentration area is identified to determine whether it is a human body area.

[0108] It should be noted that the human body area will show corresponding temperature distribution characteristics and geometric characteristics in the thermal image. The indoor human body detection system compares the temperature distribution characteristics of the human body area with the temperature distribution characteristics of each heat concentration area, and compares the geometric characteristics of the human body area with the geometric characteristics of each heat concentration area. Based on the comparison results, it can be determined whether each heat concentration area is a human body area.

[0109] Exemplarily, if the average temperature, temperature range, thermal center position, and isothermal distribution of the heat concentration area are the same as the average temperature, temperature range, thermal center position, and isothermal distribution of the human body area, and the height, width, and area of the heat concentration area are also the same as the height, width, and area of the human body area, it can be determined whether the heat concentration area is a human body area.

[0110] The indoor human detection system of this embodiment, when determining the possible presence of a human body indoors based on the measured heart rate, further generates a thermal image based on the infrared radiation signal, extracts a foreground thermal image from the thermal image, and then analyzes the temperature distribution characteristics and geometric features of each heat-concentrated area in the foreground thermal image to determine whether the heat-concentrated area is a human body area. When the measured heart rate determines the possible presence of a human body indoors, the system can further identify the human body area based on multiple features of the thermal image, thereby avoiding interference from indoor heat sources and improving the accuracy of indoor human detection.

[0111] Please refer to Figure 6 , Figure 6This is a flow chart of the sixth embodiment of the indoor human body detection method provided by the present application. The sixth embodiment differs from the first to fifth embodiments in that the step of determining whether the heat concentration area is a human body area based on the temperature distribution characteristics and the geometric characteristics includes:

[0112] Step S601: determining the temperature mean corresponding to the heat concentration area based on the temperature distribution characteristics.

[0113] In this embodiment, the indoor human body detection system determines the temperature mean value corresponding to the heat concentration area based on the temperature distribution characteristics of the heat concentration area.

[0114] Step S602: If the temperature mean is within the preset human body temperature range, the geometric feature is compared with the preset human body geometric feature.

[0115] In this embodiment, the indoor human body detection system compares the average temperature to the preset human body temperature range. If the average temperature is within the preset human body temperature range, the system further compares the geometric features corresponding to the heat concentration area with the preset human body geometric features. It should be noted that the preset human body geometric features include the geometric features of a standing human body, the geometric features of a lying human body, the geometric features of a sitting human body, and the geometric features of a squatting human body. The indoor human body detection system needs to compare the geometric features corresponding to the heat concentration area with the above multiple preset human body geometric features. This allows the system to identify human body areas in different indoor postures, thereby improving the accuracy of indoor human body detection.

[0116] Step S603: If the geometric features are the same as the preset human body geometric features, the heat concentration area is determined to be a human body area.

[0117] In this embodiment, the indoor human body detection system determines that a heat-concentrated area is a human body area if the geometric characteristics of the heat-concentrated area are identical to the preset human body geometric characteristics. Specifically, the heat-concentrated area is determined to be a human body area if the average temperature of the heat-concentrated area is within the preset human body temperature range and the geometric characteristics of the heat-concentrated area are identical to the preset human body geometric characteristics.

[0118] Step S604: If the temperature mean is not within the preset human body temperature range, or if the geometric feature is different from the preset human body geometric feature, it is determined that the heat concentration area is not a human body area.

[0119] In this embodiment, if the indoor human body detection system determines that the temperature mean is not within the preset human body temperature range, or determines that the geometric characteristics are different from the preset human body geometric characteristics, then the heat concentration area is determined not to be a human body area.

[0120] This embodiment identifies the human body area based on the temperature mean and geometric features corresponding to the heat concentration area. The human body area can be identified by multiple features, avoiding false alarms caused by single feature judgment and improving the accuracy of indoor human body detection.

[0121] refer to Figure 7 , Figure 7 : is a schematic diagram of the structure of the indoor human detection device provided by this application. The indoor human detection device includes:

[0122] A first determining module 10 is configured to collect infrared radiation signals in the room and extract a heart rate value from the infrared radiation signals;

[0123] a generating module 20 for generating a thermal image based on the infrared radiation signal if it is determined that the heart rate value is within a preset heart rate range;

[0124] The second determining module 30 is configured to determine that a human body exists in the room if a human body area is detected based on the thermal image.

[0125] The present application also provides a computer device. Exemplarily, the computer device includes a processor and a memory, wherein the memory stores a computer program, and the processor runs the computer program to enable the computer device to execute the functions of each module in the above-mentioned indoor human detection method or the above-mentioned indoor human detection device.

[0126] Among them, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including a central processing unit (CPU), a graphics processing unit (GPU) and a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or at least one of other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can implement or execute the disclosed methods, steps and logic block diagrams in the embodiments of the present application.

[0127] The memory may be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. The memory is used to store a computer program, and the processor may execute the computer program accordingly after receiving an execution instruction.

[0128] The present application also provides a computer storage medium for storing the computer program used in the above-mentioned computer device. The computer storage medium may be a readable storage medium, a non-volatile storage medium, or a volatile storage medium. For example, the computer storage medium may include, but is not limited to, various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0129] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or flowchart, and the combination of boxes in the structure diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0130] In addition, the functional modules or units in the various embodiments of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0131] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a smart phone, personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application.

[0132] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A method for detecting human body indoors, characterized in that: The method comprises: Collecting infrared radiation signals in the room and extracting heart rate values from the infrared radiation signals; If the heart rate value is within a preset heart rate range, generating a thermal image based on the infrared radiation signal; If a human body region is detected based on the thermal image, it is determined that a human body exists in the room.

2. The indoor human body detection method according to claim 1, characterized in that: The step of extracting the heart rate value from the infrared radiation signal comprises: performing filtering processing on the infrared radiation signal to obtain a reference infrared signal; Acquiring an indoor temperature, and obtaining a target infrared signal based on the indoor temperature and the reference infrared signal; A heart rate value is extracted based on the target infrared signal.

3. The indoor human body detection method according to claim 2, characterized in that: The step of obtaining a target infrared signal based on the indoor temperature and the reference infrared signal includes: determining an ambient infrared radiation signal based on the indoor temperature and a preset indoor ambient emissivity; Determining an environment reflected infrared signal based on the indoor temperature, a preset indoor environment emissivity, and a preset indoor environment reflectivity; A target infrared signal is determined based on the reference infrared signal, the ambient infrared radiation signal and the ambient reflected infrared signal.

4. The indoor human body detection method according to claim 2, characterized in that: The step of determining the heart rate value based on the target infrared signal includes: performing spectrum analysis on the target infrared signal, and extracting heart rate frequency domain features from the target infrared signal; Calculating a power spectrum density based on the heart rate frequency domain characteristics, and determining the heart rate wave frequency according to a peak value of the power spectrum density; A heart rate value is calculated according to the heart rate wave frequency.

5. The indoor human body detection method according to claim 1, characterized in that: Before the step of determining that a human body exists in the room if a human body area is detected based on the thermal image, the method includes: Segmenting the thermal image to obtain a foreground thermal image; extracting temperature distribution features and geometric features of each heat concentration area in the foreground thermal image; For each heat concentration area, whether the heat concentration area is a human body area is determined based on the temperature distribution characteristics and the geometric characteristics.

6. The indoor human body detection method according to claim 5, characterized in that: The step of determining whether the heat concentration area is a human body area based on the temperature distribution characteristics and the geometric characteristics includes: Based on the temperature distribution characteristics, determining the temperature mean corresponding to the heat concentration area; If the temperature mean is within the preset human body temperature range, comparing the geometric feature with the preset human body geometric feature; If the geometric features are the same as the preset human body geometric features, the heat concentration area is determined to be a human body area.

7. The indoor human body detection method according to claim 6, characterized in that: The step of determining whether the heat concentration area is a human body area based on the temperature distribution characteristics and the geometric characteristics further includes: If the temperature mean is not within the preset human body temperature range, or if the geometric feature is different from the preset human body geometric feature, it is determined that the heat concentration area is not a human body area.

8. An indoor human body detection device, characterized in that: The indoor human body detection device comprises: a first determining module, configured to collect an infrared radiation signal indoors and determine a heart rate value based on the infrared radiation signal; a generating module, configured to generate a thermal image based on the infrared radiation signal if it is determined that the heart rate value is within a preset heart rate range; The second determining module is configured to determine that a human body exists in the room if a human body area is detected based on the thermal image.

9. A computer device, characterized in that: The computer device includes a processor and a memory, the memory stores a computer program, and the processor is configured to execute the computer program to implement the indoor human body detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is run on a processor, the indoor human body detection method according to any one of claims 1 to 7 is executed.

Images