An infrared image generation method, apparatus, device, and storage medium

Abstract

The application discloses an infrared image generation method, device and equipment and a storage medium. The method comprises the following steps: determining a temperature region in a detection region and a quantized value of the temperature of each temperature region according to an original thermal imaging signal collected by an infrared thermal imaging sensor; determining a mapping relationship between a temperature grade and a color system according to the quantized value of the temperature of each temperature region, the number of temperature grades and a preset color system; performing color mapping according to the quantized value of the temperature of each temperature region and the mapping relationship between the temperature grade and the color system, generating a candidate infrared image, and determining labeling information of the candidate infrared image based on a preset object recognition model; and processing the candidate infrared image according to a target display layer, a target display object category and the labeling information, and generating a target infrared image. The technical scheme of the application can more comprehensively extract available information in a signal and generate an accurate and effective infrared image.

Description

Technical Field

[0001] This invention relates to the field of image technology, and in particular to an infrared image generation method, apparatus, device, and storage medium. Background Technology

[0002] As infrared thermal imaging sensors are widely used in fields such as fire rescue and post-disaster fire situation assessment, the requirements for the image quality of infrared thermal imaging sensors are becoming increasingly stringent.

[0003] How to process the signals collected by infrared thermal imaging sensors, extract more comprehensive usable information from the signals, generate accurate and effective infrared images, and assist relevant personnel in making more accurate assessments and judgments of the fire scene environment is an urgent problem to be solved. Summary of the Invention

[0004] This invention provides an infrared image generation method, apparatus, device, and storage medium, which can more comprehensively extract usable information from signals and generate accurate and effective infrared images.

[0005] According to one aspect of the present invention, an infrared image generation method is provided, comprising:

[0006] Based on the raw thermal imaging signal collected by the infrared thermal imaging sensor, the temperature range within the detection area is determined, as well as the quantified value of the temperature in each temperature range.

[0007] Based on the quantified values ​​of temperature in each temperature zone, the number of temperature levels, and the preset color system, determine the mapping relationship between temperature levels and color systems.

[0008] Based on the quantified values ​​of temperature in each temperature region and the mapping relationship between temperature level and color system, color mapping is performed to generate candidate infrared images, and the annotation information of the candidate infrared images is determined based on the preset object recognition model.

[0009] Based on the target display layer, the target object category, and the annotation information, the candidate infrared images are processed to generate the target infrared image.

[0010] According to another aspect of the present invention, an infrared image generation apparatus is provided, comprising:

[0011] The numerical determination module is used to determine the temperature range within the detection area and the quantified temperature value of each temperature range based on the raw thermal imaging signal collected by the infrared thermal imaging sensor.

[0012] The relationship determination module is used to determine the mapping relationship between temperature levels and color systems based on the quantified values ​​of temperature in each temperature zone, the number of temperature levels, and the preset color system.

[0013] The information determination module is used to perform color mapping based on the quantified values ​​of temperature in each temperature region and the mapping relationship between temperature level and color system, generate candidate infrared images, and determine the annotation information of candidate infrared images based on a preset object recognition model.

[0014] The image generation module is used to process candidate infrared images and generate target infrared images based on the target display layer, the target object category, and annotation information.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the infrared image generation method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the infrared image generation method according to any embodiment of the present invention.

[0020] The technical solution of this invention determines the temperature regions within the detection area and the quantified values ​​of the temperature in each temperature region based on the raw thermal imaging signals collected by the infrared thermal imaging sensor. It then determines the mapping relationship between temperature levels and the color system based on the quantified values ​​of the temperature in each temperature region, the number of temperature levels, and a preset color system. Finally, it performs color mapping based on the quantified values ​​of the temperature in each temperature region and the mapping relationship between temperature levels and the color system to generate candidate infrared images. Based on a preset object recognition model, it determines the annotation information of the candidate infrared images. Finally, it processes the candidate infrared images according to the target display layer, the target object category, and the annotation information to generate the target infrared image. By processing the signals collected by the infrared thermal imaging sensor, usable information in the signals can be extracted more comprehensively, generating accurate and effective infrared images, assisting relevant personnel in making more accurate assessments and judgments of the fire scene environment.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of an infrared image generation method provided in Embodiment 1 of the present invention;

[0024] Figure 2 This is a flowchart of an infrared image generation method provided in Embodiment 2 of the present invention;

[0025] Figure 3 This is a structural block diagram of an infrared image generation device provided in Embodiment 3 of the present invention;

[0026] Figure 4 This is a schematic diagram of the structure of the electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," "target," "candidate," "alternative," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] It should be noted that as infrared thermal imaging sensors are widely used in fire rescue and post-disaster fire assessment, their imaging quality is related to the quality and density of the infrared-sensitive materials within the sensor and the average infrared thermal radiation of the imaging scene. In special circumstances such as fires, the following problems can easily occur: the image content of infrared thermal imaging is easily affected by large areas of flame and high-temperature smoke particles, resulting in a phenomenon similar to "overexposure" (specifically manifested as a red or white area in the scene). In this case, the image will lose some relatively low-temperature but still important key information (such as the location and condition of other burning objects), impacting rescue efforts.

[0030] In addition, materials with different combustion temperatures cannot be effectively distinguished from thermal images during combustion, and traditional methods of directly reducing the brightness and exposure of thermal images are prone to failing to identify information about low-temperature objects.

[0031] To address the problem that traditional thermal imaging cannot accurately capture the entire fire scene, this invention proposes an infrared thermal imaging sensor signal enhancement scheme for firefighting scenarios. This scheme processes the original thermal imaging signal to generate more accurate infrared images, increasing the amount of usable information in the imaging data and assisting firefighters in making more accurate assessments and judgments of the fire scene environment. The specific infrared image generation scheme will be described in detail in subsequent embodiments.

[0032] Example 1

[0033] Figure 1 This is a flowchart of an infrared image generation method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where thermal imaging signals acquired by an infrared thermal imaging sensor are enhanced to obtain more accurate and effective infrared images. This method can be executed by an infrared image generation device, which can be implemented in hardware and / or software and can be configured in an electronic device, such as an infrared thermal imaging sensor. Figure 1 As shown, the infrared image generation method includes:

[0034] S101. Based on the raw thermal imaging signal collected by the infrared thermal imaging sensor, determine the temperature range within the detection area and the quantified value of the temperature in each temperature range.

[0035] An infrared thermal imaging sensor is a pre-designed sensor that can collect thermal signals from the surrounding environment to generate a color thermal image (i.e., an infrared image). For example, an infrared thermal imaging sensor can be placed in a fire scene to collect signals from the fire scene. The raw thermal imaging signal is a digital signal converted from the collected infrared radiation levels by the infrared thermal imaging sensor. The detection area refers to the area within the detection range of the infrared thermal imaging sensor. A temperature region refers to a connected area of ​​the same temperature within the detection area. The detection area can include at least one temperature region, each corresponding to a specific temperature. For example, the detection area can contain two temperature regions, one with a quantized value of 50 degrees Celsius and the other with a quantized value of 100 degrees Celsius.

[0036] Optionally, an infrared thermal imaging sensor can be used to collect signals in the detection area of ​​a fire scene (fire site) to determine the original thermal imaging signal of the detection area. Then, based on preset rules, the intensity of infrared radiation in the original thermal imaging signal is analyzed to determine the temperature range within the detection area. According to the intensity of infrared radiation in different temperature ranges, it is quantified into corresponding numbers to determine the quantified value of the temperature of each temperature range.

[0037] S102. Determine the mapping relationship between temperature levels and color systems based on the quantified values ​​of temperature in each temperature zone, the number of temperature levels, and the preset color system.

[0038] The number of temperature levels refers to the total number of temperature levels the target classifies, which represents the number of temperature ranges the target divides into. The preset color system refers to a series of colors within the same color family, such as red and blue. Each color system contains at least two different shades of the same color family. The mapping relationship between temperature levels and color systems characterizes the correspondence between temperature levels and different colors within the color system.

[0039] Optionally, the mapping relationship between temperature levels and color systems is determined based on the quantified temperature values ​​of each temperature region, the number of temperature levels, and a preset color system. This includes: classifying temperature regions based on a preset clustering algorithm according to the distance relationships between temperature regions within the detection area, and determining distribution intervals based on the clustering results; determining the temperature range of the distribution interval based on the quantified temperature values ​​of the temperature regions contained within the distribution interval; determining the temperature range of each temperature level based on the temperature range of the distribution interval and the preset number of temperature levels; and determining the mapping relationship between temperature levels and color systems based on the preset color system, the temperature range of each temperature level, and the number of temperature levels.

[0040] Optionally, a clustering algorithm can be used to classify all the obtained temperature values ​​to obtain one or more main intervals of temperature value distribution, that is, to determine the distribution interval.

[0041] Optionally, after determining the distribution interval, the maximum and minimum values ​​of the quantified temperature values ​​of the temperature regions contained in the distribution interval can be used as the upper and lower boundary values ​​of the temperature range of the distribution interval, thereby determining the temperature range of the distribution interval.

[0042] Optionally, after determining the temperature range of the distribution interval, the temperature range of the distribution interval can be divided into sub-temperature ranges on an average basis according to the preset number of temperature levels, and each temperature level can be matched with each sub-temperature range to determine the temperature range of each temperature level.

[0043] Optionally, based on a preset color system, the temperature range of each temperature level, and the number of temperature levels, the mapping relationship between temperature levels and color systems is determined, including: determining the corresponding number of target colors from the preset color system based on the number of temperature levels, and matching the corresponding target colors for each temperature level; generating the mapping relationship between temperature levels and color systems based on the correspondence between each temperature level and the target colors, and the temperature range of each temperature level.

[0044] It should be noted that, based on the correspondence between each temperature level and the target color, as well as the temperature range of each temperature level, after determining the mapping relationship between temperature level and color system, each temperature level has its own unique temperature range and a corresponding unique color in the color system, namely the target color.

[0045] Optionally, after determining the distribution range, the method further includes: if there are at least two determined distribution ranges, then for each distribution range, determining the mapping relationship between temperature level and color system; if there is only one determined distribution range, then directly determining the mapping relationship between temperature level and color system.

[0046] It should be noted that if the number of distribution intervals is at least two, then the number of corresponding color systems is also at least two.

[0047] Optionally, if there are at least two determined distribution intervals, the above-described operation of determining the mapping relationship between temperature level and color system can be performed for each distribution interval to generate the mapping relationship. If there is only one determined distribution interval, the mapping relationship between temperature level and color system can be determined directly for that distribution interval.

[0048] S103. Based on the quantified values ​​of temperature in each temperature region and the mapping relationship between temperature level and color system, perform color mapping to generate candidate infrared images, and determine the annotation information of candidate infrared images based on the preset object recognition model.

[0049] Here, candidate infrared images refer to infrared images generated by color mapping of the original infrared image corresponding to the original thermal imaging signal. Object recognition models are pre-trained models capable of detecting and recognizing different objects within an image.

[0050] Optionally, for each temperature region, the temperature level to which its quantized value belongs can be determined, and the target color corresponding to that temperature level can be determined based on the mapping relationship between the temperature level and the color system. The color of that temperature region can be mapped to the corresponding target color, and the original infrared image after color mapping of all temperature regions can be determined as the generated candidate infrared image.

[0051] Optionally, based on a pre-set object recognition model, the annotation information of the candidate infrared images is determined, including: using a pre-trained object recognition model to perform object recognition processing on the candidate infrared images, and annotating them according to the recognition results to determine the annotation information of the candidate infrared images. The object recognition model can be, for example, the YOLO (You Only LookOnce) object detection model. The annotation information can be annotation information representing the number, location, and category of targets contained in the candidate infrared images.

[0052] Optionally, after generating the candidate infrared image, the method further includes: determining the region in the candidate infrared image that belongs to the preset dark range under the color system as the high-temperature layer of the candidate infrared image; and determining the region in the candidate infrared image that belongs to the preset light range under the color system as the low-temperature layer of the candidate infrared image.

[0053] S104. Based on the target display layer, the target display object category, and the annotation information, process the candidate infrared images to generate the target infrared image.

[0054] The target display layer refers to the layer in the candidate infrared image that needs to be displayed, as specified by relevant personnel. The target display object category refers to the category of target objects that need to be displayed in the candidate infrared image, as specified by relevant personnel.

[0055] Optionally, the target display layer can be a low-temperature layer and / or a high-temperature layer; the target display object category can be flame, corridor, or door / window.

[0056] Optionally, the annotation information of candidate infrared images can be filtered according to the category of the target displayed object. The annotation information of the target displayed object and the target display layer are displayed on the candidate infrared image, while the information of other objects and other display layers are hidden. The processed candidate infrared image is then determined as the target infrared image.

[0057] Optionally, after determining the target infrared image, it can also be visualized, that is, the processed infrared image and annotation information can be displayed. This facilitates relevant personnel to quickly analyze the on-site environment.

[0058] The technical solution of this invention determines the temperature regions within the detection area and the quantified values ​​of the temperature in each temperature region based on the raw thermal imaging signals collected by the infrared thermal imaging sensor. It then determines the mapping relationship between temperature levels and the color system based on the quantified values ​​of the temperature in each temperature region, the number of temperature levels, and a preset color system. Finally, it performs color mapping based on the quantified values ​​of the temperature in each temperature region and the mapping relationship between temperature levels and the color system to generate candidate infrared images. Based on a preset object recognition model, it determines the annotation information of the candidate infrared images. Finally, it processes the candidate infrared images according to the target display layer, the target object category, and the annotation information to generate the target infrared image. By processing the signals collected by the infrared thermal imaging sensor, usable information in the signals can be extracted more comprehensively, generating accurate and effective infrared images, assisting relevant personnel in making more accurate assessments and judgments of the fire scene environment.

[0059] Example 2

[0060] Figure 2 This is a flowchart of an infrared image generation method provided in Embodiment 2 of the present invention; based on the above embodiments, this embodiment proposes a preferred example of processing raw thermal imaging signal data to generate a marked and optimized color thermal image (i.e., a target infrared image). Figure 2 The method includes the following steps:

[0061] Acquiring raw thermal imaging signal data: The raw signal is a digital signal converted from the collected infrared radiation levels, which is a quantification of the temperature levels in different ranges of the target area.

[0062] Obtain the main distribution range of temperature values: Through clustering algorithms, all obtained temperature values ​​are classified to obtain one or more main distribution ranges of temperature values.

[0063] Temperature range assessment: The number of main temperature ranges is used to determine the appropriate adjustment algorithm.

[0064] If there is only one main temperature range, the color mapping is updated based on the temperature range (the difference between the highest and lowest temperatures) and the required number of temperature levels to be displayed, corresponding to the temperature range of each temperature level (the specific formula is as follows). For example, if the main temperature range is 20 degrees to 220 degrees, and 100 temperature levels need to be displayed, then each temperature level corresponds to 2 degrees. 20 degrees to 22 degrees is the first level, 22 degrees to 24 degrees is the second level, and so on.

[0065] For example, if T_max = maximum temperature, T_min = minimum temperature, L = number of temperature levels to be displayed, t_max = maximum temperature corresponding to each temperature level, t_min = maximum temperature corresponding to each temperature level, and t_del = temperature range corresponding to each temperature level, then the following conditions are met:

[0066] t_max = T_max / L

[0067] t_min=T_min / L

[0068] t_del=(T_max-T_min) / L

[0069] If there are multiple main temperature ranges, update the color mapping logic for each range using the same method, based on the temperature difference range within each main range. For example, if there are two main temperature ranges, 20°C to 220°C and 500°C to 800°C, 100 temperature levels and 30 temperature levels need to be displayed respectively. For the first temperature range, each temperature level corresponds to 2 degrees. 20°C to 22°C is level one, 22°C to 24°C is level two, and so on. For the second temperature range, each temperature level corresponds to 10 degrees. 500°C to 510°C is level one, 510°C to 520°C is level two, and so on.

[0070] Color mapping is implemented based on temperature values: A color is assigned to each temperature level under each color mapping logic to represent the same temperature range. For example, if the two main temperature ranges are 20°C to 220°C and 500°C to 800°C, 100 temperature levels and 30 temperature levels need to be displayed respectively. For the first temperature range, a color system A is assigned, with each temperature level representing 2 degrees. 20°C to 22°C is the first level, mapped to color A1; 22°C to 24°C is the second level, mapped to color A2, and so on. For the second temperature range, a color system B is assigned, with each temperature level representing 3 degrees. 500°C to 510°C is the first level, mapped to color B1; 510°C to 520°C is the second level, mapped to color B2, and so on.

[0071] Generate color heatmaps: Color heatmaps are generated using layers. A layer is created for each color system, i.e., each temperature distribution range. Users can show or hide different layers based on their ROI (Range of Interest), i.e., the temperature distribution they are interested in. For example, in a firefighting scenario, firefighters need to obtain critical information that is relatively low-temperature but still important. In this case, they can choose to hide the high-temperature display layer, which filters out large areas of high-temperature flames and smoke particles from the image, reducing the impact on rescue operations.

[0072] Object recognition and annotation based on color heatmaps are performed using a pre-trained object recognition model: YOLO and other recognition models are used to perform targeted recognition on each layer. Bounding and category labeling are then performed. Different recognition objects are pre-defined for different temperature layers, greatly enhancing recognition efficiency and accuracy (e.g., in high-temperature layers, only open flames are recognized, increasing efficiency while avoiding the possibility of misidentifying flames of different shapes as objects with mismatched temperatures, thus significantly improving accuracy).

[0073] Based on requirements, temperature layers and object recognition and labeling categories can be overlaid: With the support of multi-layer solutions, the layers to be displayed and the labeled objects to be displayed can be arbitrarily combined. For example, by displaying a low-temperature layer overlaid with high-temperature and low-temperature object recognition, not only can large areas of high-temperature flames and smoke be avoided from interfering with the image, and the state of people and building structures can be seen more clearly, but the specific location of important objects such as flames and high-temperature smoke that interfere with the view can also be known through the labeled objects.

[0074] Finally, output a color thermal image with markings and optimized imaging.

[0075] Example 3

[0076] Figure 3 This is a structural block diagram of an infrared image generation device provided in Embodiment 3 of the present invention. The infrared image generation device provided in this embodiment is applicable to situations where thermal imaging signals acquired by infrared thermal imaging sensors are enhanced to obtain more accurate and effective infrared images. This infrared image generation device can be implemented in hardware and / or software and configured in a device with infrared image generation functionality, such as… Figure 3 As shown, the device specifically includes:

[0077] The numerical determination module 301 is used to determine the temperature range within the detection area and the quantized value of the temperature of each temperature range based on the original thermal imaging signal collected by the infrared thermal imaging sensor.

[0078] The relationship determination module 302 is used to determine the mapping relationship between temperature levels and color systems based on the quantified values ​​of temperature in each temperature zone, the number of temperature levels, and the preset color system.

[0079] The information determination module 303 is used to perform color mapping based on the quantified values ​​of temperature in each temperature region and the mapping relationship between temperature level and color system, generate candidate infrared images, and determine the annotation information of candidate infrared images based on a preset object recognition model.

[0080] The image generation module 304 is used to process candidate infrared images and generate target infrared images based on the target display layer, the target display object category and annotation information.

[0081] The technical solution of this invention determines the temperature regions within the detection area and the quantified values ​​of the temperature in each temperature region based on the raw thermal imaging signals collected by the infrared thermal imaging sensor. It then determines the mapping relationship between temperature levels and the color system based on the quantified values ​​of the temperature in each temperature region, the number of temperature levels, and a preset color system. Finally, it performs color mapping based on the quantified values ​​of the temperature in each temperature region and the mapping relationship between temperature levels and the color system to generate candidate infrared images. Based on a preset object recognition model, it determines the annotation information of the candidate infrared images. Finally, it processes the candidate infrared images according to the target display layer, the target object category, and the annotation information to generate the target infrared image. By processing the signals collected by the infrared thermal imaging sensor, usable information in the signals can be extracted more comprehensively, generating accurate and effective infrared images, assisting relevant personnel in making more accurate assessments and judgments of the fire scene environment.

[0082] Furthermore, the relationship determination module 302 may include:

[0083] The interval determination unit is used to classify temperature regions based on a preset clustering algorithm and the distance relationship between each temperature region within the detection area, and to determine the distribution interval based on the clustering results.

[0084] The first range determination unit is used to determine the temperature range of the distribution interval based on the quantified values ​​of the temperature of the temperature regions included in the distribution interval.

[0085] The second range determination unit is used to determine the temperature range of each temperature level based on the temperature range of the distribution interval and the number of preset temperature levels.

[0086] The relationship determination unit is used to determine the mapping relationship between temperature levels and color systems based on a preset color system, the temperature range of each temperature level, and the number of temperature levels.

[0087] Furthermore, the relation determination unit is specifically used for:

[0088] Based on the number of temperature levels, a corresponding number of target colors are determined from the preset color system, and the corresponding target colors are matched for each temperature level;

[0089] Based on the correspondence between each temperature level and the target color, as well as the temperature range of each temperature level, a mapping relationship between temperature levels and color systems is generated.

[0090] Furthermore, the relationship determination module 302 is also used for:

[0091] If the number of determined distribution intervals is at least two, then for each distribution interval, determine the mapping relationship between temperature level and color system;

[0092] If the number of determined distribution intervals is one, then the mapping relationship between temperature level and color system can be directly determined.

[0093] Furthermore, the above-mentioned device is also used for:

[0094] The regions in the candidate infrared image that belong to the preset dark range under the color system are identified as the high-temperature layer of the candidate infrared image;

[0095] The low-temperature layer of the candidate infrared image is determined based on the area in the candidate infrared image that belongs to the preset light color range under the color system.

[0096] Furthermore, the information determination module 303 is specifically used for:

[0097] A pre-trained object recognition model is used to perform object recognition processing on the candidate infrared images, and the recognition results are used to label the candidate infrared images to determine the labeling information; the object recognition model is the YOLO target detection model.

[0098] Furthermore, the target display layer is a low-temperature layer and / or a high-temperature layer; the target display object category is flame, corridor, or door / window.

[0099] Example 4

[0100] Figure 4 This is a schematic diagram of the structure of the electronic device provided in Embodiment 4 of the present invention. Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0101] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0102] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0103] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as infrared image generation methods.

[0104] In some embodiments, the infrared image generation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the infrared image generation method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the infrared image generation method by any other suitable means (e.g., by means of firmware).

[0105] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0106] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0107] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0108] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0109] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0110] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0111] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and no limitation is imposed herein.

[0112] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for generating infrared images, characterized in that, include: Based on the raw thermal imaging signal acquired by the infrared thermal imaging sensor, the temperature regions within the detection area are determined, as well as the quantified values ​​of the temperature in each temperature region; wherein, the temperature region refers to the range of connected areas with the same temperature within the detection area. Based on the quantified values ​​of temperature in each temperature zone, the number of temperature levels, and the preset color system, determine the mapping relationship between temperature levels and color systems. Based on the quantified values ​​of temperature in each temperature region and the mapping relationship between temperature level and color system, color mapping is performed to generate candidate infrared images, and the annotation information of the candidate infrared images is determined based on the preset object recognition model. Based on the target display layer, the target display object category, and the annotation information, the candidate infrared images are processed to generate the target infrared image; Based on the quantified temperature values ​​of each temperature zone, the number of temperature levels, and the preset color system, the mapping relationship between temperature levels and the color system is determined, including: Based on a pre-defined clustering algorithm, the temperature regions are classified according to the distance relationship between each temperature region within the detection area, and the distribution range is determined based on the clustering results. The temperature range of the distribution interval is determined based on the quantified values ​​of the temperature regions contained within the distribution interval. The temperature range of each temperature level is determined based on the temperature range of the distribution area and the number of preset temperature levels. Based on the preset color system, the temperature range of each temperature level, and the number of temperature levels, determine the mapping relationship between temperature levels and color system; After generating candidate infrared images, the process also includes: The regions in the candidate infrared image that belong to the preset dark range under the color system are identified as the high-temperature layer of the candidate infrared image; The low-temperature layer of the candidate infrared image is determined based on the area in the candidate infrared image that belongs to the preset light color range under the color system.

2. The method according to claim 1, characterized in that, Based on the preset color system, the temperature range of each temperature level, and the number of temperature levels, determine the mapping relationship between temperature levels and the color system, including: Based on the number of temperature levels, a corresponding number of target colors are determined from the preset color system, and the corresponding target colors are matched for each temperature level; Based on the correspondence between each temperature level and the target color, as well as the temperature range of each temperature level, a mapping relationship between temperature levels and color systems is generated.

3. The method according to claim 1, characterized in that, After determining the distribution range, the process also includes: If the number of determined distribution intervals is at least two, then for each distribution interval, determine the mapping relationship between temperature level and color system; If the number of determined distribution intervals is one, then the mapping relationship between temperature level and color system can be directly determined.

4. The method according to claim 1, characterized in that, Based on a pre-defined object recognition model, the annotation information of candidate infrared images is determined, including: A pre-trained object recognition model is used to perform object recognition processing on the candidate infrared images, and the recognition results are used to label the candidate infrared images to determine the labeling information; the object recognition model is the YOLO target detection model.

5. The method according to claim 1, characterized in that, in, The target display layer is a low-temperature layer and / or a high-temperature layer; the target display object category is flame, corridor, or door / window.

6. An infrared image generating device, characterized in that, include: The numerical determination module is used to determine the temperature range within the detection area and the quantified temperature value of each temperature range based on the raw thermal imaging signal collected by the infrared thermal imaging sensor; wherein, the temperature range refers to the range of connected areas with the same temperature within the detection area. The relationship determination module is used to determine the mapping relationship between temperature levels and color systems based on the quantified values ​​of temperature in each temperature zone, the number of temperature levels, and the preset color system. The information determination module is used to perform color mapping based on the quantified values ​​of temperature in each temperature region and the mapping relationship between temperature level and color system, generate candidate infrared images, and determine the annotation information of candidate infrared images based on a preset object recognition model. The image generation module is used to process candidate infrared images and generate target infrared images based on the target display layer, the target display object category, and annotation information. The relationship determination module includes: The interval determination unit is used to classify temperature regions based on a preset clustering algorithm and the distance relationship between each temperature region within the detection area, and to determine the distribution interval based on the clustering results. The first range determination unit is used to determine the temperature range of the distribution interval based on the quantified values ​​of the temperature of the temperature regions included in the distribution interval. The second range determination unit is used to determine the temperature range of each temperature level based on the temperature range of the distribution interval and the number of preset temperature levels. The relationship determination unit is used to determine the mapping relationship between temperature levels and color systems based on the preset color system, the temperature range of each temperature level, and the number of temperature levels. The device is also used for: The regions in the candidate infrared image that belong to the preset dark range under the color system are identified as the high-temperature layer of the candidate infrared image; The low-temperature layer of the candidate infrared image is determined based on the area in the candidate infrared image that belongs to the preset light color range under the color system.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the infrared image generation method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the infrared image generation method according to any one of claims 1-5.

Images