CN111707372B

CN111707372B - Human body temperature detection method, system and device and image processor

Info

Publication number: CN111707372B
Application number: CN202010478877.7A
Authority: CN
Inventors: 张焱; 张华宾; 林铭
Original assignee: Beijing Dushi Technology Co ltd
Current assignee: Beijing Dushi Technology Co ltd
Priority date: 2020-05-29
Filing date: 2020-05-29
Publication date: 2021-05-07
Anticipated expiration: 2040-05-29
Also published as: CN111707372A

Abstract

The application discloses a human body temperature detection method, a human body temperature detection system, a human body temperature detection device and an image processor. Wherein, the method comprises the following steps: acquiring a first visible light image acquired by visible light acquisition equipment and a first thermal infrared image acquired by thermal infrared image acquisition equipment; detecting a first target object in the first visible light image; detecting a second target object in the first thermal infrared image, and determining first temperature information of a designated part of the second target object; determining whether the first target object and the second target object are the same target object according to first relative position information of the first target object relative to other target objects in the first visible light image and second relative position information of the second target object relative to other target objects in the first thermal infrared image; and determining second temperature information of the designated portion of the first target object based on the first temperature information when the first target object and the second target object are determined to be the same target object.

Description

Human body temperature detection method, system and device and image processor

Technical Field

The present application relates to the field of human body temperature detection technologies, and in particular, to a human body temperature detection method, system, device, and image processor.

Background

Along with the increasing demand of people for detecting the human body temperature in a specified scene, a plurality of temperature measuring systems are provided for users in the market. Most of the existing temperature measurement systems are dual-light fusion temperature measurement systems, and are mainly realized by physical fusion of visible light acquisition equipment and thermal infrared acquisition equipment. Specifically, a visible light image acquired by the visible light acquisition device is received through the AI processor, a target object (human body) is identified in the visible light image, and coordinate information of the human body in the visible light image is determined. Then, the AI processor determines a human body image area in the thermal infrared image acquired by the thermal infrared acquisition equipment according to the coordinate information of the human body in the visible light image, and finally determines the temperature of the human body according to the thermal infrared pixel value of the human body image area in the thermal infrared image.

Therefore, the conventional dual-optical fusion temperature measurement system requires that the visible light collection device and the thermal infrared collection device must be accurately aligned, that is, the image scenes collected by the two collection devices need to be consistent, and only then can the coordinate information of the collected images of the thermal infrared collection device and the visible light collection device be ensured to be in one-to-one correspondence. However, in practical application scenarios, such precise alignment is difficult to achieve, and requires a great deal of manual work. Even if the temperature measurement device can be accurately aligned, the alignment can be affected along with the interference of expansion with heat, contraction with cold and the like of the system, so that the temperature measurement result is inaccurate.

Aiming at the technical problem that the current double-light fusion temperature measurement system in the prior art is mainly realized by physical fusion of visible light acquisition equipment and thermal infrared acquisition equipment, the visible light acquisition equipment and the thermal infrared acquisition equipment are required to be accurately aligned to a certain extent, so that the operation difficulty is high, the interference of expansion with heat, contraction with cold and the like is easy to cause, and the accuracy of a temperature measurement result is poor, an effective solution is not provided at present.

Disclosure of Invention

The invention provides a human body temperature detection method, a human body temperature detection system, a human body temperature detection device and an image processor, and at least solves the technical problems that the current double-light fusion temperature measurement system in the prior art is realized mainly by physical fusion of visible light acquisition equipment and thermal infrared acquisition equipment, the visible light acquisition equipment and the thermal infrared acquisition equipment are required to be accurately aligned to a certain extent, the operation difficulty is high, the interference of expansion with heat and contraction with cold is easy to happen, and the accuracy of a temperature measurement result is poor.

According to an aspect of the embodiments of the present disclosure, there is provided a human body temperature detection method, including: acquiring a first visible light image acquired by visible light acquisition equipment and a first thermal infrared image acquired by thermal infrared image acquisition equipment; detecting a first target object in the first visible light image; detecting a second target object in the first thermal infrared image, and determining first temperature information of a designated part of the second target object; determining whether the first target object and the second target object are the same target object according to first relative position information of the first target object relative to other target objects in the first visible light image and second relative position information of the second target object relative to other target objects in the first thermal infrared image; and determining second temperature information of the designated portion of the first target object based on the first temperature information when the first target object and the second target object are determined to be the same target object.

According to another aspect of the embodiments of the present disclosure, there is provided an image processor, including a first artificial intelligence processing module configured to acquire a first visible light image acquired by a visible light acquisition device and detect a first target object in the first visible light image; the second artificial intelligence processing module is configured to acquire a first thermal infrared image acquired by the thermal infrared image acquisition device and detect a second target object in the first thermal infrared image; the temperature detection module is connected with the second artificial intelligence processing module and is configured for determining first temperature information of the designated part of the second target object according to the first thermal infrared image; and the information fusion module is connected with the first artificial intelligence processing module, the second artificial intelligence processing module and the temperature detection module, and is configured to judge whether the first target object and the second target object are the same target object or not according to first relative position information of the first target object relative to other target objects in the first visible light image and second relative position information of the second target object relative to other target objects in the first thermal infrared image, and determine second temperature information of the specified part of the first target object according to the first temperature information under the condition that the first target object and the second target object are judged to be the same target object.

According to another aspect of the embodiments of the present disclosure, there is also provided a human body temperature detection system, including: visible light acquisition equipment and thermal infrared image acquisition equipment; and the image processor is in communication connection with the visible light acquisition device and the thermal infrared image acquisition device, and is configured to perform first target object detection on a first visible light image acquired by the visible light acquisition device, perform second target object detection and temperature detection on a first thermal infrared image acquired by the thermal infrared image acquisition device, and determine temperature information of the first target object according to a temperature detection result of the second target object.

According to another aspect of the embodiments of the present disclosure, there is also provided a human body temperature detection apparatus, including: the first acquisition module is used for acquiring a first visible light image acquired by visible light acquisition equipment and a first thermal infrared image acquired by thermal infrared image acquisition equipment; a first target object detection module for detecting a first target object in the first visible light image; the detection and temperature determination module is used for detecting a second target object in the first thermal infrared image and determining first temperature information of a designated part of the second target object; the judging module is used for judging whether the first target object and the second target object are the same target object or not according to first relative position information of the first target object relative to other target objects in the first visible light image and second relative position information of the second target object relative to other target objects in the first thermal infrared image; and a first determination module for determining second temperature information of the designated portion of the first target object based on the first temperature information when it is determined that the first target object and the second target object are the same target object.

According to another aspect of the embodiments of the present disclosure, there is also provided a human body temperature detection apparatus, including: a processor; and a memory coupled to the processor for providing instructions to the processor for processing the following processing steps: acquiring a first visible light image acquired by visible light acquisition equipment and a first thermal infrared image acquired by thermal infrared image acquisition equipment; detecting a first target object in the first visible light image; detecting a second target object in the first thermal infrared image, and determining first temperature information of a designated part of the second target object; determining whether the first target object and the second target object are the same target object according to first relative position information of the first target object relative to other target objects in the first visible light image and second relative position information of the second target object relative to other target objects in the first thermal infrared image; and determining second temperature information of the designated portion of the first target object based on the first temperature information when the first target object and the second target object are determined to be the same target object.

According to another aspect of the disclosed embodiments, there is also provided a storage medium. The storage medium comprises a stored program, wherein the above described method is performed by a processor when the program is run.

In the embodiment of the present invention, a first target object in a first visible light image is detected by a first artificial intelligence processing module, a second target object in a first thermal infrared image is detected by a second artificial intelligence processing module, temperature information of a designated portion of the second target object is determined by a temperature detection module according to the first thermal infrared image, whether the first target object and the second target object are the same target object is determined by an information fusion module according to first relative position information of the first target object with respect to other target objects in the first visible light image and second relative position information of the second target object with respect to other target objects in the first thermal infrared image, and in a case where the first target object and the second target object are determined to be the same target object, it means that the temperature information of the designated portion of the second target object detected by the second artificial intelligence processing module is equal to the same designated portion of the first target object The second temperature information of the designated portion of the first target object can be specified based on the first temperature information. Therefore, by the mode, the situation that the visible light acquisition equipment and the thermal infrared acquisition equipment are required to be accurately aligned is avoided, and the same target object can be ensured to be consistent in relative position information in the first visible light image and the first thermal infrared image as long as the deviation between the image scenes acquired by the visible light acquisition equipment and the thermal infrared acquisition equipment is kept within a certain reasonable range, so that the temperature of the target object can be accurately determined, the operation difficulty is low, the interference of thermal expansion, cold contraction and the like is avoided, and the accuracy of a temperature measurement result is greatly improved. And then solved current two optical fusion temperature measurement systems and mainly relied on the physical fusion of visible light collection equipment and thermal infrared collection equipment to realize, require that visible light collection equipment and thermal infrared collection equipment must accurate alignment, lead to the operation degree of difficulty high and easily receive interference such as expend with heat and contract with cold to lead to the poor technical problem of temperature measurement result accuracy.

The above and other objects, advantages and features of the present application will become more apparent to those skilled in the art from the following detailed description of specific embodiments thereof, taken in conjunction with the accompanying drawings.

Drawings

Some specific embodiments of the present application will be described in detail hereinafter by way of illustration and not limitation with reference to the accompanying drawings. The same reference numbers in the drawings identify the same or similar elements or components. Those skilled in the art will appreciate that the drawings are not necessarily drawn to scale. In the drawings:

fig. 1 is a schematic diagram of a human body temperature detection system according to embodiment 1 of the present disclosure;

fig. 2 is a schematic view of a first visible-light image with an added identification pattern according to embodiment 1 of the present disclosure;

fig. 3 is yet another schematic view of a first visible-light image with an added identification graphic according to embodiment 1 of the present disclosure;

fig. 4 is a flowchart of a human body temperature detection method according to a third aspect of embodiment 1 of the present disclosure;

fig. 5 is a schematic view of a human body temperature detection device according to embodiment 2 of the present disclosure; and

fig. 6 is a schematic diagram of a human body temperature detection device according to embodiment 3 of the present disclosure.

Detailed Description

It should be noted that, in the present disclosure, the embodiments and features of the embodiments may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

In order to make the technical solutions of the present disclosure better understood by those skilled in the art, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only some embodiments of the present disclosure, not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances for describing the embodiments of the disclosure herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.

Example 1

Fig. 1 is a schematic diagram of a human body temperature detection system according to embodiment 1 of the present application. Referring to fig. 1, a first aspect of embodiment 1 of the present application provides an image processor 300, which includes a first artificial intelligence processing module 330 configured to acquire a first visible light image acquired by a visible light acquisition device 100 and detect a first target object in the first visible light image; a second artificial intelligence processing module 340 configured to acquire the first thermal infrared image acquired by the thermal infrared image acquisition device 200 and detect a second target object in the first thermal infrared image; the temperature detection module 350 is connected with the second artificial intelligence processing module 340 and configured to determine first temperature information of a designated part of the second target object according to the first thermal infrared image; and an information fusion module 360, connected to the first artificial intelligence processing module 330, the second artificial intelligence processing module 340, and the temperature detection module 350, configured to determine whether the first target object and the second target object are the same target object according to first relative position information of the first target object with respect to other target objects in the first visible light image and second relative position information of the second target object with respect to other target objects in the first thermal infrared image, and determine second temperature information of the designated portion of the first target object according to the first temperature information under the condition that the first target object and the second target object are the same target object.

As described in the background art, most of the existing temperature measurement systems are dual-light fusion temperature measurement systems, and are mainly realized by physical fusion of visible light collection equipment and thermal infrared collection equipment. Specifically, a visible light image acquired by the visible light acquisition device is received through the AI processor, a target object (human body) is identified in the visible light image, and coordinate information of the human body in the visible light image is determined. Then, the AI processor determines a human body image area in the thermal infrared image acquired by the thermal infrared acquisition equipment according to the coordinate information of the human body in the visible light image, and finally determines the temperature of the human body according to the thermal infrared pixel value of the human body image area in the thermal infrared image. Therefore, the conventional dual-optical fusion temperature measurement system requires that the visible light collection device and the thermal infrared collection device must be accurately aligned, that is, the image scenes collected by the two collection devices need to be consistent, and only then can the coordinate information of the collected images of the thermal infrared collection device and the visible light collection device be ensured to be in one-to-one correspondence. However, in practical application scenarios, such precise alignment is difficult to achieve, and requires a great deal of manual work. Even if the temperature measurement device can be accurately aligned, the alignment can be affected along with the interference of expansion with heat, contraction with cold and the like of the system, so that the temperature measurement result is inaccurate.

Specifically, in view of the above problem, referring to fig. 1, the image processor 300 provided in the first aspect of the present embodiment can be applied to a dual optical fusion thermometry system. The image processor 300 provided by the present embodiment includes a first artificial intelligence processing module 330, a second artificial intelligence processing module 340, a temperature detection module 350, and an information fusion module 360. In the process of image processing, a first visible light image acquired by the visible light acquisition device 100 is first acquired by the first artificial intelligence processing module 330, and a first target object is detected in the first visible light image. Then, the second artificial intelligence processing module 340 obtains a first thermal infrared image collected by the thermal infrared image collecting device 200, and detects a second target object in the first thermal infrared image. First temperature information of the designated portion of the second target object is then determined from the first thermal infrared image by a temperature detection module 350 connected to the second artificial intelligence processing module 340. Such as but not limited to including the face, forehead and/or hands, etc.

Further, through the information fusion module 360 connected to the first artificial intelligence processing module 330, the second artificial intelligence processing module 340 and the temperature detection module 350, whether the first target object and the second target object are the same target object is determined according to the first relative position information of the first target object with respect to the other target object in the first visible light image and the second relative position information of the second target object with respect to the other target object in the first thermal infrared image, and in a case where the first target object and the second target object are determined to be the same target object, the second temperature information of the designated portion of the first target object is determined according to the first temperature information. For example, but not limiting of, first relative position information of the first target object with respect to other target objects in the first visible light image is a second target object at the left of the second row, and second relative position information of the second target object with respect to other target objects in the first thermal infrared image is also the second target object at the left of the second row. In this case, the information fusion module 360 determines that the first target object in the first visible light image and the second target object in the first thermal infrared image are the same target object. Therefore, the information fusion module 360 can determine the second temperature information of the designated portion of the first target object according to the first temperature information. For example, the first temperature information is the forehead temperature of the first target object, and the information fusion module 360 determines the first temperature information as the second temperature information of the designated portion (i.e., forehead) of the first target object.

Thus, in the present embodiment, the first target object in the first visible light image is detected by the first artificial intelligence processing module 330, the second target object in the first thermal infrared image is detected by the second artificial intelligence processing module 340, the temperature information of the designated portion of the second target object is determined by the temperature detection module 350 according to the first thermal infrared image, whether the first target object and the second target object are the same target object is determined by the information fusion module 360 according to the first relative position information of the first target object with respect to the other target objects in the first visible light image and the second relative position information of the second target object with respect to the other target objects in the first thermal infrared image, and in the case where the first target object and the second target object are determined to be the same target object, it means that the temperature information of the designated portion of the second target object detected by the second artificial intelligence processing module 340 is equal to the temperature information of the first target object The temperature information of the same designated portion, therefore, the second temperature information of the designated portion of the first target object can be specified from the first temperature information. Therefore, by the mode, the situation that the visible light acquisition equipment and the thermal infrared acquisition equipment are required to be accurately aligned is avoided, and the same target object can be ensured to be consistent in the relative position information of the first visible light image and the first thermal infrared image as long as the deviation between the image scenes acquired by the visible light acquisition equipment 100 and the thermal infrared acquisition equipment 200 is ensured to be kept within a certain reasonable range, so that the temperature of the target object can be accurately determined, the operation difficulty is low, the interference of thermal expansion, cold contraction and the like is avoided, and the accuracy of a temperature measurement result is greatly improved. And then solved current two optical fusion temperature measurement systems and mainly relied on the physical fusion of visible light collection equipment and thermal infrared collection equipment to realize, require that visible light collection equipment and thermal infrared collection equipment must accurate alignment, lead to the operation degree of difficulty high and easily receive interference such as expend with heat and contract with cold to lead to the poor technical problem of temperature measurement result accuracy.

Optionally, the operation of determining whether the first target object and the second target object are the same target object according to the first relative position information of the first target object relative to the other target objects in the first visible light image and the second relative position information of the second target object relative to the other target objects in the first thermal infrared image includes: determining arrangement position information of the first target object relative to other target objects in the first visible light image as first relative position information; determining arrangement position information of a second target object relative to other target objects in the first thermal infrared image as second relative position information; judging whether the first relative position information is consistent with the second relative position information; and determining that the first target object and the second target object are the same target object when the first relative position information and the second relative position information are determined to be consistent.

Specifically, in the process of determining whether the first target object and the second target object are the same target object, the arrangement position information of the first target object with respect to the other target objects in the first visible light image may be determined as the first relative position information. For example, the first visible light image includes a plurality of target objects, and the arrangement position information of the first target object with respect to the other target objects is a second target object located at the left of the second row. Arrangement position information of the second target object with respect to other target objects in the first thermal infrared image is then determined as second relative position information. For example: the first thermal infrared image also has a plurality of target objects, and the arrangement position information of the second target object relative to other target objects is a second target object at the left of the second row. In this case, since the first relative position information coincides with the second relative position information, as long as it is ensured that the deviation between the image scenes captured by the visible light capture device 100 and the thermal infrared capture device 200 is kept within a certain reasonable range, it means that the first target object and the second target object are the same target object. Similarly, in the case where the first relative position information does not coincide with the second relative position information, it means that the first target object and the second target object are not the same target object. In this way, whether the first target object and the second target object are the same target object can be reasonably determined.

In addition, it is also possible to determine whether the first target object and the second target object are the same target object based on the first positional deviation information and the second positional deviation information by selecting the same target reference object in the first visible light image and the first thermal infrared image, then determining first positional deviation information of the first target object with respect to the target reference object in the first visible light image, determining second positional deviation information of the second target object with respect to the target reference object in the first thermal infrared image, and determining whether the first target object and the second target object are the same target object based on the first positional deviation information and the second positional deviation information. In the process of selecting the reference object, for example, but not limited to, a target reference object may be detected in the first visible light image, and then the same target reference object may be detected in the first thermal infrared image according to the shape and contour of the detected target reference object and according to the first positional deviation information and the second positional deviation information.

Optionally, the first artificial intelligence processing module 330 is further configured to determine a first image region containing the designated part of the first target object in the first visible light image; and the information fusion module 360 is further configured to add an identification graphic related to the temperature of the specified portion of the first target object at the position of the first image region according to the second temperature information.

Specifically, referring to fig. 2, in the present embodiment, a first image region including a designated portion (for example, the forehead portion, the hand portion, etc.) of the first target object is first determined in the first visible light image by the first artificial intelligence processing module 330, then the second temperature information of the designated portion of the first target object detected by the temperature detection module 350 is fused with the first image region in the first visible light image by the information fusion module 360, and then an identification pattern related to the temperature of the designated portion of the first target object is added at the position of the first image region. As shown in fig. 2 and 3, for example, a color rectangular frame is added to the first image area for marking the position of the detected human face and/or human hand of the target object in the first image, and specific temperature information is added to a specific part (for example, the forehead, eyes, human hand, etc.) of the target object. Therefore, by the mode, the monitoring video with high definition and marks can be provided for monitoring workers, and the monitoring workers can monitor the monitoring video conveniently.

Optionally, the system further includes a third artificial intelligence processing module 370, connected to the first artificial intelligence processing module 330 and the information fusion module 360, and configured to acquire a face image region including a face of the first target object detected by the first artificial intelligence processing module 330, perform face recognition on the face image region, and determine identity information of the first target object; and the information fusion module 360 is further configured to add an identification graphic related to the identity of the first target object at the location of the first image region.

In the practical application process, the human face recognition needs to be carried out on the target object while the target object detection and the human body temperature detection are carried out. In the embodiment, a third artificial intelligence processing module 370 for face recognition is dynamically added to the image processor 300, wherein the third artificial intelligence processing module 370 is connected to the first artificial intelligence processing module 330 and the information fusion module 360. A face image region including the face of the first target object detected by the first artificial intelligence processing module 330 is acquired by the third artificial intelligence processing module 370, and face recognition detection is performed on the face image region, so as to determine the identity information of the first target object, for example, the determined identity information of the first target object is "the li-juan". Further, an identification graphic related to the identity of the first target object is added at the position of the first image area through the information fusion module 360. Accordingly, in this way, the first target object, the temperature information related to the first target object, and the identification information can be detected in the first visible light image. For example, the first target object can be detected in the first visible light image, the body temperature of the first target object is 36.5 °, the identity information of the first target object is "the silk, that is, the information fused by the information fusion module 360 is: the first target object in the first visible light image was a silk task with a body temperature of 36.5 °.

In addition, in the image processor provided in this embodiment, the modules related to target object detection (e.g., the first artificial intelligence processing module 330), the modules related to temperature detection (e.g., the second artificial intelligence processing module 340 and the temperature detection module 350), and the modules related to face recognition (e.g., the third artificial intelligence processing module 370) may be dynamically unloaded, so that the system temperature measurement is not affected when the modules related to target object detection are unloaded, the system is not affected when the modules related to face recognition are unloaded, and the system is not affected when the modules related to temperature detection are unloaded. By the method, the flexibility of the temperature measurement system in various application scenes is greatly improved.

Optionally, the method further comprises: the first preprocessing module 310 is configured to generate a second visible light image corresponding to the first visible light image, where the second visible light image is suitable for a preset first image detection model to perform detection; the first artificial intelligence processing module 330 includes a first designated part detection unit 331 and a first designated part mapping unit 332, wherein the first designated part detection unit 331 is connected to the first preprocessing module 310 and configured to detect a second image region including the designated part of the first target object in the second visible light image through the first image detection model; the first designated location mapping unit 332 is configured to determine the first image area in the first visible-light image based on the position information of the second image area in the second visible-light image.

Specifically, referring to fig. 1, the image processor 300 further includes a first preprocessing module 310 for generating a second visible light image corresponding to the first visible light image, wherein the second visible light image is suitable for the preset first image detection model to perform the detection. The first image detection model is an image detection model capable of carrying out image detection on a visible light image. Since the current image detection model usually supports recognition of an image with a resolution within a limited range, in order to ensure that the first artificial intelligence processing module 330 can effectively detect a target object in the first visible light image, in this embodiment, the first preprocessing module 310 needs to preprocess the acquired first visible light image, so as to generate a second visible light image suitable for detection by the first artificial intelligence processing module 330.

Further, the first artificial intelligence processing module 330 includes a first designated part detecting unit 331 and a first designated part mapping unit 332, wherein the first designated part detecting unit 331 is connected to the first preprocessing module 310, and is configured to detect a second image region including the designated part of the first target object in the second visible light image through the first image detection model. When the second image region including the designated portion is detected, the first designated portion mapping unit 332 needs to specify the first image region in the first visible-light image based on the positional information of the second image region in the second visible-light image. Therefore, in this way, not only the target object in the first visible light image can be effectively detected, but also the first image area can be accurately determined in the first visible light image.

Optionally, the first pre-processing module 310 comprises at least one of: a first format conversion unit 311 configured to convert the format of the image into a format matched with the first image detection model; a first resolution conversion unit 312 configured to convert a resolution of the image into a resolution matching the first image detection model; and a first image enhancement unit 313 configured to enhance detail information in the image.

Specifically, referring to fig. 1, the preprocessing module 210 includes at least one of a first format conversion unit 311, a first resolution conversion unit 312, and a first image enhancement unit 313. In the case where the format of the first visible-light image output by the visible-light image capturing apparatus 100 does not match the image format that can be processed by the first image detection model, the format of the image may be converted into a format that matches the first image detection model by the first format conversion unit 311

Further, in the case that the resolution of the first visible light image acquired by the visible light image acquisition device 100 is lower than the resolution of the image that can be detected by the first artificial intelligence processing module 330, the first resolution conversion unit 312 may be an upsampling unit, configured to perform an upsampling operation on the first visible light image, for example, the upsampling may be performed by using a polyphase filter or a linear filter, so as to complete the low-resolution to high-resolution enhancement.

Further, in the case that the resolution of the first visible-light image acquired by the visible-light image acquisition device 100 is higher than the resolution of the image that can be detected by the first artificial intelligence processing module 330, the first resolution conversion unit 312 may be a down-sampling unit for performing an up-sampling operation on the first visible-light image, so as to convert the resolution of the first visible-light image into a resolution matching the first image detection model.

Further, the detail information in the first visible light image may also be enhanced by the first image enhancing unit 313. Furthermore, in this embodiment, according to practical situations, any several items of the first format conversion unit 311, the first resolution conversion unit 312, and the first image enhancement unit 313 may be used in combination to pre-process the image captured by the visible light image capture device 100, so as to generate a second visible light image corresponding to the first visible light image and suitable for detection by a preset first image detection model.

Optionally, the operation of determining the first image region in the first visible light image according to the position of the second image region in the second visible light image includes: determining the position information of the first image area in the first visible light image according to the position information of the second image area in the second visible light image and the position mapping relation between the first visible light image and the second visible light image; and determining the first image area in the first visible light image according to the position information of the first image area in the first visible light image.

Specifically, the first designated area mapping unit 332 first converts the position information in the second visible-light image into corresponding position information in the first visible-light image, for example, by using a preset coordinate conversion algorithm, according to the position information of the second image area in the second visible-light image and the position mapping relationship between the first visible-light image and the second visible-light image, thereby determining the position information of the first image area in the first visible-light image. The determined position information of the first image area in the first visible light image may include, for example, x, y, w, h, i.e., x, y coordinates and width and height information of the first image area in the first visible light image. The first image area is then determined in the first visible-light image based on the position information of the first image area in the first visible-light image. In this way, the accuracy of the determined first image area is guaranteed.

Optionally, the operation of determining first temperature information of the designated part of the second target object according to the first thermal infrared image includes: determining a third image area containing a designated part of a second target object in the first thermal infrared image; and determining first temperature information of the designated part of the second target object according to the image information of the third image area.

Specifically, in the operation of determining the first temperature information of the specified portion of the second target object based on the first thermal infrared image, the third image area containing the specified portion of the second target object is first determined in the first thermal infrared image, and then the first temperature information of the specified portion of the second target object is determined based on the image information of the third image area. In this way, the accuracy of the determined first temperature information can be ensured.

Optionally, the method further comprises: the second preprocessing module 320 is configured to generate a second thermal infrared image corresponding to the first thermal infrared image, where the second thermal infrared image is suitable for a preset second image detection model to perform detection; the second artificial intelligence processing module 340 includes a second designated part detecting unit 341 and a second designated part mapping unit 342, wherein the second designated part detecting unit 341 is connected to the second preprocessing module 320 and configured to detect a fourth image region including a designated part of the second target object in the second thermal infrared image through the second image detection model; the second designated location mapping unit 342 is configured to determine the third image area in the first thermal infrared image based on the location information of the fourth image area in the second thermal infrared image.

Specifically, referring to fig. 1, the image processor 300 further includes a second preprocessing module 320 for generating a second thermal infrared image corresponding to the first thermal infrared image, wherein the second thermal infrared image is suitable for a preset second image detection model to perform detection. The second image detection model is an image detection model capable of detecting the thermal infrared image. Since the current second image detection model generally supports recognition of images with resolutions within a limited range (for example, the resolutions are 512 × 512, 640 × 360, 640 × 480 or others), in order to ensure that the second artificial intelligence processing module 340 can effectively detect the second target object in the first thermal infrared image, in this embodiment, the second preprocessing module 320 needs to preprocess the acquired first thermal infrared image, so as to generate the second thermal infrared image suitable for the second artificial intelligence processing module 340 to detect.

Further, the second artificial intelligence processing module 340 includes a second designated bit detection unit 341 and a second designated bit mapping unit 342. The second designated portion detecting unit 341 is connected to the second preprocessing module 320, and configured to detect, through the second image detection model, a fourth image area including a designated portion of the second target object in the second thermal infrared image. When the fourth image region including the designated portion of the second target object is detected, the second designated portion mapping unit 342 needs to specify the third image region in the first thermal infrared image based on the position information of the fourth image region in the second thermal infrared image. Therefore, in this way, not only the target object in the first thermal infrared image can be effectively detected, but also the third image area can be accurately determined in the first thermal infrared image.

Optionally, the second pre-processing module 320 comprises at least one of: a second format conversion unit 321 configured to convert the format of the thermal infrared image into a format matched with the second image detection model; a second resolution conversion unit 322 configured to convert the resolution of the thermal infrared image into a resolution matching the second image detection model; and a second image enhancement unit 323 configured to enhance detail information in the thermal infrared image.

Specifically, referring to fig. 1, the second pre-processing module 320 includes at least one of a second format conversion unit 321, a second resolution conversion unit 322, and a second image enhancement unit 323. In the case where the format of the first thermal infrared image output by the thermal infrared image capturing device 200 does not match the format of the image that can be processed by the second image detection model, the format of the image may be converted into a format that matches the second image detection model by the second format conversion unit 321.

Further, in a case that the resolution of the first thermal infrared image acquired by the thermal infrared image acquisition device 200 is lower than the resolution of the image that can be detected by the second artificial intelligence processing module 340, the second resolution conversion unit 322 may be an upsampling unit, configured to perform an upsampling operation on the first thermal infrared image, for example, the upsampling may be performed by using a polyphase filter or a linear filter, so as to complete the low resolution to high resolution. Therefore, the model does not need to be retrained based on the collected thermal infrared image, the resolution of the image is converted into the resolution matched with the image detection model, and then the low-resolution thermal infrared image is effectively detected by utilizing the existing artificial intelligence detection function.

Further, in the case that the resolution of the first thermal infrared image acquired by the thermal infrared image acquisition device 200 is higher than the resolution of the image which can be detected by the second artificial intelligence processing module 340, the second resolution conversion unit 322 may be a down-sampling unit for performing a down-sampling operation on the first thermal infrared image so as to convert the resolution of the first thermal infrared image into a resolution matching the second image detection model.

Further, due to the imaging characteristics of the thermal infrared sensor, low resolution and the like, the thermal infrared image is often noisy, and thus the edge information of the object is interfered. For the problem of high noise, the embodiment performs denoising through the second image enhancement unit 323 by using a preset denoising filter algorithm to suppress noise in the image without damaging the edge of the object. Common denoising and filtering algorithms include, for example, a bilateral filtering algorithm and a guided filtering algorithm.

Preferably, since the thermal infrared image is imaged according to the surface temperature of the object, and the temperature difference between the object and the background in the actual scene is not very large, the edge details of the object are not obvious in the thermal infrared image. To address this problem, the present embodiment may also perform edge enhancement by the second image enhancement unit 323 using a preset edge sharpening algorithm to enhance the detail information of the object. Common edge sharpening algorithms include, for example, laplacian filter algorithm and sobel filter algorithm.

In addition, it should be specifically noted that the second image enhancement unit 323 is not limited to include a denoising filter algorithm and an edge sharpening algorithm, and may also include other algorithms capable of enhancing image quality.

Preferably, the second preprocessing module 320 of this embodiment may also first convert the resolution of the first thermal infrared image into a resolution matching the second image detection model through the second resolution converting unit 322. Then, the image output from the second resolution conversion unit 322 is subjected to an image enhancement operation by the second image enhancement unit 323, so as to suppress noise in the image and enhance detail information in the image, thereby generating a second thermal infrared image suitable for detection by the second artificial intelligence processing module 340.

Furthermore, in this embodiment, according to practical situations, any several items of the second format conversion unit 321, the second resolution conversion unit 322 and the first image enhancement unit 323 can be used in combination to pre-process the image acquired by the thermal infrared image acquisition device 200, so as to generate a second thermal infrared image corresponding to the first thermal infrared image and suitable for detection by a preset second image detection model.

Optionally, the operation of determining the third image area in the first thermal infrared image according to the position information of the fourth image area in the second thermal infrared image includes: determining the position information of the third image area in the first thermal infrared image according to the position information of the fourth image area in the second thermal infrared image and the position mapping relation between the first thermal infrared image and the second thermal infrared image; and determining the third image area in the first thermal infrared image according to the position information of the third image area in the first thermal infrared image.

Specifically, the second specified position mapping unit 342 first converts the position information in the second thermal infrared image into corresponding position information in the first thermal infrared image according to the position information of the fourth image area in the second thermal infrared image and the position mapping relationship between the first thermal infrared image and the second thermal infrared image, for example, by using a coordinate conversion algorithm set in advance, thereby determining the position information of the third image area in the first thermal infrared image. The determined position information of the third image area in the first thermal infrared image may include, for example, x, y, w, h, i.e., x, y coordinates and width and height information of the third image area in the first thermal infrared image. The third image area is then determined in the first thermal infrared image based on the position information of the third image area in the first thermal infrared image. In this way, the accuracy of the determined third image area is guaranteed.

Optionally, the operation of determining the first temperature information of the designated part of the second target object according to the image information of the third image area includes: selecting a predetermined number of pixel points with the highest pixel values in a third image region; determining a temperature value corresponding to the selected pixel point according to the pixel value of the selected pixel point; and calculating an average temperature value according to the temperature value corresponding to the selected pixel point, and taking the average temperature value as first temperature information of the specified part of the second target object.

Specifically, the temperature detection module 350 selects a predetermined number of pixel points with the highest pixel values in the third image region, determines a temperature value corresponding to the selected pixel point according to the pixel values of the selected pixel points, and finally obtains an average temperature value according to the temperature value corresponding to the selected pixel point, and uses the average temperature value as the first temperature information of the designated portion of the second target object. In this way, the first temperature information of the designated portion of the second target object can be accurately determined.

Optionally, a temperature anomaly detection module 380 is further included, connected to the temperature detection module 350, and configured to determine whether the temperature of the designated portion of the second target object is anomalous according to the first temperature information and a preset temperature threshold.

Specifically, referring to fig. 1, the image processor 300 further includes a temperature abnormality detection module 380 connected to the temperature detection module 350. The temperature anomaly detection module 380 of the present embodiment determines whether the temperature of the designated portion of the second target object is anomalous or not according to the first temperature information of the designated portion of the second target object determined by the temperature detection module 350 and the preset temperature threshold. By the mode, the individual with abnormal temperature can be eliminated in time, and infection is avoided.

Optionally, the information fusion module 360 is further configured to add an identification pattern related to the temperature abnormality of the first target object at the position of the first image region, in case that the first target object and the second target object are determined to be the same target object and the temperature abnormality of the designated portion of the second target object is determined.

In practice, a monitoring worker monitors a target object, usually by watching a monitoring video. Therefore, if a mark for identifying the target object and the temperature distribution information of the target object (for example, a color rectangular frame is used to mark the target object, and a mark figure such as face temperature information and hand temperature information is added) can be added to the video, it is more beneficial for the monitoring staff to observe the monitoring video.

Specifically, fig. 2 exemplarily shows one schematic view of the first visible-light image to which the identification pattern is added, and fig. 3 exemplarily shows still another schematic view of the first visible-light image to which the identification pattern is added. Referring to fig. 1, 2 and 3, in the present embodiment, the information fusion module 360 determines whether the temperature of the designated portion of the second target object detected by the temperature detection module 350 is abnormal, and when the temperature of the designated portion of the second target object is determined to be abnormal and the first target object and the second target object are determined to be the same target object, it means that the temperature of the designated portion of the first target object is also abnormal, so an identification pattern related to the temperature abnormality of the first target object is added at the position of the first image region by the information fusion module 360, for example, a rectangular frame with different colors is used to distinguish whether the temperature of the human face and/or the human hand of the first target object is abnormal. Therefore, by the mode, the monitoring video with high definition and marks can be provided for monitoring workers, and the monitoring workers can monitor the monitoring video conveniently.

A second aspect of embodiment 1 of the present application provides a human body temperature detection system, including: a visible light collection device 100, a thermal infrared image collection device 200; and the image processor 300 according to any one of the above descriptions, wherein the image processor 300 is in communication connection with the visible light collection device 100 and the thermal infrared image collection device 200, and is configured to perform first target object detection on a first visible light image collected by the visible light collection device 100, perform second target object detection and temperature detection on a first thermal infrared image collected by the thermal infrared image collection device 200, and determine temperature information of the first target object according to a temperature detection result of the second target object.

Specifically, referring to fig. 1, a second aspect of embodiment 1 of the present application provides a human body temperature detection system, which includes a visible light collection device 100, a thermal infrared image collection device 200, and an image processor 300 described in any one of the above. Accordingly, a visible light image (corresponding to the first visible light image in fig. 1) may be acquired by the visible light acquisition device 100 (e.g., a visible light camera), a thermal infrared image (corresponding to the first thermal infrared image in fig. 1) may be acquired by the thermal infrared image acquisition device 200 (e.g., a thermal infrared camera), and then the acquired visible light image and the acquired thermal infrared image may be transmitted to the image processor 300 by the visible light acquisition device 100 and the thermal infrared image acquisition device 200. After receiving the visible light image collected by the visible light collection device 100 and the thermal infrared image collected by the thermal infrared image collection device 200, the image processor 300 performs a first target object detection on the visible light image, performs a second target object detection on the thermal infrared image and a temperature detection of a corresponding designated location (e.g., a human face and/or a human hand), and finally determines temperature information of the first target object according to a temperature detection result of the second target object. For example: determining whether the first target object and the second target object are the same target object, and in the case where it is determined that the first target object and the second target object are the same target object, meaning that the temperature information of the designated portion of the second target object is equal to the temperature information of the designated portion of the first target object, thus, in this way, it is no longer required that the visible light collection device and the thermal infrared collection device be precisely aligned, and as long as it is ensured that the deviation between the image scenes collected by the visible light collection device 100 and the thermal infrared collection device 200 is kept within a certain reasonable range, it is ensured that the relative position information of the same target object in the first visible light image and the first thermal infrared image is consistent, therefore, the temperature of the target object can be accurately determined, the operation difficulty is low, the interference of expansion caused by heat, contraction caused by cold and the like is avoided, and the accuracy of the temperature measurement result is greatly improved. And then solved current two optical fusion temperature measurement systems and mainly relied on the physical fusion of visible light collection equipment and thermal infrared collection equipment to realize, require that visible light collection equipment and thermal infrared collection equipment must accurate alignment, lead to the operation degree of difficulty high and easily receive interference such as expend with heat and contract with cold to lead to the poor technical problem of temperature measurement result accuracy.

Optionally, the human body temperature detection system further comprises: and the display module 410 is in communication connection with the information fusion module 360 of the image processor 300 and is used for displaying the first visible light image added with the identification graph.

Specifically, referring to the above, the information fusion module 360 is used to add an identification pattern at the position of the first image region. Therefore, referring to fig. 1, the human body temperature detection system further includes a display module 410, connected to the information fusion module 360, for displaying the first visible light image with the added identification pattern. Meanwhile, the collected temperature of the target object, the position of the target object and the relevant data of the first visible light image added with the identification graph can be sent to a remote server. Thus, not only can the first visible light image with the mark of the position information and the temperature information of the target object be displayed for the related staff, but also the remote server can conduct further data analysis.

Optionally, the human body temperature detection system further includes a network interface 420, communicatively connected to the information fusion module 360 of the image processor 300, for transmitting the first visible light image added with the identification pattern through a network.

Specifically, referring to fig. 1, the human body temperature detection system further includes a network interface 420, and the related data of the target object temperature, the target object position, and the first visible light image added with the identification pattern may be sent to the remote server through the network interface 420 for further data analysis.

Optionally, the human body temperature detection system further comprises an alarm module 430, communicatively connected to the temperature anomaly detection module 380 of the image processor 300, for giving an alarm if the temperature anomaly detection module 380 determines that the temperature of the designated portion of the target object is anomalous.

Specifically, referring to fig. 1, the human body temperature detection system further includes an alarm module 430, which is in communication connection with the temperature anomaly detection module 380. In the case where the temperature abnormality detection module 380 determines that the temperature of the specified portion of the target object is abnormal, the alarm module 430 issues an alarm. Therefore, by the method, when the temperature abnormality of the designated part of the target object is detected, related workers can be warned in time.

In the human body temperature detection system shown in fig. 1, referring to fig. 4, a third aspect of embodiment 1 of the present application proposes a human body temperature detection method. Referring to fig. 4, the method includes:

s401: acquiring a first visible light image acquired by visible light acquisition equipment and a first thermal infrared image acquired by thermal infrared image acquisition equipment;

s402: detecting a first target object in the first visible light image;

s403: detecting a second target object in the first thermal infrared image, and determining first temperature information of a designated part of the second target object;

s404: determining whether the first target object and the second target object are the same target object according to first relative position information of the first target object relative to other target objects in the first visible light image and second relative position information of the second target object relative to other target objects in the first thermal infrared image; and

s405: when the first target object and the second target object are judged to be the same target object, second temperature information of the designated part of the first target object is determined according to the first temperature information.

Wherein the designated area includes, for example and without limitation, a human face and/or a human hand.

Optionally, the method further comprises: determining a first image area containing a designated part of the first target object in the first visible light image; and adding an identification graphic related to the temperature of the specified part of the first target object at the position of the first image area according to the second temperature information.

Optionally, the method further comprises: acquiring a face image area of a face containing a first target object detected by a first artificial intelligence processing module, carrying out face recognition on the face image area, and determining identity information of the first target object; and adding an identification graphic associated with the identity of the first target object at the location of the first image region.

Optionally, the method further comprises: generating a second visible light image corresponding to the first visible light image, wherein the second visible light image is suitable for a preset first image detection model to detect; and an operation of determining a first image region containing a specified part of the first target object in the first visible-light image, including: detecting a second image area containing the designated part of the first target object in the second visible light image through the first image detection model; the image processing device is used for determining the first image area in the first visible light image according to the position information of the second image area in the second visible light image.

Optionally, the operation of generating the second visible light image corresponding to the first visible light image comprises at least one of: converting the format of the image into a format matched with the first image detection model; converting a resolution of the image to a resolution matching the first image detection model; and enhancing detail information in the image.

Optionally, the method further comprises: generating a second thermal infrared image corresponding to the first thermal infrared image, wherein the second thermal infrared image is suitable for a preset second image detection model to detect; and an operation of determining a third image region containing a specified portion of the second target object in the first thermal infrared image, including: detecting a fourth image area containing a designated part of the second target object in the second thermal infrared image through a second image detection model; and determining a third image area in the first thermal infrared image according to the position information of the fourth image area in the second thermal infrared image.

Optionally, the operation of generating a second thermal infrared image corresponding to the first thermal infrared image comprises: converting the format of the thermal infrared image into a format matched with the second image detection model; converting the resolution of the thermal infrared image to a resolution matching the second image detection model; and enhancing detail information in the thermal infrared image.

Optionally, the method further comprises: and judging whether the temperature of the designated part of the second target object is abnormal or not according to the first temperature information and a preset temperature threshold value.

Optionally, the method further comprises: when the first target object and the second target object are judged to be the same target object and the temperature of the designated part of the second target object is abnormal, an identification graph related to the temperature abnormality of the first target object is added at the position of the first image area.

The human body temperature detection method provided in the third aspect of this embodiment may refer to all descriptions in the image processor 300 provided in the first aspect, and may implement all functions of the image processor 300 provided in the first aspect, which are not described herein again.

Therefore, in the human body temperature detection method provided by the third aspect of the present embodiment, the first visible light image collected by the visible light collection device and the first thermal infrared image collected by the thermal infrared image collection device are first acquired, then the first target object in the first visible light image is detected, the second target object in the first thermal infrared image is detected, and the temperature information of the designated portion of the second target object is determined according to the first thermal infrared image. Finally, it is determined whether the first target object and the second target object are the same target object based on first relative position information of the first target object with respect to the other target object in the first visible light image and second relative position information of the second target object with respect to the other target object in the first thermal infrared image, and if it is determined that the first target object and the second target object are the same target object, it means that the detected temperature information of the designated portion of the second target object is equal to the temperature information of the same designated portion of the first target object, so that it is possible to determine the second temperature information of the designated portion of the first target object based on the first temperature information. Therefore, by the mode, the situation that the visible light acquisition equipment and the thermal infrared acquisition equipment are required to be accurately aligned is avoided, and the same target object can be ensured to be consistent in relative position information in the first visible light image and the first thermal infrared image as long as the deviation between the image scenes acquired by the visible light acquisition equipment and the thermal infrared acquisition equipment is kept within a certain reasonable range, so that the temperature of the target object can be accurately determined, the operation difficulty is low, the interference of thermal expansion, cold contraction and the like is avoided, and the accuracy of a temperature measurement result is greatly improved. And then solved current two optical fusion temperature measurement systems and mainly relied on the physical fusion of visible light collection equipment and thermal infrared collection equipment to realize, require that visible light collection equipment and thermal infrared collection equipment must accurate alignment, lead to the operation degree of difficulty high and easily receive interference such as expend with heat and contract with cold to lead to the poor technical problem of temperature measurement result accuracy.

Further, according to a fourth aspect of the present embodiment, there is provided a storage medium. The storage medium comprises a stored program, wherein the method of any of the above is performed by a processor when the program is run.

Example 2

Fig. 5 shows a human body temperature detection apparatus 500 according to the present embodiment, the apparatus 500 corresponding to the method according to the third aspect of embodiment 1. Referring to fig. 5, the apparatus 500 includes: a first obtaining module 510, configured to obtain a first visible light image collected by a visible light collecting device and a first thermal infrared image collected by a thermal infrared image collecting device; a first target object detection module 520 for detecting a first target object in the first visible light image; a detection and temperature determination module 530, configured to detect a second target object in the first thermal infrared image, and determine first temperature information of a designated portion of the second target object; a determining module 540, configured to determine whether the first target object and the second target object are the same target object according to first relative position information of the first target object with respect to other target objects in the first visible light image and second relative position information of the second target object with respect to other target objects in the first thermal infrared image; and a first determining module 550, configured to determine, when it is determined that the first target object and the second target object are the same target object, second temperature information of the designated portion of the first target object based on the first temperature information.

Optionally, the determining module 540 includes: the first determining submodule is used for determining the arrangement position information of the first target object relative to other target objects in the first visible light image as first relative position information; the second determining submodule is used for determining the arrangement position information of the second target object relative to other target objects in the first thermal infrared image as second relative position information; the first judgment submodule is used for judging whether the first relative position information is consistent with the second relative position information; and a second judging submodule for judging that the first target object and the second target object are the same target object under the condition that the first relative position information is judged to be consistent with the second relative position information.

Optionally, the method further comprises: a second determination module for determining a first image area containing a specified portion of the first target object in the first visible light image; and a first identification pattern adding module for adding an identification pattern related to the temperature of the specified part of the first target object at the position of the first image area according to the second temperature information.

Optionally, the method further comprises: the second acquisition module is used for acquiring a face image area of the face containing the first target object detected by the first artificial intelligence processing module, carrying out face recognition on the face image area and determining the identity information of the first target object; and a second identification graphic adding module for adding an identification graphic related to the identity of the first target object at the position of the first image area.

Optionally, the method further comprises: the first generation module is used for generating a second visible light image corresponding to the first visible light image, wherein the second visible light image is suitable for detection of a preset first image detection model; and the second determining module comprises: the detection submodule is used for detecting a second image area containing the designated part of the first target object in the second visible light image through the first image detection model; and the third determining submodule is used for determining the first image area in the first visible light image according to the position information of the second image area in the second visible light image.

Optionally, the first generating module comprises at least one of: the first format conversion sub-module is used for converting the format of the image into a format matched with the first image detection model; a first resolution conversion sub-module for converting a resolution of the image into a resolution matching the first image detection model; and a first image enhancer module for enhancing detail information in the image.

Optionally, the third determining sub-module includes: the first determining unit is used for determining the position information of the first image area in the first visible light image according to the position information of the second image area in the second visible light image and the position mapping relation between the first visible light image and the second visible light image; and a second determining unit configured to determine the first image region in the first visible-light image based on position information of the first image region in the first visible-light image.

Optionally, the detecting and temperature determining module 530 includes: a fourth determination submodule for determining a third image area containing a specified portion of the second target object in the first thermal infrared image; and a fifth determining submodule for determining first temperature information of the specified portion of the second target object based on the image information of the third image area.

Optionally, the method further comprises: the second generation module is used for generating a second thermal infrared image corresponding to the first thermal infrared image, wherein the second thermal infrared image is suitable for a preset second image detection model to detect; and a fourth determination submodule comprising: a detection unit configured to detect a fourth image area including a specified portion of the second target object in the second thermal infrared image by the second image detection model; and the third determining unit is used for determining the third image area in the first thermal infrared image according to the position information of the fourth image area in the second thermal infrared image.

Optionally, the second generating module comprises at least one of: the second format conversion sub-module is used for converting the format of the thermal infrared image into a format matched with the second image detection model; the second resolution conversion sub-module is used for converting the resolution of the thermal infrared image into the resolution matched with the second image detection model; and a second image enhancement sub-module for enhancing detail information in the thermal infrared image.

Optionally, the third determining unit includes: the first determining subunit is used for determining the position information of the third image area in the first thermal infrared image according to the position information of the fourth image area in the second thermal infrared image and the position mapping relationship between the first thermal infrared image and the second thermal infrared image; and a second determining subunit, configured to determine the third image area in the first thermal infrared image according to the position information of the third image area in the first thermal infrared image.

Optionally, a fifth determining submodule, comprising: the selecting unit is used for selecting a preset number of pixel points with the highest pixel values in the third image area; a fourth determining unit, configured to determine, according to the pixel value of the selected pixel point, a temperature value corresponding to the selected pixel point; and the calculating unit is used for calculating an average temperature value according to the temperature value corresponding to the selected pixel point, and taking the average temperature value as the first temperature information of the specified part of the second target object.

Optionally, the method further comprises: and the abnormity judging module is used for judging whether the temperature of the appointed part of the second target object is abnormal or not according to the first temperature information and a preset temperature threshold value.

Optionally, the method further comprises: and the third identification graph adding module is used for adding an identification graph related to the temperature abnormity of the first target object at the position of the first image area under the condition that the first target object and the second target object are the same target object and the temperature abnormity of the designated part of the second target object is judged.

Optionally, the designated area includes a human face and/or a human hand.

Thus, according to the present embodiment, the apparatus 500 first acquires the first visible light image collected by the visible light collecting device and the first thermal infrared image collected by the thermal infrared image collecting device, then detects the first target object in the first visible light image, detects the second target object in the first thermal infrared image, and determines the temperature information of the designated portion of the second target object according to the first thermal infrared image. Finally, it is determined whether the first target object and the second target object are the same target object based on first relative position information of the first target object with respect to the other target object in the first visible light image and second relative position information of the second target object with respect to the other target object in the first thermal infrared image, and if it is determined that the first target object and the second target object are the same target object, it means that the detected temperature information of the designated portion of the second target object is equal to the temperature information of the same designated portion of the first target object, so that it is possible to determine the second temperature information of the designated portion of the first target object based on the first temperature information. Therefore, by the mode, the situation that the visible light acquisition equipment and the thermal infrared acquisition equipment are required to be accurately aligned is avoided, and the same target object can be ensured to be consistent in relative position information in the first visible light image and the first thermal infrared image as long as the deviation between the image scenes acquired by the visible light acquisition equipment and the thermal infrared acquisition equipment is kept within a certain reasonable range, so that the temperature of the target object can be accurately determined, the operation difficulty is low, the interference of thermal expansion, cold contraction and the like is avoided, and the accuracy of a temperature measurement result is greatly improved. And then solved current two optical fusion temperature measurement systems and mainly relied on the physical fusion of visible light collection equipment and thermal infrared collection equipment to realize, require that visible light collection equipment and thermal infrared collection equipment must accurate alignment, lead to the operation degree of difficulty high and easily receive interference such as expend with heat and contract with cold to lead to the poor technical problem of temperature measurement result accuracy.

Example 3

Fig. 6 shows a human body temperature detection apparatus 600 according to the present embodiment, the apparatus 600 corresponding to the method according to the third aspect of embodiment 1. Referring to fig. 6, the apparatus 600 includes: a processor 610; and a memory 620 coupled to the processor 610 for providing instructions to the processor 610 to process the following processing steps: acquiring a first visible light image acquired by visible light acquisition equipment and a first thermal infrared image acquired by thermal infrared image acquisition equipment; detecting a first target object in the first visible light image; detecting a second target object in the first thermal infrared image, and determining first temperature information of a designated part of the second target object; determining whether the first target object and the second target object are the same target object according to first relative position information of the first target object relative to other target objects in the first visible light image and second relative position information of the second target object relative to other target objects in the first thermal infrared image; and determining second temperature information of the designated portion of the first target object based on the first temperature information when the first target object and the second target object are determined to be the same target object.

Optionally, the memory 620 is further configured to provide the processor 610 with instructions to process the following processing steps: determining a first image area containing a designated part of the first target object in the first visible light image; and adding an identification graphic related to the temperature of the specified part of the first target object at the position of the first image area according to the second temperature information.

Optionally, the memory 620 is further configured to provide the processor 610 with instructions to process the following processing steps: acquiring a face image area of a face containing a first target object detected by a first artificial intelligence processing module, carrying out face recognition on the face image area, and determining identity information of the first target object; and adding an identification graphic associated with the identity of the first target object at the location of the first image region.

Optionally, the memory 620 is further configured to provide the processor 610 with instructions to process the following processing steps: generating a second visible light image corresponding to the first visible light image, wherein the second visible light image is suitable for a preset first image detection model to detect; and an operation of determining a first image region containing a specified part of the first target object in the first visible-light image, including: detecting a second image area containing the designated part of the first target object in the second visible light image through the first image detection model; the image processing device is used for determining the first image area in the first visible light image according to the position information of the second image area in the second visible light image.

Optionally, the memory 620 is further configured to provide the processor 610 with instructions to process the following processing steps: generating a second thermal infrared image corresponding to the first thermal infrared image, wherein the second thermal infrared image is suitable for a preset second image detection model to detect; and an operation of determining a third image region containing a specified portion of the second target object in the first thermal infrared image, including: detecting a fourth image area containing a designated part of the second target object in the second thermal infrared image through a second image detection model; and determining a third image area in the first thermal infrared image according to the position information of the fourth image area in the second thermal infrared image.

Optionally, the memory 620 is further configured to provide the processor 610 with instructions to process the following processing steps: and judging whether the temperature of the designated part of the second target object is abnormal or not according to the first temperature information and a preset temperature threshold value.

Optionally, the memory 620 is further configured to provide the processor 610 with instructions to process the following processing steps: when the first target object and the second target object are judged to be the same target object and the temperature of the designated part of the second target object is abnormal, an identification graph related to the temperature abnormality of the first target object is added at the position of the first image area.

Optionally, the designated area includes a human face and/or a human hand.

Thus, according to this embodiment, the apparatus 600 first acquires the first visible light image collected by the visible light collecting device and the first thermal infrared image collected by the thermal infrared image collecting device, then detects the first target object in the first visible light image, detects the second target object in the first thermal infrared image, and determines the temperature information of the designated portion of the second target object according to the first thermal infrared image. Finally, it is determined whether the first target object and the second target object are the same target object based on first relative position information of the first target object with respect to the other target object in the first visible light image and second relative position information of the second target object with respect to the other target object in the first thermal infrared image, and if it is determined that the first target object and the second target object are the same target object, it means that the detected temperature information of the designated portion of the second target object is equal to the temperature information of the same designated portion of the first target object, so that it is possible to determine the second temperature information of the designated portion of the first target object based on the first temperature information. Therefore, by the mode, the situation that the visible light acquisition equipment and the thermal infrared acquisition equipment are required to be accurately aligned is avoided, and the same target object can be ensured to be consistent in relative position information in the first visible light image and the first thermal infrared image as long as the deviation between the image scenes acquired by the visible light acquisition equipment and the thermal infrared acquisition equipment is kept within a certain reasonable range, so that the temperature of the target object can be accurately determined, the operation difficulty is low, the interference of thermal expansion, cold contraction and the like is avoided, and the accuracy of a temperature measurement result is greatly improved. And then solved current two optical fusion temperature measurement systems and mainly relied on the physical fusion of visible light collection equipment and thermal infrared collection equipment to realize, require that visible light collection equipment and thermal infrared collection equipment must accurate alignment, lead to the operation degree of difficulty high and easily receive interference such as expend with heat and contract with cold to lead to the poor technical problem of temperature measurement result accuracy.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

The relative arrangement of the components and steps, the numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise. Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description. Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate. In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.

Spatially relative terms, such as "above … …," "above … …," "above … …," "above," and the like, may be used herein for ease of description to describe one device or feature's spatial relationship to another device or feature as illustrated in the figures. It will be understood that the spatially relative terms are intended to encompass different orientations of the device in use or operation in addition to the orientation depicted in the figures. For example, if a device in the figures is turned over, devices described as "above" or "on" other devices or configurations would then be oriented "below" or "under" the other devices or configurations. Thus, the exemplary term "above … …" can include both an orientation of "above … …" and "below … …". (the device may also be oriented 90 degrees or at other orientations in different ways), and the spatially relative descriptors used herein interpreted accordingly.

In the description of the present disclosure, it is to be understood that the orientation or positional relationship indicated by the directional terms such as "front, rear, upper, lower, left, right", "lateral, vertical, horizontal" and "top, bottom", etc., are generally based on the orientation or positional relationship shown in the drawings, and are presented only for the convenience of describing and simplifying the disclosure, and in the absence of a contrary indication, these directional terms are not intended to indicate and imply that the device or element being referred to must have a particular orientation or be constructed and operated in a particular orientation, and therefore, should not be taken as limiting the scope of the disclosure; the terms "inner and outer" refer to the inner and outer relative to the profile of the respective component itself.

The above description is only for the preferred embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A human body temperature detection method is characterized by comprising the following steps:

acquiring a first visible light image acquired by visible light acquisition equipment and a first thermal infrared image acquired by thermal infrared image acquisition equipment, wherein the deviation between image scenes acquired by the visible light acquisition equipment and the thermal infrared image acquisition equipment is kept within a certain range;

detecting a first target object in the first visible light image;

detecting a second target object in the first thermal infrared image, and determining first temperature information of a designated part of the second target object;

determining whether the first target object and the second target object are the same target object according to first relative position information of the first target object relative to other target objects in the first visible light image and second relative position information of the second target object relative to other target objects in the first thermal infrared image; and

and when the first target object and the second target object are judged to be the same target object, determining second temperature information of the designated part of the first target object according to the first temperature information.

2. A storage medium comprising a stored program, wherein the method of claim 1 is performed by a processor when the program is run.

3. An image processor (300), comprising:

a first artificial intelligence processing module (330) configured to acquire a first visible light image acquired by a visible light acquisition device (100) and detect a first target object in the first visible light image;

a second artificial intelligence processing module (340) configured to acquire a first thermal infrared image acquired by a thermal infrared image acquisition device (200) and detect a second target object in the first thermal infrared image, wherein a deviation between image scenes acquired by the visible light acquisition device (100) and the thermal infrared image acquisition device (200) is maintained within a certain range;

the temperature detection module (350) is connected with the second artificial intelligence processing module (340) and is configured for determining first temperature information of the appointed part of the second target object according to the first thermal infrared image; and

and an information fusion module (360) connected to the first artificial intelligence processing module (330), the second artificial intelligence processing module (340) and the temperature detection module (350), configured to determine whether the first target object and the second target object are the same target object according to first relative position information of the first target object with respect to other target objects in the first visible light image and second relative position information of the second target object with respect to other target objects in the first thermal infrared image, and determine second temperature information of a designated portion of the first target object according to the first temperature information when the first target object and the second target object are determined to be the same target object.

4. The image processor (300) of claim 3, wherein the operation of determining whether the first target object and the second target object are the same target object based on first relative position information of the first target object with respect to other target objects in the first visible light image and second relative position information of the second target object with respect to other target objects in the first thermal infrared image comprises:

determining arrangement position information of the first target object relative to other target objects in the first visible light image as the first relative position information;

determining arrangement position information of the second target object relative to other target objects in the first thermal infrared image as the second relative position information;

determining whether the first relative position information and the second relative position information are consistent; and

when it is determined that the first relative position information matches the second relative position information, it is determined that the first target object and the second target object are the same target object.

5. The image processor (300) of claim 3, wherein the first artificial intelligence processing module (330) is further configured to determine a first image region in the first visible light image containing a designated part of the first target object; and is

The information fusion module (360) is further configured to add an identification graphic related to the temperature of the specified portion of the first target object at the position of the first image region according to the second temperature information.

6. The image processor (300) of claim 5, further comprising a third artificial intelligence processing module (370), connected to the first artificial intelligence processing module (330) and the information fusion module (360), configured to obtain a face image region including the face of the first target object detected by the first artificial intelligence processing module (330), perform face recognition on the face image region, and determine identity information of the first target object; and is

The information fusion module (360) is further configured for adding an identification graphic related to the identity of the first target object at the location of the first image region.

7. The image processor (300) of claim 5, further comprising: a first preprocessing module (310) configured to generate a second visible light image corresponding to the first visible light image, wherein the second visible light image is suitable for a preset first image detection model to detect; and is

The first artificial intelligence processing module (330) includes a first designated part detection unit (331) and a first designated part mapping unit (332), wherein

The first specified part detection unit (331) is connected to the first preprocessing module (310) and configured to detect a second image region including the specified part of the first target object in the second visible light image by the first image detection model;

the first designated location mapping unit (332) is configured to determine the first image area in the first visible-light image based on position information of the second image area in the second visible-light image.

8. The image processor (300) of claim 7, wherein the operation of determining the first image region in the first visible light image based on the position of the second image region in the second visible light image comprises:

determining the position information of the first image area in the first visible light image according to the position information of the second image area in the second visible light image and the position mapping relation between the first visible light image and the second visible light image; and

and determining the first image area in the first visible light image according to the position information of the first image area in the first visible light image.

9. The image processor (300) of claim 3, wherein the operation of determining first temperature information of a designated portion of the second target object from the first thermal infrared image comprises:

determining a third image region containing a designated portion of the second target object in the first thermal infrared image; and

and determining first temperature information of the appointed part of the second target object according to the image information of the third image area.

10. The image processor (300) of claim 9, further comprising: a second preprocessing module (320) configured to generate a second thermal infrared image corresponding to the first thermal infrared image, wherein the second thermal infrared image is suitable for a preset second image detection model to detect; and is

The second artificial intelligence processing module (340) includes a second designated location detecting unit (341) and a second designated location mapping unit (342), wherein

The second specified part detection unit (341) is connected with the second preprocessing module (320) and configured to detect a fourth image area containing a specified part of the second target object in the second thermal infrared image through the second image detection model;

the second specified location mapping unit (342) is configured to determine the third image area in the first thermal infrared image based on location information of the fourth image area in the second thermal infrared image.

11. The image processor (300) of claim 9, wherein the operation of determining first temperature information of a designated part of the second target object from the image information of the third image region comprises:

selecting a preset number of pixel points with the highest pixel values in the third image area;

determining a temperature value corresponding to the selected pixel point according to the pixel value of the selected pixel point; and

and calculating an average temperature value according to the temperature value corresponding to the selected pixel point, and taking the average temperature value as first temperature information of the specified part of the second target object.

12. The image processor (300) of claim 5, further comprising a temperature anomaly detection module (380), connected to the temperature detection module (350), configured to determine whether the temperature of the designated portion of the second target object is anomalous based on the first temperature information and a preset temperature threshold.

13. The image processor (300) of claim 12, wherein the information fusion module (360) is further configured to add an identification graphic related to the temperature anomaly of the first target object at the position of the first image region in case it is determined that the first target object and the second target object are the same target object and the temperature anomaly of the designated part of the second target object.

14. A human body temperature detection system, comprising: a visible light acquisition device (100), a thermal infrared image acquisition device (200); and an image processor (300) as claimed in any one of claims 3 to 13, wherein

The image processor (300) is in communication connection with the visible light acquisition device (100) and the thermal infrared image acquisition device (200), and is configured to perform first target object detection on a first visible light image acquired by the visible light acquisition device (100), perform second target object detection and temperature detection on a first thermal infrared image acquired by the thermal infrared image acquisition device (200), and determine temperature information of the first target object according to a temperature detection result of the second target object.

15. A human body temperature detection device, comprising:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a first visible light image acquired by visible light acquisition equipment and a first thermal infrared image acquired by thermal infrared image acquisition equipment, and the deviation between image scenes acquired by the visible light acquisition equipment and the thermal infrared image acquisition equipment is kept within a certain range;

a first target object detection module for detecting a first target object in the first visible light image;

the detection and temperature determination module is used for detecting a second target object in the first thermal infrared image and determining first temperature information of a designated part of the second target object;

a determination module, configured to determine whether the first target object and the second target object are the same target object according to first relative position information of the first target object with respect to other target objects in the first visible light image and second relative position information of the second target object with respect to other target objects in the first thermal infrared image; and

and a first determining module, configured to determine, when it is determined that the first target object and the second target object are the same target object, second temperature information of a designated portion of the first target object according to the first temperature information.

16. A detection device for detecting the temperature of a designated part and a human body is characterized by comprising:

a processor; and

a memory coupled to the processor for providing instructions to the processor for processing the following processing steps:

detecting a first target object in the first visible light image;