Thermal imaging image processing method, device, equipment and medium

Abstract

A thermal imaging image processing method, device, equipment and medium are disclosed. The method comprises: acquiring a thermal imaging image collected by a thermal imaging device, and dividing the thermal imaging image into at least two regions; determining a user interest parameter and / or a temperature sensitivity parameter of each region according to the thermal imaging image; determining a grid division parameter of each region according to the user interest parameter and / or the temperature sensitivity parameter; respectively performing grid division on each region according to the grid division parameter of each region; and storing at least one temperature data in each grid in the thermal imaging image. Through the grid storage of the temperature data in the thermal imaging image and the dynamic adjustment mechanism of the grid division precision, the storage amount of redundant temperature data is reduced, and the grid division precision determination strategy of each region is different, which realizes the reduction of storage requirements while ensuring the sampling precision of the stored temperature data.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a method, apparatus, device, and medium for processing thermal imaging images. Background Technology

[0002] With the continuous development of thermal imaging technology, thermal imaging cameras are widely used in fields such as surveillance, security, medical care, and industry. Thermal imaging cameras can capture the temperature information of an object's surface in real time and convert it into image data, providing high-precision temperature analysis.

[0003] However, since thermal imaging cameras need to collect temperature data pixel by pixel across the entire image, storing a large amount of temperature data poses a significant challenge to hard drive storage space, especially when long-term storage or storage of high-resolution thermal imaging images is required.

[0004] The traditional method is to store the temperature value pixel by pixel of the entire image. Although this ensures the accuracy of the data, it results in a huge amount of data storage, high storage costs, and increased computational load for retrieval, leading to slow retrieval speed and low processing efficiency. Summary of the Invention

[0005] This invention provides a method, apparatus, device, and medium for processing thermal imaging images, in order to solve the problem of large data volume in thermal imaging images while ensuring the accuracy of temperature data stored in the thermal imaging images.

[0006] According to one aspect of the present invention, a method for processing thermal imaging images is provided, comprising:

[0007] Acquire thermal imaging images captured by a thermal imaging device, and divide the thermal imaging images into at least two regions;

[0008] Based on the thermal imaging images, determine the user interest parameters and / or temperature sensitivity parameters for each of the regions;

[0009] The grid division parameters for each region are determined based on the user's interest parameters and / or temperature sensitivity parameters.

[0010] Each region is divided into grids according to the grid division parameters of each region, and at least one temperature data in each grid of the thermal imaging image is stored.

[0011] According to another aspect of the present invention, a thermal imaging image processing apparatus is provided, comprising:

[0012] The region division module is used to acquire thermal imaging images collected by thermal imaging devices and divide the thermal imaging images into at least two regions.

[0013] The region parameter determination module is used to determine the user interest parameters and / or temperature sensitivity parameters of each region based on the thermal imaging image.

[0014] The grid division parameter determination module is used to determine the grid division parameters for each region based on the user's interest parameters and / or temperature sensitivity parameters.

[0015] The grid temperature data storage module is used to divide each region into grids according to the grid division parameters of each region, and to store at least one temperature data in each grid of the thermal imaging image.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] 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 thermal imaging image processing method according to any embodiment of the present invention.

[0020] 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 thermal imaging image processing method according to any embodiment of the present invention.

[0021] The technical solution of this invention reduces the amount of redundant temperature data to be stored by gridding temperature data in thermal imaging images and dynamically adjusting the grid division accuracy, thereby improving the storage efficiency of temperature data. Furthermore, the different degrees of grid division accuracy in each region are determined based on the user's interest parameters and / or temperature sensitivity parameters in each region, balancing the requirements for storage accuracy and storage efficiency, and reducing storage requirements while ensuring the sampling accuracy of stored temperature data.

[0022] 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

[0023] 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.

[0024] Figure 1 This is a flowchart of a thermal imaging image processing method according to an embodiment of the present invention;

[0025] Figure 2 This is a flowchart of another thermal imaging image processing method provided by an embodiment of the present invention.

[0026] Figure 3 This is a flowchart of another thermal imaging image processing method provided by an embodiment of the present invention.

[0027] Figure 4 This is a flowchart of another thermal imaging image processing method provided by an embodiment of the present invention.

[0028] Figure 5 This is a flowchart of another thermal imaging image processing method provided by an embodiment of the present invention.

[0029] Figure 6 This is a schematic diagram of the structure of a thermal imaging image processing device according to an embodiment of the present invention;

[0030] Figure 7 This is a schematic diagram of the structure of an electronic device that implements the thermal imaging image processing method of the present invention. Detailed Implementation

[0031] 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.

[0032] It should be noted that the terms "candidate," "target," 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.

[0033] Figure 1 This invention provides a flowchart of a method for processing thermal imaging images, applicable to situations where temperature data from thermal imaging images is stored. The method can be executed by a thermal imaging image processing device, which can be implemented in hardware and / or software and can be configured in a server with computing capabilities. Figure 1 As shown, the method includes:

[0034] S110. Acquire the thermal imaging image collected by the thermal imaging device and divide the thermal imaging image into at least two regions.

[0035] Thermal imaging equipment is a device that can capture the surface temperature information of an object and convert it into image data, such as a thermal imaging camera. The value of each pixel in a thermal imaging image is the temperature data of the object corresponding to that pixel.

[0036] The thermal imaging image is divided into regions, with the entire image frame divided into at least two regions. Specifically, the number of regions is determined according to storage accuracy requirements. When the thermal imaging device initially acquires the thermal imaging image, it is divided evenly according to the number of regions to obtain the corresponding number of regions. After the user operates on multiple historical thermal imaging images acquired by the thermal imaging device, the region division results are updated based on the user's operation data on the historical thermal imaging images. For example, based on the statistical results of the user's operation data on historical thermal imaging images, frequently clicked areas in the thermal imaging image are determined, i.e., areas with a click frequency greater than a preset threshold. These frequently clicked areas are selected as one of the regions. The other regions in the thermal imaging image are divided evenly according to the remaining region division number. The remaining regions are the areas in the thermal imaging image excluding the frequently clicked areas. The number of remaining regions is the difference between the predetermined number of region divisions and the number of frequently clicked areas.

[0037] S120. Determine the user-interest parameters and / or temperature sensitivity parameters for each region based on the thermal imaging image.

[0038] The user interest parameter represents the degree of user attention to temperature information in each region. A higher user interest parameter indicates greater user interest in the temperature data of the pixels within that region, or in other words, a greater degree of user interest in the temperature information of the corresponding object. The user interest parameter can be determined based on the user's historical attention behavior or a pre-set user attention level. The temperature sensitivity parameter represents the degree of temperature variation among pixels in each region. A higher temperature sensitivity parameter indicates greater temperature variation among pixels in that region.

[0039] Specifically, the process involves acquiring user interaction data with the thermal imaging image. Users obtain temperature data for target points and / or target regions on the thermal imaging image through these interactions. For example, clicking on a target pixel yields its temperature data, or selecting a target region yields its average temperature. Based on this interaction data, a region of interest (ROI) is determined. Then, a user interest parameter is determined for this ROI based on the overlap between the ROI and other regions. For instance, the overlap area between the target region and the ROI is determined, and the ratio of this overlap area to the total area of ​​the target region is considered the user interest parameter for that region.

[0040] The temperature data of all pixels in the target region of the thermal imaging image is acquired. Based on the temperature data of all pixels, the temperature change rate of the target region is determined and used as a temperature sensitivity parameter for the target region. For example, the standard deviation of the temperature data in the target region is determined based on the temperature data of each pixel, representing the temperature fluctuation range within the target region. This standard deviation is used as the temperature sensitivity parameter for the target region. For instance, the temperature sensitivity parameter TS of the target region r... r The calculation formula is: TS r =σ(T) r ),in: Let t be the temperature value of all pixels within the target region r. r,i σ(T) represents the temperature value of the i-th pixel in the target region r. r ) represents the standard deviation of temperature data in the target region r, indicating the magnitude of temperature fluctuation within that region. The specific formula is: Where, μ r Let N be the average temperature of all pixels within the target region r. r This represents the total number of pixels within the target region r.

[0041] S130. Determine the meshing parameters for each region based on the user's parameters of interest and / or temperature sensitivity parameters.

[0042] The mesh generation parameter represents the granularity of the data partitioning for each region. This parameter can be either the number of meshes or the mesh size. For example, the mesh generation parameter represents the total number of meshes in each region, and also the amount of temperature data stored in each region. A larger mesh generation parameter indicates more and finer temperature data storage for that region, while a smaller parameter indicates less and coarser temperature data storage. The mesh generation parameter can also represent the mesh size, i.e., the size of the meshes within each region. A smaller parameter indicates more and finer temperature data storage for that region. The specific correspondence can be determined by the actual content represented by the mesh generation parameter.

[0043] Specifically, since the user interest parameter of a region represents the user's attention to that region, the higher the user's attention, the greater the storage precision requirement for that region, and the larger the corresponding grid division parameter. Since the temperature data of the thermal imaging image is stored for subsequent retrieval and viewing by users, if the user interest parameter of the first region in the thermal imaging image is greater than that of the second region, it means that when users view the thermal imaging image, the probability of viewing the first region is greater than that of viewing the second region. Therefore, the first region is stored with more refined data, that is, the grid division parameter of the first region is greater than that of the second region.

[0044] Similarly, because the temperature distribution in thermal imaging images is dynamic, the temperature change characteristics of different regions can vary greatly. In thermal imaging, there are often some critical components, such as electrical equipment contacts and moving parts of machinery. These parts experience significant temperature variations and are prone to generating hotspots. Areas with large temperature gradients in these areas are identified as hotspot regions. Hotspot regions are highly sensitive to temperature distribution and therefore require a larger grid to meticulously record temperature changes within them. Conversely, areas such as equipment casings and background regions exhibit smaller temperature variations; these are stable regions. Stable regions are less sensitive to temperature distribution and can use larger grids to store temperature data, reducing data storage and computational burden.

[0045] For example, a mapping relationship can be determined between user-interested parameters and mesh generation parameters. In this mapping relationship, the user-interested parameters are directly proportional to the mesh generation parameters; that is, the larger the user-interested parameters for a target area, the larger the mesh generation parameters for that target area. The specific expression of the mapping relationship can be determined based on actual circumstances and is not limited here. Alternatively, a mapping relationship can be determined between temperature sensitivity parameters and mesh generation parameters. In this mapping relationship, the temperature sensitivity parameters are directly proportional to the mesh generation parameters; that is, the larger the temperature sensitivity parameters for a target area, the larger the mesh generation parameters for that target area. The specific expression of the mapping relationship can be determined based on actual circumstances and is not limited here. Alternatively, a comprehensive influence parameter can be determined for each area based on the user-interested parameters and temperature sensitivity parameters, and a mapping relationship can be determined between the comprehensive influence parameter and the mesh generation parameters. In this mapping relationship, the comprehensive influence parameter is directly proportional to the mesh generation parameters; that is, the larger the comprehensive influence parameter for a target area, the larger the mesh generation parameters for that target area. The specific expression of the mapping relationship can be determined based on actual circumstances and is not limited here. The value of the comprehensive influence parameter can be determined based on the weighted value of the user-interested parameters and temperature sensitivity parameters. The weights of the user-interested parameters and temperature sensitivity parameters can be adjusted based on actual circumstances and are not limited here.

[0046] S140. Divide each region into grids according to the grid division parameters of each region, and store at least one temperature data in each grid of the thermal imaging image.

[0047] Specifically, the thermal imaging image is divided into grids according to the grid division parameters for each region, resulting in at least one grid division result for each region. Based on the grid division results, at least one temperature data point within each grid is determined and stored. For example, after dividing each region into grids, one temperature data point within each grid is stored, such as the maximum or average temperature within that grid. Optionally, when storing at least one temperature data point in each grid, the region information of that grid is also stored, such as the region location and user-interested parameters and / or temperature sensitivity parameters, to facilitate subsequent image retrieval and viewing of the stored data.

[0048] Grid partitioning is an effective storage strategy that breaks down a screen into smaller regions, significantly reducing storage and processing complexity, while also providing flexible regionalized operations.

[0049] In one feasible embodiment, storing at least one temperature data point in each grid of the thermal imaging image includes:

[0050] The representative temperature data for each grid is determined based on the temperature data of each pixel within each grid; wherein the representative temperature data includes at least one of the following: grid average temperature, grid maximum temperature, and grid minimum temperature;

[0051] The representative temperature data of each grid in the thermal imaging image is stored.

[0052] After dividing the thermal imaging image into grids, representative temperature data for each grid is determined and stored. The representative temperature data includes the grid average temperature, grid maximum temperature, and grid minimum temperature. The grid average temperature is the average of the temperature data of all pixels within the grid; the grid maximum temperature is the maximum value among all pixels within the grid; and the grid minimum temperature is the minimum value among all pixels within the grid.

[0053] For example, there are N cells in grid r. r For each pixel, the representative temperature data of the grid consists of the average, highest, and lowest temperatures of all pixels within that grid. The grid's average temperature D is... r It can be calculated using the following formula: Among them, D r The average temperature of grid r is N. r T is the total number of pixels in grid r; r，i It is the temperature value of the i-th pixel within grid r.

[0054] The technical solution of this invention reduces the amount of redundant temperature data to be stored by gridding temperature data in thermal imaging images and dynamically adjusting the grid division accuracy, thereby improving the storage efficiency of temperature data. Furthermore, the different degrees of grid division accuracy in each region are determined based on the user's interest parameters and / or temperature sensitivity parameters in each region, balancing the requirements for storage accuracy and storage efficiency, and reducing storage requirements while ensuring the sampling accuracy of stored temperature data.

[0055] Figure 2 This is a flowchart of another thermal imaging image processing method provided by an embodiment of the present invention. This embodiment further explains the steps for determining the user's parameters of interest in the above embodiments. Figure 2 As shown, the method includes:

[0056] S210. Acquire the thermal imaging image collected by the thermal imaging device and divide the thermal imaging image into at least two regions.

[0057] S220: Obtain user operation data on historical thermal imaging images collected by the thermal imaging device.

[0058] Operational data refers to user behavior data regarding the acquisition of temperature data from thermal imaging images. For example, operational data includes at least the number of times a user clicks on each area in historical thermal imaging images and the duration of their viewing.

[0059] Specifically, the system acquires multiple historical thermal imaging images over a given period, along with the user's click locations, click counts, and viewing durations for these images. Since users need to click on a target pixel or select a target area to view its temperature data, historical click data can determine the user's level of attention to the temperature of objects in different areas of the image. Viewing duration is used to calculate the total time a user spends viewing the temperature of a target pixel or area.

[0060] For example, the number of times a user clicks or visits each area in a historical thermal imaging image is counted as the first operation data, and the total time a user stays on each area in a historical thermal imaging image is counted as the viewing time, which is used as the second operation data.

[0061] S230. Determine the user operation parameters for each area based on the operation data.

[0062] User operation parameters represent the degree of attention a user pays to each area in their historical operation behavior.

[0063] Specifically, the first or second operation data for each region is used as the user operation parameter for that region; alternatively, the user operation parameter for each region is determined based on the first and second operation data, combining the two factors of click-through rate and viewing duration. Since click-through rate and viewing duration have different impacts on user interest, weighting factors w1 and w2 are introduced to balance these two factors. The formula for calculating the user operation parameter is: IL r1 =w1·C r +w2·t r , where: C r It represents the number of times a user clicks on region r in a historical thermal imaging image; t r This refers to the duration a user views region r in a historical thermal image; w1 and w2 are weighting coefficients used to adjust the influence of click count and viewing duration on interest level. The specific values ​​of these weights can be adjusted according to user needs and accuracy requirements, and are not limited here.

[0064] S240. Perform target feature recognition on the thermal imaging image, and determine the target feature parameters of each region based on the target feature recognition results.

[0065] In the entire image captured by the thermal imaging device, users pay more attention to specific target objects. The type of target object is determined according to the deployment scenario of the thermal imaging device. For example, in the power scenario, the target object may be the contact point of the power equipment or the moving part of the machinery. These target objects have large temperature variations, which users pay more attention to. Therefore, the user's interest in the area with the target object is higher.

[0066] Specifically, the target object is determined based on the deployment scenario of the thermal imaging equipment and the user's focus, and then the target features of the target object are determined. Feature recognition is then performed on the thermal imaging image based on these target features to obtain the target feature recognition result. The target feature recognition result includes the target object's identification location information. Based on the target object's identification location information and its positional relationship with each region, the target feature parameters for each region are determined. For example, the target feature parameters for each region can be determined based on the number of target objects in each region, or based on the ratio of the area of ​​each target object in each region to the total area of ​​that region.

[0067] S250. Determine the user interest parameters for each region based on the user operation parameters and target feature parameters for each region.

[0068] Weighting factors w3 and w4 are introduced to balance the influence of user operation parameters and target feature parameters on the user interest parameters. The formula for calculating the user interest parameters is: IL r =w3·IL r1 +w4·IL r2 , where: IL r1 Indicates the user operation parameters for region r; IL r2 The target feature parameters of region r are represented by w3 and w4, which are weight coefficients used to adjust the influence weight of user operation parameters and target feature parameters. The specific values ​​of the weights can be adjusted according to user needs and accuracy requirements, and are not restricted here.

[0069] Optionally, the user interest value is determined based on the weighted value of the user operation parameters and target feature parameters of each region. The first target level that is successfully matched is determined based on the matching result of the user interest value and the pre-determined range of interest parameter levels. This first target level is then used as the user interest parameter.

[0070] For example, based on historical data, the range of values ​​of interest to users is determined, and this range is divided into N levels, with each level corresponding to a sub-range of values ​​of interest to users, such as IL. r ∈{IL1, IL2, ... IL N}, IL1 represents the lowest level of user-interested parameters, IL NThis represents the highest level of user interest in the parameters. The sub-value ranges corresponding to each level can be obtained by evenly distributing the total value range, or the sub-value ranges corresponding to each level can be adjusted according to user needs, such as choosing a linear or non-linear method to divide the levels.

[0071] S260. Determine the temperature sensitivity parameters of each region based on the thermal imaging images.

[0072] S270. Determine the meshing parameters for each region based on the user's parameters of interest and / or temperature sensitivity parameters.

[0073] S280. Divide each region into grids according to the grid division parameters of each region, and store at least one temperature data in each grid of the thermal imaging image.

[0074] The technical solution of this invention determines the user's interest parameters by using user operation parameters and target feature parameters of each region, thereby improving the accuracy of determining the user's interest parameters of each region and thus improving the accuracy of determining the grid division parameters.

[0075] Figure 3 This is a flowchart of another thermal imaging image processing method provided by an embodiment of the present invention. This embodiment further explains the steps for determining the temperature sensitivity parameters in the above embodiments. Figure 3 As shown, the method includes:

[0076] S310. Acquire the thermal imaging image collected by the thermal imaging device and divide the thermal imaging image into at least two regions.

[0077] S320. Determine the regional temperature fluctuation parameters and regional temperature limit parameters of each region based on the temperature data of each pixel in each region, and determine the time dimension temperature change parameters of each region by combining the historical temperature data of each pixel in each corresponding region in the historical thermal imaging images collected by the thermal imaging equipment. Use the regional temperature fluctuation parameters, regional temperature limit parameters and time dimension temperature change parameters as sensitivity influence parameters.

[0078] The temperature distribution in thermal imaging images is dynamic, and the temperature variation characteristics of different regions can vary greatly. Therefore, in the process of meshing each region, in addition to considering the basic numerical characteristics of thermal imaging data, multiple factors such as scene characteristics, temperature change rate, and spatial distribution patterns should be considered for dynamic adjustment and optimization. Thus, temperature sensitivity is an important indicator when meshing each region. High-sensitivity regions should use smaller meshes, while low-sensitivity regions can use larger meshes. Sensitivity can be determined by analyzing the temperature change rate to ensure sufficient storage accuracy in areas with drastic temperature changes (such as high-temperature areas or fault areas of equipment).

[0079] Sensitivity parameters for a region are used to characterize the temperature variation within that region. To measure the degree of temperature variation within a region, sensitivity parameters are represented by three aspects: regional temperature variance, magnitude variance, and temperature variation over time.

[0080] Specifically, the temperature values ​​of all pixels within region r. t r,i This represents the temperature value of the i-th pixel, and the average temperature of all pixels within the grid is: The temperature fluctuation parameter of region r is expressed as: Where, μ r N is the average temperature within region r. r This represents the total number of pixels within region r.

[0081] The temperature values ​​T of all pixels within the statistical region r r The minimum temperature value T in r,min and maximum temperature value T r,max The difference between the maximum and minimum temperature values ​​within the grid is used as the regional temperature limit parameter, which is expressed as: ΔT r =T r,max -T r,min .

[0082] The process involves acquiring historical thermal imaging images within a preset time period from a thermal imaging device, determining the temperature difference between each pixel in the target area of ​​the current thermal imaging image and the corresponding pixel in the target area of ​​the historical thermal imaging images, and using the maximum temperature difference between each pixel as a time-dimensional temperature change parameter. For example, three historical thermal imaging images are acquired, and the temperature value T of each pixel in the target area of ​​the current thermal imaging image is determined. r (t), and the temperature value T of the corresponding pixel in each historical thermal image. r (t-1), T r (t-2) and T r (t-3), the time dimension temperature change value of this pixel is determined as max{|T r (t)-T r (t-1)|,|T r (t)-T r (t-2)|,|T r (t)-T r (t-3)|} determines the time dimension temperature change value of each pixel in the target area, and takes the largest time dimension temperature change value as the time dimension temperature change parameter of the target area.

[0083] S330. Determine the temperature sensitivity parameter based on at least one sensitivity influence parameter for each region.

[0084] Specifically, the temperature sensitivity parameter can be determined by using one other sensitive influencing parameter for each region, or by weighting any two sensitive influencing parameters for each region, or by weighting the regional temperature fluctuation parameter, regional temperature limit parameter, and time-dimensional temperature change parameter for each region. The weights of each sensitive influencing parameter can be determined based on the actual scenario's accuracy requirements and the user's personalized needs. The number of sensitive influencing parameters involved in determining the temperature sensitivity parameter can also be determined based on the actual scenario's accuracy requirements and the user's personalized needs. There are no restrictions on the specific weight values ​​or the number of sensitive influencing parameters involved.

[0085] Optionally, a temperature sensitivity value is determined based on the weighted value of at least one sensitivity influence parameter for each region, and a second target level that is successfully matched is determined based on the matching result of the temperature sensitivity value and the pre-determined temperature sensitivity parameter level division range, and the second target level is used as the temperature sensitivity parameter.

[0086] For example, the range of values ​​for a temperature sensitivity parameter is determined based on historical data, and this range is divided into N levels, with each level corresponding to a sub-range of values ​​for a temperature sensitivity parameter, such as TS. r ∈{TS1, TS2, ... TS N}, TS1 represents the lowest level of temperature sensitivity parameter, TS N This represents the highest level of temperature sensitivity parameter. The sub-value range corresponding to each level can be obtained by averaging the total value range, or the sub-value range corresponding to each level can be adjusted according to user needs, such as choosing a linear or non-linear method to divide the levels.

[0087] S340. Determine the user's interest parameters for each region based on the thermal imaging image.

[0088] S350. Determine the meshing parameters for each region based on the user's parameters of interest and / or temperature sensitivity parameters.

[0089] S360. Divide each region into grids according to the grid division parameters of each region, and store at least one temperature data in each grid of the thermal imaging image.

[0090] The technical solution of this invention determines the temperature sensitivity parameters by using the sensitivity influence parameters of each region, thereby improving the accuracy of determining the temperature sensitivity parameters of the region and thus improving the accuracy of determining the grid division parameters.

[0091] Figure 4This is a flowchart of another thermal imaging image processing method provided by an embodiment of the present invention. This embodiment further explains the determination of grid division parameters in the above embodiments. Figure 4 As shown, the method includes:

[0092] S410. Acquire the thermal imaging image collected by the thermal imaging device and divide the thermal imaging image into at least two regions.

[0093] S420. Determine the user-interest parameters and / or temperature sensitivity parameters for each region based on the thermal imaging image.

[0094] S430: Determine the storage priority of each region based on user-interested parameters and / or temperature sensitivity parameters.

[0095] Storage priority is used to represent the storage precision of each region. Regions with higher storage priority have higher storage precision, and vice versa.

[0096] Specifically, the storage priority of each region can be determined by using the user's interest parameters for that region, or by using the temperature sensitivity parameters for that region, or by determining the storage priority of a region based on the weighted value of the user's interest parameters and the temperature sensitivity parameters for that region.

[0097] For example, the formula for calculating the storage priority of region r is: PL r =α·IL r +β·TS r Where α and β are weighting factors, representing the importance of user-interested parameters and temperature sensitivity parameters in priority calculation, which can be determined based on scenario requirements and user-specific settings; IL r and TS r These are the user-interested parameters and temperature-sensitive parameters for region r, respectively.

[0098] S440. Determine the grid partitioning parameters for each region based on the pre-determined mapping relationship between storage priority and grid partitioning parameters and the storage priority of each region.

[0099] The mapping relationship between storage priority and grid partitioning parameters is used to represent the correspondence between storage priority and grid partitioning parameters. This correspondence can be determined by a mapping table or by a relational expression.

[0100] There is a direct correlation between meshing parameters and storage priority. Higher storage priority corresponds to larger meshing parameters, resulting in higher meshing precision, and vice versa. For example, the meshing parameter GS... r Based on storage priority PLr The grid division levels correspond to the grid division levels. For example, the grid division parameters of the entire image can be divided into N levels, from the smallest grid (high precision) to the largest grid (low precision), as shown below: GS r ∈{GS1, GS2, ... GS N}, where: GS1 represents the minimum meshing parameter; GS N This represents the maximum mesh generation parameter. Based on this, the priority PL is stored. r It is also divided into N levels, representing different regions from low priority to high priority. Specifically, the region priority is divided into the following levels: PL r ∈{PL1, PL2, ... PL N}, where: PL1 represents the lowest priority, PL N This indicates the highest priority. It is recommended that each storage priority level correspond to a mapping relationship of one grid partitioning parameter level. After determining the target storage priority of the target area, the corresponding target storage priority level is determined based on this target storage priority. Then, the target grid partitioning parameters corresponding to the target storage priority level are determined based on this mapping relationship, which are the target grid partitioning parameters for the target area.

[0101] By performing gridded sampling of temperature data in different regions of a thermal imaging image, each region is divided into multiple grids, and at least one temperature data point representing that grid is stored in each grid. Each region is then allocated its storage priority according to PL. r and mesh generation parameters GS r The grid is divided based on the mapping relationship between data points. Lower storage priority areas are divided using larger grids, resulting in lower storage precision and therefore smaller amounts of temperature data stored in these areas, thus reducing storage space. Conversely, higher storage priority areas are divided using smaller grids, resulting in higher storage precision and ensuring data accuracy. This approach balances data precision and storage efficiency, avoiding unnecessary storage redundancy.

[0102] Optionally, during storage, the amount of stored data can be further optimized using compression algorithms. For example, each region can be divided into high-priority and low-priority storage regions based on storage priority. The temperature data of each grid in the low-priority storage region can be stored using lossy compression or low-precision storage to further save storage space.

[0103] In one feasible embodiment, the mapping relationship between storage priority and grid partitioning parameters includes a level partitioning mapping relationship, a linear mapping relationship, and a non-linear mapping relationship;

[0104] The level division mapping relationship is determined as follows: the storage priority is divided into a first number of priority levels according to the value range of the storage priority, and into a first number of grid levels according to the value range of the grid division parameters. The one-to-one mapping relationship between each priority level and each grid level is determined as the level division mapping relationship.

[0105] The expression for the linear mapping relationship is as follows: The expression for the nonlinear mapping relationship is shown below:

[0106] Among them, GS r PL represents the meshing parameters for region r. r Indicates the storage priority of region r, GS min GS represents the smallest meshing parameter within the range of possible meshing parameters. max PL represents the maximum meshing parameter within the range of possible meshing parameters. min PL represents the lowest storage priority within the range of possible storage priority values. max γ represents the maximum storage priority within the range of storage priority values; γ represents the non-linear adjustment factor.

[0107] Specifically, a precise correlation is established between storage priority and grid partitioning parameters. Upon acquiring a new thermal imaging image, the storage priority of the new image is updated, and updated grid partitioning parameters are determined based on this updated priority. The new thermal imaging image is then partitioned based on these updated parameters to improve the storage accuracy of temperature data within the image. The grid size level in each region is dynamically adjusted according to the region's storage priority, resulting in finer grid partitioning to accommodate varying storage accuracy requirements.

[0108] Storage priority PL of region r r and mesh generation parameters GS r Mapping and association can be performed in three ways. When determining the grid division parameters for thermal imaging images, the target mapping relationship can be determined from these three mapping relationships based on scene storage requirements and user needs. When the region's priority is PL... r When changes occur, adjust the mesh generation parameters GS in real time. r This is to ensure optimal storage accuracy for thermal imaging images.

[0109] Specifically, based on the above-mentioned hierarchical classification results of storage priority and grid partitioning parameters, the expression for the hierarchical mapping relationship is as follows:

[0110]

[0111] If storage priority PL r The partitioning is continuous and linear, and the changes in the mesh partitioning parameters can also be represented by a linear mapping relationship. Assume the storage priority PL... r The value range is [PL] min ,PL max Mesh generation parameters GS r The value range is [GS] min GS max The relationship between storage priority and grid partitioning parameters can then be represented by a linear mapping expression, where GS min and GS max These are the minimum and maximum meshing parameters, respectively; PL min and PL max These are the values ​​for the lowest and highest storage priorities, respectively. The grid size is adjusted linearly according to the storage priority; the higher the priority, the smaller the grid and the higher the precision. Here, the grid division parameter represents the grid size, so a smaller grid division parameter indicates finer division precision. If the grid division parameter represents the number of grid divisions, then a larger grid division parameter indicates finer division precision, and it should be adjusted according to the actual situation.

[0112] If the allocation of storage priorities is complex, or if a more flexible adjustment of the relationship between storage priorities and grid partitioning parameters is required in certain application scenarios, a non-linear mapping relationship can be used to associate storage priorities and grid partitioning parameters. For example, logarithmic or exponential mappings can be used to adjust the precision of grid partitioning. Through non-linear mapping, the grid in higher priority areas can be reduced more finely, while the grid in lower priority areas changes more gradually, further improving the precision of grid partitioning and temperature data storage.

[0113] By establishing three mapping relationships between storage priority and meshing parameters, the accuracy of meshing parameter determination is improved, thereby enhancing the efficiency and precision of data storage based on meshing results.

[0114] When the storage priority of region r changes (e.g., increased user attention to a region or increased temperature fluctuations), the mesh partitioning parameters are dynamically adjusted. This is achieved by monitoring changes in the storage priority of each region in real time and updating the mesh partitioning parameters accordingly. For example, if the priority of a region increases from PL2 to PL3, the mesh partitioning parameters for that region will change from GS... r3 Adjusted to GS2.

[0115] The update formula for dynamic optimization is: GS r (t+1)=f(PL r (t+1)); where PL r(t+1) represents the updated storage priority, GS r (t+1) represents the updated mesh generation parameters, f(PL) r This indicates the mapping relationship between storage priority and grid partitioning parameters.

[0116] By controlling the mapping relationship between storage priority and grid partitioning parameters, the data storage precision can be flexibly adjusted according to actual needs. For example, in scenarios requiring higher data precision, areas with high storage priority will be allocated smaller grids for storage, while other areas will use larger grids to save storage space. This dynamic adjustment mechanism ensures the system's efficiency and flexibility.

[0117] S450. Divide each region into grids according to the grid division parameters of each region, and store at least one temperature data in each grid of the thermal imaging image.

[0118] The technical solution of this invention improves the accuracy of grid partitioning parameters by determining the mapping relationship between storage priority and grid partitioning parameters, and then determining the grid partitioning parameters according to the storage priority of each region. This, in turn, improves the accuracy and storage efficiency of storing the entire image temperature data based on the grid partitioning results.

[0119] Figure 5 This is a flowchart of another thermal imaging image processing method provided by an embodiment of the present invention. This embodiment further describes the retrieval step after storing the thermal imaging image in the above embodiment. Figure 5 As shown, the method includes:

[0120] S510. Determine the display priority of each region in the stored thermal imaging image to be retrieved, and divide each region into a priority display region and a delayed display region according to the display priority.

[0121] The thermal imaging image to be retrieved refers to historical thermal imaging images that the user needs to view and that have already been stored. The stored data of the thermal imaging image to be detected includes at least the stored temperature data of each grid, grid location information, and region information corresponding to the grid area. This region information includes at least the storage priority. Display priority is used to indicate the order in which the temperature stored data is displayed in regions with higher display priority than regions with lower display priority. For example, the stored data of the thermal imaging image to be detected includes at least the user-interested parameters and / or temperature sensitivity parameters for each region. The display priority is determined based on the user-interested parameters and / or temperature sensitivity parameters. The display priority can be the same as or different from the storage priority. When the display priority and storage priority are the same, the stored data of the thermal imaging image to be detected includes the storage priority of each region, but does not need to store the user-interested parameters and / or temperature sensitivity parameters for each region.

[0122] Specifically, a display priority threshold is determined. This threshold can be set based on the actual search scenario and user customization needs; there is no specific numerical limit to the threshold value. Areas with a display priority greater than the threshold are designated as priority display areas, while areas with a display priority less than or equal to the threshold are designated as delayed display areas.

[0123] S520. Determine the user's display requirement area, and determine the target delayed display area from the delayed display area based on the display requirement area.

[0124] The user's desired display area is determined through clicks or selections. The click or selection location within this area is then matched with the location of the delayed display area. The successfully matched delayed display area is designated as the target delayed display area. In other words, the target delayed display area is defined as one that includes part or all of the delayed display area within the desired display area.

[0125] S530: Retrieve and display the storage temperature data corresponding to the priority display area and the target delayed display area.

[0126] The storage temperature data of each grid in the priority display area and the target delay display area are retrieved, loaded, and displayed, while the storage temperature data of each grid in other delay display areas are not displayed. Optionally, the display order of the priority display area precedes that of the target delay display area.

[0127] When there is no user's display requirement area information, the storage temperature data of each grid in the priority display area is retrieved, loaded, and displayed. The storage temperature data of each grid in the delayed display area is not displayed until it is determined that the user's display requirement area includes the delayed display area. Only then is the storage temperature data of each grid in the delayed display area retrieved, loaded, and displayed.

[0128] The technical solution of this invention determines a priority display area and a delayed display area, thereby prioritizing the loading of stored temperature data in the priority display area, reducing the retrieval volume of the delayed display area and postponing the retrieval order of the delayed display area, thus improving the retrieval speed and efficiency of temperature data. Furthermore, the storage of temperature data is determined based on the storage priority of each area, thus ensuring the accuracy of temperature data recovery.

[0129] Figure 6 This is a schematic diagram of a thermal imaging image processing device provided in an embodiment of the present invention. Figure 6 As shown, the device includes:

[0130] The region division module 610 is used to acquire the thermal imaging image collected by the thermal imaging device and divide the thermal imaging image into at least two regions.

[0131] The region parameter determination module 620 is used to determine the user-interested parameters and / or temperature sensitivity parameters for each region based on the thermal imaging image;

[0132] Mesh generation parameter determination module 630 is used to determine the mesh generation parameters of each region based on user-interested parameters and / or temperature sensitivity parameters;

[0133] The grid temperature data storage module 640 is used to divide each region into grids according to the grid division parameters of each region, and to store at least one temperature data in each grid of the thermal imaging image.

[0134] The technical solution of this invention reduces the amount of redundant temperature data to be stored by gridding temperature data in thermal imaging images and dynamically adjusting the grid division accuracy, thereby improving the storage efficiency of temperature data. Furthermore, the different degrees of grid division accuracy in each region are determined based on the user's interest parameters and / or temperature sensitivity parameters in each region, balancing the requirements for storage accuracy and storage efficiency, and reducing storage requirements while ensuring the sampling accuracy of stored temperature data.

[0135] Optionally, the region parameter determination module includes a parameter of interest determination unit, specifically used for:

[0136] Acquire user operation data on historical thermal imaging images captured by the thermal imaging device;

[0137] Determine the user operation parameters for each of the aforementioned areas based on the operation data;

[0138] Target feature recognition is performed on the thermal imaging image, and target feature parameters of each region are determined based on the target feature recognition results;

[0139] The user interest parameters for each region are determined based on the user operation parameters and the target feature parameters for each region.

[0140] Optionally, the region parameter determination module includes a temperature sensitivity parameter determination unit, specifically used for:

[0141] Based on the temperature data of each pixel in each region, the regional temperature fluctuation parameter and the regional temperature limit parameter of each region are determined. In addition, the time dimension temperature change parameter of each region is determined by combining the historical temperature data of each pixel in each corresponding region in the historical thermal imaging images collected by the thermal imaging device. The regional temperature fluctuation parameter, the regional temperature limit parameter and the time dimension temperature change parameter are used as sensitivity influence parameters.

[0142] The temperature sensitivity parameter is determined based on at least one sensitivity influence parameter for each of the aforementioned regions.

[0143] Optional, a mesh generation parameter determination module, specifically used for:

[0144] The storage priority of each region is determined based on the user's interest parameters and / or temperature sensitivity parameters.

[0145] The grid partitioning parameters for each region are determined based on the predetermined mapping relationship between storage priority and grid partitioning parameters and the storage priority of each region.

[0146] Optionally, the mapping relationship between storage priority and grid partitioning parameters includes a level partitioning mapping relationship, a linear mapping relationship, and a non-linear mapping relationship;

[0147] The level division mapping relationship is determined as follows: the storage priority is divided into a first number of priority levels according to the value range of the storage priority, and into a first number of grid levels according to the value range of the grid division parameters, and the one-to-one mapping relationship between each priority level and each grid level is determined as the level division mapping relationship;

[0148] The expression for the linear mapping relationship is as follows:

[0149]

[0150] The expression for the nonlinear mapping relationship is as follows:

[0151]

[0152] Among them, GS r PL represents the meshing parameters for region r. r Indicates the storage priority of region r, GS min GS represents the smallest meshing parameter within the range of possible meshing parameters. max PL represents the maximum meshing parameter within the range of possible meshing parameters. min PL represents the lowest storage priority within the range of possible storage priority values. max γ represents the maximum storage priority within the range of storage priority values; γ represents the non-linear adjustment factor.

[0153] Optional, a grid temperature data storage module, specifically used for:

[0154] The representative temperature data for each grid is determined based on the temperature data of each pixel within each grid; wherein the representative temperature data includes at least one of the following: grid average temperature, grid maximum temperature, and grid minimum temperature;

[0155] The representative temperature data of each grid in the thermal imaging image are stored.

[0156] Optionally, the device further includes a temperature data retrieval module for storing temperature data from at least one grid in the thermal imaging image.

[0157] The display priority of each region in the stored thermal imaging image to be retrieved is determined, and each region is divided into a priority display region and a delayed display region according to the display priority;

[0158] Determine the user's display requirement area, and determine the target delayed display area from the delayed display area based on the display requirement area;

[0159] The storage temperature data corresponding to the priority display area and the target delayed display area are retrieved and displayed.

[0160] The thermal imaging image processing apparatus provided in the embodiments of the present invention can execute the thermal imaging image processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0161] The acquisition, storage, use, and processing of data in this application comply with relevant national laws and regulations and do not violate public order and good morals.

[0162] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0163] Figure 7 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.

[0164] like Figure 7 As 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.

[0165] 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.

[0166] 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 the processing of thermal imaging images.

[0167] In some embodiments, the processing of the method thermal imaging image can 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 can be loaded and / or mounted 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 method thermal imaging image processing described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the method thermal imaging image processing by any other suitable means (e.g., by means of firmware).

[0168] 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 reference products (ASSPs), systems-on-a-chip (SoCs), complex 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 transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0169] 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.

[0170] 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.

[0171] 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).

[0172] The systems and technologies described herein can be implemented in computing systems that include back-end components (e.g., as data servers), or computing systems that include switching components (e.g., application servers), or computing systems that include front-end 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 back-end, switching, or front-end 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.

[0173] 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.

[0174] 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 this is not limited herein.

[0175] 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 processing thermal imaging images, characterized in that, The method includes: Acquire thermal imaging images captured by a thermal imaging device, and divide the thermal imaging images into at least two regions; Based on the thermal imaging images, determine the user interest parameters and / or temperature sensitivity parameters for each of the regions; The grid division parameters for each region are determined based on the user's interest parameters and / or temperature sensitivity parameters. Each region is divided into grids according to the grid division parameters of each region, and at least one temperature data in each grid of the thermal imaging image is stored.

2. The method according to claim 1, characterized in that, Determining user interest parameters for each region based on the thermal imaging image includes: Acquire user operation data on historical thermal imaging images captured by the thermal imaging device; Determine the user operation parameters for each of the aforementioned areas based on the operation data; Target feature recognition is performed on the thermal imaging image, and target feature parameters of each region are determined based on the target feature recognition results; The user interest parameters for each region are determined based on the user operation parameters and the target feature parameters for each region.

3. The method according to claim 1, characterized in that, Determining temperature sensitivity parameters for each region based on the thermal imaging image includes: Based on the temperature data of each pixel in each region, the regional temperature fluctuation parameter and the regional temperature limit parameter of each region are determined. In addition, the time dimension temperature change parameter of each region is determined by combining the historical temperature data of each pixel in each corresponding region in the historical thermal imaging images collected by the thermal imaging device. The regional temperature fluctuation parameter, the regional temperature limit parameter and the time dimension temperature change parameter are used as sensitivity influence parameters. The temperature sensitivity parameter is determined based on at least one sensitivity influence parameter for each of the aforementioned regions.

4. The method according to claim 1, characterized in that, The meshing parameters for each region are determined based on the user's interest parameters and / or temperature sensitivity parameters, including: The storage priority of each region is determined based on the user's interest parameters and / or temperature sensitivity parameters. The grid partitioning parameters for each region are determined based on the predetermined mapping relationship between storage priority and grid partitioning parameters and the storage priority of each region.

5. The method according to claim 4, characterized in that, in, The mapping relationship between storage priority and grid partitioning parameters includes level partitioning mapping, linear mapping, and non-linear mapping; The level division mapping relationship is determined as follows: the storage priority is divided into a first number of priority levels according to the value range of the storage priority, and into a first number of grid levels according to the value range of the grid division parameters, and the one-to-one mapping relationship between each priority level and each grid level is determined as the level division mapping relationship; The expression for the linear mapping relationship is as follows: The expression for the nonlinear mapping relationship is as follows: Among them, GS r PL represents the meshing parameters for region r. r Indicates the storage priority of region r, GS min GS represents the smallest meshing parameter within the range of possible meshing parameters. max PL represents the maximum meshing parameter within the range of possible meshing parameters. min PL represents the lowest storage priority within the range of possible storage priority values. max γ represents the maximum storage priority within the range of storage priority values; γ represents the non-linear adjustment factor.

6. The method according to claim 1, characterized in that, Storing at least one temperature data point in each grid cell of the thermal imaging image includes: The representative temperature data for each grid is determined based on the temperature data of each pixel within each grid; wherein the representative temperature data includes at least one of the following: grid average temperature, grid maximum temperature, and grid minimum temperature; The representative temperature data of each grid in the thermal imaging image are stored.

7. The method according to claim 1, characterized in that, After storing at least one temperature data point in each grid of the thermal imaging image, the method further includes: The display priority of each region in the stored thermal imaging image to be retrieved is determined, and each region is divided into a priority display region and a delayed display region according to the display priority; Determine the user's display requirement area, and determine the target delayed display area from the delayed display area based on the display requirement area; The storage temperature data corresponding to the priority display area and the target delayed display area are retrieved and displayed.

8. A thermal imaging image processing apparatus, characterized in that, The device includes: The region division module is used to acquire thermal imaging images collected by thermal imaging devices and divide the thermal imaging images into at least two regions. The region parameter determination module is used to determine the user interest parameters and / or temperature sensitivity parameters of each region based on the thermal imaging image. The grid division parameter determination module is used to determine the grid division parameters for each region based on the user's interest parameters and / or temperature sensitivity parameters. The grid temperature data storage module is used to divide each region into grids according to the grid division parameters of each region, and to store at least one temperature data in each grid of the thermal imaging image.

9. 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 thermal imaging image processing method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for processing thermal imaging images according to any one of claims 1-7.

Images