Hybrid body temperature measurement system and method thereof

Abstract

A hybrid body temperature measurement system and method are disclosed. In the method, position sensing data is obtained. The position sensing data includes one or more objects' azimuth angles relative to a reference position. The position sensing data is mapped to a thermal image to generate a mapping result. The thermal image is imaged in response to temperature. The objects' positions in the thermal image are determined based on the mapping result. Accordingly, the detection accuracy can be improved.

Description

Technical Field

[0001] This invention relates to a biometric technology, and more particularly to a hybrid body temperature measurement system and method. Background Technology

[0002] Patients with certain infectious diseases may present with fever or high temperature symptoms. To prevent these patients from entering specific areas, people passing through entrances are usually required to have their temperature checked. Using thermal imaging cameras to remotely observe the temperature of passersby is a convenient and safe method for control personnel. Therefore, thermal imaging cameras are typically installed at the entrances of department stores, hospitals, subway stations, and other similar locations.

[0003] Generally, thermal imagers are set with specific temperature thresholds. When the temperature of a certain area in the thermal image exceeds this threshold, the thermal imager assumes that a human body has been detected in that area and marks its temperature. However, existing thermal imagers cannot distinguish whether the object in the area is actually a human or a non-living object. For example, the temperature of a floor exposed to sunlight may exceed the temperature threshold. Furthermore, existing thermal imagers cannot determine the relative distance of the object being detected. Therefore, different temperatures may be obtained when a human body is measured at different distances from the sensor, leading to high errors and a high false positive rate in the detection results. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a hybrid body temperature measurement system and method that combines the sensing results of thermal images with more accurate position sensing data to improve accuracy and identification efficiency.

[0005] The hybrid body temperature measurement method of this invention includes (but is not limited to) the following steps: acquiring position sensing data. The position sensing data includes the azimuth angles of one or more objects to be measured relative to a reference position. Mapping the position sensing data onto a thermal image to produce a mapping result. The thermal image is formed in response to temperature. Determining the position of one or more objects to be measured in the thermal image based on the mapping result.

[0006] The hybrid temperature measurement system of this invention includes (but is not limited to) a computing device. The computing device is configured to acquire position sensing data, map the position sensing data onto a thermal image to generate a mapping result, and determine the position of one or more objects under test in the thermal image based on the mapping result. The position sensing data includes the azimuth angle of one or more objects under test relative to a reference position. The thermal image is formed in response to temperature. The position of one or more objects under test in the thermal image is determined based on the mapping result.

[0007] Based on the above, in the hybrid body temperature measurement system and method of this invention, the mapping result between position sensing data and thermal image is obtained, and the position of the object to be measured in the thermal image is confirmed accordingly. This improves the accuracy of body temperature measurement.

[0008] To make the above features and advantages of the present invention more apparent and understandable, specific embodiments are described below in conjunction with the accompanying drawings. Attached Figure Description

[0009] Figure 1 This is a block diagram of a hybrid body temperature measurement system according to an embodiment of the present invention.

[0010] Figure 2 This is a flowchart of a hybrid body temperature measurement method according to an embodiment of the present invention.

[0011] Figure 3 This is a flowchart of generating mapping results according to an embodiment of the present invention.

[0012] Figure 4 This is a schematic diagram of block division according to an embodiment of the present invention.

[0013] Figure 5 This is a schematic diagram of sub-block division according to an embodiment of the present invention.

[0014] Figure 6 This is a flowchart of the first temperature determination condition according to an embodiment of the present invention.

[0015] Figure 7 This is a flowchart of the second temperature determination condition according to an embodiment of the present invention.

[0016] Figure 8 This is a flowchart of comparison data according to an embodiment of the present invention.

[0017] Figure 9 This is a schematic diagram of azimuth conversion according to an embodiment of the present invention.

[0018] Figure 10 This is a flowchart of position confirmation according to an embodiment of the present invention.

[0019] Figure 11 This is a schematic diagram of the mapping result according to an embodiment of the present invention.

[0020] Figure 12 This is a schematic diagram showing the position confirmation according to an embodiment of the present invention.

[0021] Figure 13 This is a flowchart of multi-person location confirmation according to an embodiment of the present invention.

[0022] Figures 14 to 16 This is a schematic diagram of multiple-person location confirmation according to an embodiment of the present invention.

[0023] Figure 17 This is a flowchart of temperature correction according to an embodiment of the present invention.

[0024] [Symbol Explanation]

[0025] 1: Hybrid Body Temperature Measurement System

[0026] 10: Temperature sensor

[0027] 30: Distance sensor

[0028] 50: Monitor

[0029] 100: Computing device

[0030] 110: Memory

[0031] 130: Processor

[0032] S210~S250, S310~S350, S610~S670, S710~S770, S810~S830, S1010~S1050, S1310~S1330, S1710~S1750: Steps

[0033] X, Y: Axis

[0034] M, TG: Thermal imaging

[0035] L1~L4: Length

[0036] P1, P2: Characters

[0037] A1~A7, An: Block

[0038] An01~An16, A701~A716: Sub-blocks

[0039] C: Horizontal center

[0040] θ1, θ2: Viewpoint

[0041] RP: Reference Position

[0042] O1~O4: Analytes

[0043] PA1, PA2, PA3, P A2_1 P A2_2 P A703_max_center :Location

[0044] A2_1, A2_2: Second Block

[0045] D A2_1 D A2_2 :distance Detailed Implementation

[0046] Figure 1This is a block diagram of a hybrid body temperature measurement system 1 according to an embodiment of the present invention. Please refer to... Figure 1 The hybrid body temperature measurement system 1 includes (but is not limited to) a temperature sensor 10, a distance sensor 30, and a computing device 100.

[0047] Temperature sensor 10 may be a thermal imaging camera, infrared camera, thermal imaging camera, or other sensor that images in response to temperature or infrared radiation. Temperature sensor 10 may include, but is not limited to, electronic components such as an infrared-sensitive photosensitive element, lens, focusing mechanism, and image processor. In one embodiment, temperature sensor 10 may generate a thermal image, and the sensed values ​​(e.g., temperature or infrared radiation) on several pixels in the thermal image may form a data array (e.g., each element in a two-dimensional array corresponds to one pixel). The thermal image or its data array records the temperature distribution.

[0048] The distance sensor 30 can be a radar, a time-of-flight (ToF) camera, a LiDAR scanner, a depth sensor, an infrared rangefinder, an ultrasonic sensor, or other distance-related sensors. In one embodiment, the distance sensor 30 can detect the azimuth angle of the object being measured, i.e., the azimuth angle of the object relative to the distance sensor 30. In another embodiment, the distance sensor 30 can detect the distance of the object being measured, i.e., the distance of the object relative to the distance sensor 30. In yet another embodiment, the distance sensor 30 can detect the number of objects within the field of view (FOV). In some embodiments, one or more of the aforementioned detection results (e.g., azimuth angle, distance, and / or number) can be used as position sensing data.

[0049] In one embodiment, both the distance sensor 30 and the temperature sensor 10 are positioned vertically from a specific reference location. This reference location can be determined based on the user's actual needs. For example, the reference location could be the exact center of a desktop.

[0050] The computing device 100 may be a desktop computer, a notebook computer, a smartphone, a tablet computer, a server, a thermal imager, or other computing device. The computing device 100 includes (but is not limited to) a memory 110 and a processor 130. The computing device 100 is coupled to a distance sensor 30 and a temperature sensor 10.

[0051] The memory 110 can be any type of fixed or removable random access memory (RAM), read-only memory (ROM), flash memory, hard disk drive (HDD), solid-state drive (SSD), or similar component. In one embodiment, the memory 110 is used to record program code, software modules, configuration settings, data (e.g., thermal images, position sensing data, temperature, position, decision results, etc.), or files, as will be described in detail later.

[0052] Processor 130 is coupled to memory 110. Processor 130 may be a central processing unit (CPU), a graphics processing unit (GPU), or other programmable general-purpose or special-purpose microprocessor, digital signal processor (DSP), programmable controller, field-programmable gate array (FPGA), application-specific integrated circuit (ASIC), neural network accelerator, or other similar components or combinations thereof. In one embodiment, processor 130 is used to execute all or part of the operations of the image processing device 100, and can load and execute various program codes, software modules, files, and data recorded in memory 110.

[0053] In some embodiments, the body temperature measurement system 1 further includes a display 50. The display 50 may be a liquid crystal display (LCD), a light-emitting diode (LED) display, an organic light-emitting diode (OLED), a quantum dot display, or other types of display. The display 50 is coupled to the computing device 100. In one embodiment, the display 50 is used to display a thermal image.

[0054] In one embodiment, the devices and / or components in the body temperature measurement system 1 may be integrated into a standalone device. In another embodiment, some of the devices and / or components in the body temperature measurement system 1 may be integrated into a standalone device and may communicate with other devices and / or components to acquire data. For example, the thermal imager (including the computing unit 100, the temperature sensor 10, and the display 50) may have the distance sensor 30 externally connected or directly integrated with the distance sensor 30.

[0055] The methods described in the embodiments of the present invention will be explained below in conjunction with the various devices, components, and modules in the hybrid body temperature measurement system 1. The various processes of this method may be adjusted according to the implementation situation, and are not limited thereto.

[0056] Figure 2 This is a flowchart of a hybrid body temperature measurement method according to an embodiment of the present invention. Please refer to... Figure 2 The processor 130 can acquire position sensing data (step S210). Specifically, the distance sensor 30 can generate position sensing data. In one embodiment, the position sensing data includes the azimuth angle of the object being measured relative to a reference position. The object being measured is, for example, a person, cat, dog, or other living organism, or the ground, table, chair, or other inanimate object. The reference position is the location of the temperature sensor 10 and the distance sensor 30. In another embodiment, the position sensing data includes the distance of the object being measured relative to the reference position. In yet another embodiment, the position sensing data includes the number of objects being measured.

[0057] Processor 130 can map position sensing data to a thermal image to generate a mapping result (step S230). Specifically, temperature sensor 10 can generate a thermal image. It is worth noting that in the prior art, position sensing data cannot be directly converted into coordinates or positions on a thermal image. This embodiment of the invention combines position sensing data and thermal images to make the final identification result (related to the quantity, location, and / or distance of the object under test) more accurate. Therefore, this embodiment of the invention needs to determine the relationship between position sensing data and thermal images (corresponding to the mapping result).

[0058] Figure 3 This is a flowchart illustrating the generation of mapping results according to an embodiment of the present invention. Please refer to... Figure 3In one embodiment, the processor 130 can divide the thermal image into multiple blocks according to multiple vertical lines (step S310). Specifically, in the following text, the left-right direction of the thermal image is considered the horizontal direction (or lateral direction), and the up-down direction of the thermal image is considered the vertical direction (or longitudinal direction). It is worth noting that the temperature sensor 10 has a specific field of view (FOV). The content in the thermal image is the objects and / or scenes within this field of view. Therefore, if two objects to be measured are located at different positions in the horizontal direction of the thermal image, it represents different azimuth angles of the two objects to be measured relative to the reference position (i.e., the position of the temperature sensor 10). Dividing the thermal image in the vertical direction is intended to obtain the azimuth angles of the objects to be measured relative to the reference position.

[0059] For example, Figure 4 This is a schematic diagram illustrating the division of blocks A1 to A7 according to an embodiment of the present invention. Please refer to... Figure 4 Assume the thermal image M is L1*L1 (e.g., length L1 is 80 pixels), with the X-axis horizontal and the Y-axis vertical. The processor 130 divides the image into blocks A1, A3, A5, and A7 every L2 (e.g., 20 pixels). The figures P1 and P2 (i.e., the objects under test) are located in different blocks. Furthermore, the processor 130 can further divide the image into blocks A2, A4, and A6 every L2 after shifting a specific length (e.g., 10 pixels) from the leftmost position. Blocks A1 and A3 partially overlap with block A2, and so on for the remaining blocks. Therefore, in a scene with multiple people present, the figures may exist in a single block or multiple blocks of the thermal image M. Figure 3 As shown, character P1 covers blocks A1 to A5, while character P2 covers blocks A6 to A7.

[0060] It should be noted that the aforementioned length, shape, quantity, and division method are merely illustrative examples and are not intended to limit the invention. Users can change their values ​​or content according to actual needs. For example, the number of blocks can be increased or decreased in response to the sensitivity of the actual application.

[0061] To further confirm whether the object under test exists in a block of thermal image, processor 130 may divide one or more blocks into one or more sub-blocks. For example, Figure 5 This is a schematic diagram illustrating the division of sub-blocks An01 to An16 according to an embodiment of the present invention. Please refer to... Figure 5 Processor 130 pairs of blocks An (n is a positive integer, for example, An is...) Figure 4 The blocks A1 to A7 are then further divided into multiple sub-blocks An01 to An16, each with a size of L3*L4 (e.g., length L3 and L4 are 10 pixels).

[0062] It should be noted that, Figure 5The diagram shows a block An cut into equal lengths along both the vertical and horizontal directions. However, in other embodiments, the number and direction of the cuts can be varied depending on the application requirements.

[0063] Please refer to Figure 3 The processor 130 can determine whether there is a test object in each block based on the temperature response of the thermal image to generate a judgment result (step S330). Specifically, after the thermal image is cut into multiple blocks or even multiple sub-blocks, the processor 130 can confirm which blocks and / or sub-blocks have a specified test object or which test object enters or exits this block and / or sub-block.

[0064] In one embodiment, the processor 130 may determine a representative temperature for one or more sub-blocks within each block, and determine whether the corresponding block contains one or more analytes based on a comparison between the representative temperature and a temperature threshold. The representative temperature may be correlated with the standard deviation, mean, or mode. The comparison result may be equal to, greater than, less than, not greater than, or not less than.

[0065] Figure 6 This is a flowchart illustrating the first temperature determination condition according to an embodiment of the present invention. Please refer to... Figure 6 The processor 130 can determine the average temperature of each sub-block and the temperature standard deviation of these average temperatures statistically analyzed for each sub-block within a specific time interval (e.g., 500 or 1000 milliseconds, depending on the sensitivity of the actual application) (step S610). The processor 130 can determine the sub-blocks Anm within block An (m is a positive integer, e.g., ...). Figure 5 The temperature standard deviation δ of 1 to 16) Anm Is it greater than the standard deviation threshold T? δ (Depending on empirical values ​​for different application scenarios) (Step S630). At this point, the temperature is represented by the temperature standard deviation δ. Anm And the temperature threshold is the standard deviation threshold T. δ If any one or more sub-blocks Anm are determined to have a temperature standard deviation δ Anm Greater than the standard deviation threshold T δ (i.e., comparison results), then the processor 130 can determine whether the test object exists in its block An or whether the test object enters or leaves this block An (i.e., judgment result) (step S650). If all or a specific number of sub-blocks Anm are determined to have a temperature standard deviation δ Anm Not greater than the standard deviation threshold T δ (i.e., comparison result), then the processor 130 can determine that the block An to which it belongs does not contain the object to be tested or the object to be tested has not entered or left this block An (i.e., judgment result) (step S670).

[0066] For example, observe data changes over 1000 milliseconds in a calm indoor environment. That is, the standard deviation threshold T.δ The value is 0.1, and the time interval is 1000 milliseconds. If the data does not change significantly within this 1-second period, then the temperature standard deviation δ is... Anm It will approach 0 and be less than the standard deviation threshold T δ , and indicates that no object enters or leaves the range of block An; conversely, it indicates that the object to be measured enters or leaves the range of block An.

[0067] The first temperature determination condition mainly observes whether the object to be tested has entered the area by measuring the overall momentum, but it cannot distinguish whether the object is a living organism or a thermal disturbance. Therefore, this embodiment of the invention proposes a second temperature determination condition.

[0068] Figure 7 This is a flowchart illustrating the second temperature determination condition according to an embodiment of the present invention. Please refer to... Figure 7 Processor 130 can determine the average temperature of each block (step S710). Processor 130 can determine the average temperature T of each block Anm in block An. nm Is it greater than the average threshold T? exist (Step S730). At this point, the representative temperature is the average temperature T. nm And the temperature threshold is the average threshold T exist (Its value is usually the lower limit of the body temperature of a specified type of test subject, such as 34-35 degrees Celsius for the human body). If any one or more sub-blocks Anm are determined to have an average temperature T nm Greater than the average threshold T exist (i.e., comparison result), then the processor 130 can determine whether the test object exists in its block An or whether the test object enters or leaves this block An (i.e., judgment result) (step S750). If all or a specific number of sub-blocks Anm are determined to have an average temperature T nm Not greater than the average threshold T exist (i.e., comparison result), then the processor 130 can determine that the block An to which it belongs does not contain the object to be tested or the object to be tested has not entered or left this block An (i.e., judgment result) (step S770).

[0069] Please refer to Figure 3 The processor 130 can compare the judgment result of the thermal image with the position sensing data to generate a mapping result (step S350). Specifically, the processor 130 finds the correlation between the judgment result of the thermal image and the position sensing data. This correlation includes the correspondence of azimuth angles.

[0070] Figure 8 This is a flowchart of comparison data according to an embodiment of the present invention. Please refer to... Figure 8The processor 130 can convert the azimuth angles corresponding to one or more objects under test in the position sensing data to the corresponding blocks in the thermal image (step S810). Specifically, since different blocks correspond to different azimuth angles, the processor 130 can map the azimuth angles of the position sensing data to specific blocks. In terms of device design, the user can arrange the center positions of the distance sensor 30 and the temperature sensor 10 to overlap in the vertical direction, so that the center point of the horizontal viewing angle of the distance sensor 30 and the horizontal viewing angle of the temperature sensor 10 can be matched at a position with the horizontal center on the X-axis.

[0071] For example, Figure 9 This is a schematic diagram of azimuth angle conversion according to an embodiment of the present invention. Please refer to... Figure 9 Both temperature sensor 10 and distance sensor 30 are located at reference position RP. Assuming the thermal image size is 80*80, and the X-axis coordinates covered by the viewing angle θ1 of temperature sensor 10 are 0~80, then the X-axis coordinate of the horizontal center C is 40. Furthermore, distance sensor 30 has the same horizontal center C at viewing angle θ2.

[0072] In addition, the azimuth conversion formula is as follows:

[0073] T angle =R angle –(RA max -TA max ) / 2…(1)

[0074] Among them, RA max For the maximum horizontal viewing angle θ2 of the distance sensor 30 (corresponding to its field of view), TA max R is the maximum horizontal viewing angle θ1 (corresponding to its field of view) of the temperature sensor 10. angle T is the azimuth angle before the position sensing data conversion. angle This is the azimuth angle after conversion from position sensing data.

[0075] The transformed X-axis coordinates are:

[0076] T xpos =T angle *(TX max / TA max (2)

[0077] Among them, TX max The size / length of the thermal image in the horizontal direction (e.g., is Figure 4 or Figure 9 80), T xpos These are the transformed X-axis coordinates. That is, the transformed coordinates are derived based on the proportional relationship between angle and length.

[0078] To determine the block to which the azimuth of the position sensing data belongs (i.e., the X-axis coordinate T corresponding to the azimuth), xpos If the block is located in which part of block An, then processor 130 can determine the X-axis coordinate T. xpos The X-axis coordinate V of the nearest block An, perpendicular to the center line / middle line of the X-axis. n :

[0079] |T xpos -V n |<(I AN / 2)…(3)

[0080] Among them, I AN The spacing between the center lines of adjacent blocks (in terms of...) Figure 4 Taking block segmentation as an example, I AN =TX max / 8). If it conforms to formula (3), then processor 130 determines the X-axis coordinate T. xpos If it is in this block An; otherwise, processor 130 determines the X-axis coordinate T. xpos Not in this block An.

[0081] It should be noted that the proportional relationship in the aforementioned formulas (1) and (2) assumes that the viewing angle θ2 is different from the viewing angle θ1. However, in other embodiments, if the viewing angle θ2 is equal to the viewing angle θ1, then formulas (1) and (2) can be ignored.

[0082] The processor 130 can determine that the judgment result of each block and the position sensing data on the same block both contain one or more objects to be measured, and generate a mapping result accordingly. Specifically, if the azimuth of the position sensing data has been mapped to a specific block in the thermal image, the processor 130 can further compare the two data sets on the same block (i.e., the position sensing data and the thermal image).

[0083] In one embodiment, the processor 130 can determine whether there is a test object (assuming it is a living organism, such as a human body) on each block based on a decision table. Table (1) shows a decision table illustrating one embodiment:

[0084] Table (1)

[0085]

[0086] In the result of formula (3), "yes" indicates that the azimuth angle corresponding to this block has detected the object to be measured in the position sensing data. "yes" in the result of the first temperature judgment condition indicates that the temperature variation of this block is large, and "yes" in the result of the second temperature judgment condition indicates that a specific type of object to be measured has been detected in this block. Conversely, the same applies, and will not be elaborated further.

[0087] In one embodiment, the processor 130 can determine that the judgment result of each block and the position sensing data of the same block both contain a target (step S830), and generate a mapping result accordingly. The mapping result includes that at least one block contains one or more targets. Taking Table (1) as an example, the decision result of situation 1 and situation 3 is that a target has been detected ("yes"). Wherein, when the temperature variation is not too large (the result of the first temperature judgment condition is "no"), the decision result is related to a stationary target. When the temperature variation is too large (the result of the first temperature judgment condition is "yes"), the decision result is related to a moving target.

[0088] In another embodiment, the mapping result may also be that no test object was detected in the block. For example, in Table (1), except for situation 1 and situation 3, all other situations are considered as no test object was detected.

[0089] Please refer to Figure 2 The processor 130 can determine the position of the object under test in the thermal image based on the mapping result (step S250). Specifically, the mapping result can help confirm the actual position of the object under test in the thermal image. This position is, for example, the coordinates of the object under test in the two-dimensional coordinate system formed by the thermal image. Alternatively, the position may also be the relative position of the object under test with other reference points in the thermal image.

[0090] Figure 10 This is a flowchart illustrating position confirmation according to an embodiment of the present invention. Please refer to... Figure 10 The processor 130 can determine the target block based on the mapping result (step S1010). The target block is the block confirmed to contain the object to be tested after comparing two sets of data. For example, a block that matches conditions 1 and 3 in Table (1) is the target block. Another example is that only a block that matches condition 1 in Table (1) is the target block. Yet another example is that only a block that matches condition 3 in Table (1) is the target block.

[0091] Processor 130 can determine the highest temperature among multiple sub-blocks in each target block of the thermal image (step S1030). Specifically, processor 130 can select one or more sub-regions with the highest temperature based on the judgment result of a second temperature judgment condition (e.g., the average temperature is greater than the average threshold). The determination of the highest temperature may be based on the numerical value or by comparing an upper limit value.

[0092] The processor 130 can determine the position of the object under test based on the sub-block with the highest temperature (step S1050). For example, the processor 130 uses the coordinates of the center point, the upper right corner, or any position within the range of the sub-block as the position of the object under test.

[0093] In one embodiment, the processor 130 can map the relative distances to the object being measured recorded in the position sensing data to blocks in the thermal image. Specifically, Figure 11 This is a schematic diagram of the mapping result according to an embodiment of the present invention. Please refer to... Figure 11 Assume that the test objects O1 to O3 are located in blocks A1, A2, and A7, respectively. The mapping results can be found in Table (2):

[0094] Table (2)

[0095]

[0096] In addition, regarding the location of the analyte O3, Figure 12 This is a schematic diagram illustrating position confirmation according to an embodiment of the present invention. Please refer to... Figure 12 The test object O3 is located in block A7. Assume that sub-blocks A702, S703, A710, and A711 meet the second temperature judgment condition (i.e., the average temperature is greater than the average threshold). If the highest temperature among these sub-blocks A702, S703, A710, and A711 is sub-block A703, then processor 130 can define the center point of this sub-block A703 as the location P of the test object O3. A703_max_center .

[0097] For multiple location confirmation, Figure 13 This is a flowchart illustrating multi-person location confirmation according to an embodiment of the present invention. Please refer to... Figure 13 The processor 130 can divide the target block into multiple secondary blocks based on the number of distances corresponding to the target block (step S1310). At this time, the mapping result includes multiple distances corresponding to a certain target block. That is, multiple objects to be measured are detected within a certain azimuth angle range of the position sensing data (corresponding to this target block), or the number of detected objects is greater than one.

[0098] For example, Figure 14 This is a schematic diagram of multi-person location confirmation according to an embodiment of the present invention, and Table (3) shows the mapping results. Please refer to... Figure 14 According to Table (3), the positions PA1 and PA3 of the test object O1 and test object O3 can be identified in the thermal image TG. However, block A2 corresponds to two distances. Therefore, it is not yet possible to determine which distance the position PA2 of the highest temperature corresponds to.

[0099] Table (3)

[0100]

[0101] Figure 15 This is a schematic diagram illustrating the location confirmation of multiple individuals according to an embodiment of the present invention. Please refer to... Figure 15The processor 130 can divide block A2 into two second blocks, A2_1 and A2_2, based on the number of location sensing data recorded in block A2 (e.g., 2). It should be noted that the size and number of the second blocks need to be determined according to actual requirements.

[0102] Please refer to Figure 13 The processor 130 can determine the second blocks corresponding to the target block and their distance from the object under test (step S1330). In the thermal image, the farther away an object is from the sensor 30, the closer its position will be to the second block at the top of the image; conversely, the closer it is, the closer its position will be to the bottom of the image. Similarly, according to steps S1030 and S1050, the processor 130 can determine the position of the highest temperature object in each second block. That is, the representative position of the highest temperature object in each second block where the average temperature is greater than the average threshold.

[0103] Figure 16 This is a schematic diagram illustrating the location confirmation of multiple individuals according to an embodiment of the present invention. Please refer to... Figures 14 to 16 And Table (3), the distance D of the analyte O2 A2_1 The distance is 100 centimeters, therefore it belongs to the second block A2_1 (relatively far away, higher in the second block), and its position is P. A2_1 The distance D of the test object O4 A2_2 The distance is 50 centimeters, therefore it belongs to the second block A2_2 (closer in distance, lower in the second block), and its position is P. A2_2 Therefore, the mapping results can be updated as shown in Table (4):

[0104] Table (4)

[0105]

[0106] Simply analyzing thermal images cannot definitively determine the distance to the object being measured, nor can it distinguish the number of people. However, this embodiment of the invention combines position sensing information from the distance sensor 30, which can further confirm the distance and identify multiple objects being measured.

[0107] To obtain accurate temperature measurements, in one embodiment, the processor 130 can compensate for the temperature of the object under test in the thermal image based on its position in the thermal image. The processor 130 can provide corresponding temperature calibration tables for different distances. For commercially available temperature measuring devices (such as forehead thermometers), the common temperature calibration method is linear correction: a temperature-stabilized heat source device (such as a blackbody furnace, which can generate a specified uniform temperature on the machine surface) is set up, the temperature-stabilized heat source device is adjusted to a fixed temperature point, and then the operator uses a temperature measuring device to measure the temperature-stabilized heat source device to obtain the temperature value. Then, the above actions are repeated and the temperature-stabilized heat source device is adjusted to several different temperature points, such as 33, 35, 36, 37, and 38 degrees. The temperatures measured by the temperature measuring device can be recorded as a reference temperature dataset. On the other hand, the temperature sensor 10 also simultaneously measures the temperature-stabilized heat source device at different temperatures and records it as a temperature dataset to be calibrated. In addition, the operator can change the distance of the temperature sensor 10 relative to the temperature-stabilized heat source device and measure the temperature-stabilized heat source device at different temperatures respectively.

[0108] In application, temperature sensor 10 measures the object to be measured. If a value x is obtained, processor 130 needs to determine where the temperature range I of value x falls in the temperature dataset to be corrected. Then, processor 130 finds the linear slope value a and offset value b of temperature range I in the reference temperature dataset to compensate for the value x, and outputs the corrected temperature y, which is the accurate body temperature.

[0109] y = ax + b...(4)

[0110] Applying formula (4) (static correction formula) to the body temperature measurement results of one or more people, the processor 130 can correct the temperature of different objects to be measured. Inevitably, in real applications, the objects to be measured will move. If the measurement results of the temperature sensor 10 are compared with the results of the temperature measuring device (e.g., forehead thermometer) used as a reference, the temperature value obtained by formula (4) will be slightly lower. Since the object to be measured is in a stationary state during the calibration process but is actually in a moving state during the actual measurement, this embodiment of the invention takes into account the compensation for the object to be measured during dynamic measurement (corresponding to situation 1 in Table (1)). Therefore, formula (4) is modified and a compensation value c is added (forming a dynamic correction formula):

[0111] y = ax + b + c…(5)

[0112] Figure 17 This is a flowchart of temperature correction according to an embodiment of the present invention. Please refer to... Figure 1The processor 130 can determine whether the object under test is in a stationary state based on the decision results obtained from Table (1) (step S1710). For example, state 1 is in a moving state and state 3 is in a stationary state. If it is in a stationary state, the processor 130 can correct the temperature according to the static correction formula (4) (step S1730). If it is in a moving state, the processor 130 can correct the temperature according to the dynamic correction formula (5) (step S1750).

[0113] If the distance is determined solely by the temperature sensor 10, clothing worn by the person may obscure the skin, leading to excessively large errors in distance estimation. Since this embodiment of the invention uses position sensing data obtained from the distance sensor 30 to acquire more accurate distance information, the corrected temperature is closer to the actual temperature.

[0114] In some embodiments, the processor 130 may combine the thermal image with the aforementioned mapping results (e.g., the position, distance, and / or corrected temperature of the object under test) and further present richer and more accurate information through the display 50.

[0115] In summary, according to the hybrid body temperature measurement system and method of the present invention, the distance sensing data obtained by the distance sensor can be mapped (or matched) with thermal images (or array data) to confirm the position, quantity, and temperature of the objects to be measured in the thermal images. This improves the accuracy of position, quantity, and temperature detection and enables the detection of multiple objects.

[0116] Although the present invention has been disclosed above with reference to embodiments, it is not intended to limit the present invention. Those skilled in the art can make some modifications and refinements without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the scope defined in the appended claims.

Claims

1. A hybrid body temperature measurement method, comprising: Position sensing data and thermal images are obtained from a distance sensor and a temperature sensor, respectively, wherein the distance sensor and the temperature sensor are arranged at a reference position and face the same direction with the same horizontal center. The position sensing data includes the distance and azimuth angle of at least one object relative to the reference position, and the thermal image is imaged in response to the temperature of the area within the field of view of the temperature sensor. The thermal image is divided into multiple blocks according to multiple vertical lines, and the azimuth angle of the at least one object to be measured included in the position sensing data is mapped to the corresponding block in the thermal image. The mapping result is generated by mapping the corresponding block in the thermal image to the distance corresponding to the at least one object under test based on the azimuth angle of the at least one object under test; as well as The location of at least one object to be measured in the thermal image is determined based on the mapping result. The step of determining the position of at least one object to be measured in the thermal image based on the mapping result includes: Determine at least one target block from the plurality of blocks, wherein each of the at least one target block includes the at least one test object; In response to a mapping result indicating that one of the at least one target block in the thermal image includes multiple distances from position sensing data, and each of the multiple distances corresponds to one of the at least one objects under test, the at least one target block is divided into multiple secondary blocks according to the number of the multiple distances, wherein the arrangement direction of these secondary blocks is perpendicular to the arrangement direction of the blocks; and Based on the distance between the at least one test object and the reference position, for each of the at least one test objects present in the at least one target block, the corresponding second block in the plurality of second blocks is determined.

2. The hybrid body temperature measurement method as described in claim 1, wherein the step of mapping the location sensing data to the thermal image to generate the mapping result includes: Based on the temperature response of the thermal image, determine whether each block contains at least one object to be measured to generate a judgment result; as well as The mapping result is generated by comparing the judgment result of the thermal image with the location sensing data.

3. The hybrid body temperature measurement method as described in claim 2, wherein the step of generating the judgment result includes: Determine the representative temperature of at least one block within each of these blocks; as well as Based on the comparison result between the representative temperature and the temperature threshold, it is determined whether the corresponding block contains at least one analyte.

4. The hybrid body temperature measurement method of claim 3, wherein the step of determining the representative temperature for each block includes: Determine the average temperature of each block in that iteration; as well as The temperature standard deviation is determined based on the average temperature, and this temperature standard deviation is used as the representative temperature.

5. The hybrid body temperature measurement method as described in claim 3, wherein the step of generating the judgment result includes: Determine the average temperature of each block, where the average temperature is used as the representative temperature.

6. The hybrid body temperature measurement method as described in claim 2, wherein the step of comparing the judgment result of the thermal image with the location sensing data includes: The azimuth angle corresponding to the at least one object under test in the position sensing data is converted to the corresponding block in the thermal image; as well as The determination result of each block and the location sensing data of the same block both contain at least one object to be measured, and the mapping result is generated accordingly.

7. The hybrid body temperature measurement method as described in claim 1, wherein the step of determining the position of the at least one object to be measured in the thermal image based on the mapping result further includes: Determine at least one of the highest temperatures among multiple sub-blocks within each target block in the thermal image; as well as The location of the at least one test object is determined based on the sub-block of the at least one highest temperature.

8. The hybrid body temperature measurement method as described in claim 1, further comprising: The temperature of the at least one object under test in the thermal image is compensated based on its position in the thermal image.

9. The hybrid body temperature measurement method as claimed in claim 1, wherein the position sensing data is obtained by the distance sensor, the thermal image is obtained by the temperature sensor and used for display, and both the distance sensor and the temperature sensor are located in the vertical direction of the reference position.

10. A hybrid body temperature measurement system, comprising: Distance sensor; A temperature sensor, wherein the distance sensor and the temperature sensor are arranged at a reference position and face the same direction with the same horizontal center; as well as The arithmetic unit is configured to: Position sensing data and thermal images are obtained from the distance sensor and the temperature sensor, respectively. The position sensing data includes the distance and azimuth of at least one object relative to the reference position, and the thermal image is formed in response to the temperature of the area within the field of view of the temperature sensor. The thermal image is divided into multiple blocks according to multiple vertical lines, and the azimuth angle of the at least one object to be measured included in the position sensing data is mapped to the corresponding block in the thermal image. A mapping result is generated by mapping the corresponding block in the thermal image to the distance corresponding to the at least one object under test based on the azimuth angle of the object under test; and The location of at least one object to be measured in the thermal image is determined based on the mapping result. The computing device is also configured to: Determine at least one target block from the plurality of blocks, wherein each of the at least one target block includes the at least one test object; In response to a mapping result indicating that one of the at least one target blocks in the thermal image includes multiple distances in the position sensing data and each of the multiple distances corresponds to one of the at least one objects under test, the at least one target block is divided into multiple secondary blocks according to the number of the multiple distances, wherein the arrangement direction of these secondary blocks is perpendicular to the arrangement direction of these blocks. as well as Based on the distance between the at least one test object and the reference position, for each of the at least one test objects present in the at least one target block, the corresponding second block in the plurality of second blocks is determined.

11. The hybrid body temperature measurement system of claim 10, wherein the computing device is further configured to: Based on the temperature response of the thermal image, a determination is made as to whether each block contains at least one object to be measured, thereby generating a determination result; and The mapping result is generated by comparing the judgment result of the thermal image with the location sensing data.

12. The hybrid body temperature measurement system of claim 11, wherein the computing device is further configured to: Determine the representative temperature of at least one block within each of those blocks; and Based on the comparison result between the representative temperature and the temperature threshold, it is determined whether the corresponding block contains at least one analyte.

13. The hybrid body temperature measurement system of claim 12, wherein the computing device is further configured to: Determine the average temperature of each block; and The temperature standard deviation is determined based on the average temperature, and this temperature standard deviation is used as the representative temperature.

14. The hybrid body temperature measurement system of claim 12, wherein the computing device is further configured to: Determine the average temperature of each block, where the average temperature is used as the representative temperature.

15. The hybrid body temperature measurement system of claim 11, wherein the computing device is further configured to: Convert the azimuth angle corresponding to the at least one object under test in the position sensing data to the corresponding block in the thermal image; and The determination result of each block and the location sensing data of the same block both contain at least one object to be measured, and the mapping result is generated accordingly.

16. The hybrid body temperature measurement system of claim 10, wherein the mapping result includes at least one of the blocks containing the at least one analyte, and the computing device is further configured to: Determine at least one of the highest temperatures among multiple sub-blocks within each target block in the thermal image; and The location of the at least one test object is determined based on the sub-block of the at least one highest temperature.

17. The hybrid body temperature measurement system of claim 10, wherein the computing device is further configured to: The temperature of the at least one object under test in the thermal image is compensated based on its position in the thermal image.

18. The hybrid body temperature measurement system of claim 10, further comprising: A distance sensor is coupled to the computing device and used to acquire the position sensing data; as well as A temperature sensor is coupled to the computing device and used to acquire the thermal image, wherein the thermal image is used for display, and both the distance sensor and the temperature sensor are located in the vertical direction of the reference position.

Images