A control method and system for infrared image compression and transmission

Abstract

A control method and system for infrared image compression and transmission, relating to the field of data processing technology. The method comprises: obtaining the network bandwidth of the infrared image to be transmitted and the network environment in which the infrared image to be transmitted is located; when the data volume of the infrared image to be transmitted is greater than the data volume threshold, performing image recognition on the infrared image to determine multiple feature areas in the infrared image to be transmitted; matching the compression ratio corresponding to each feature area based on the image features and sub-data volume corresponding to each feature area, and performing image compression operations on each feature area in combination with each compression ratio to obtain a target data packet after compression of each feature area; determining the transmission priority corresponding to each feature area according to the network bandwidth and each target data packet; and performing data transmission on the infrared image to be transmitted according to the transmission priority corresponding to each feature area. The implementation of the technical solution provided by the present application achieves the effect of improving the accuracy of infrared image compression and transmission.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a control method, system, electronic device and storage medium for infrared image compression and transmission. Background Art

[0002] With the development of infrared imaging technology and the expansion of its application scope, the application of high-definition and high-resolution infrared image data is increasing, especially in the fields of military reconnaissance, border monitoring, forest fire monitoring, etc. These high-quality infrared images provide important visual information at night and under low visible light conditions. How to efficiently compress and transmit infrared images has become a technical problem that needs to be solved urgently.

[0003] At present, the existing control methods for infrared image compression and transmission use a unified compression ratio to compress and transmit the entire infrared image. However, in practical applications, when processing high-quality infrared images, the amount of data that needs to be compressed and transmitted is often large. It is difficult to consider the differences between various parts of the infrared image by only using a unified compression ratio to compress and transmit the entire infrared image. Especially under fluctuating network conditions, it is easy to cause the data of various parts of the infrared image to be lost during the compression process, resulting in low accuracy in infrared image compression and transmission. Summary of the invention

[0004] The present application provides a control method, system, electronic device and storage medium for infrared image compression and transmission, which have the effect of improving the accuracy of infrared image compression and transmission.

[0005] In a first aspect, the present application provides a control method for infrared image compression and transmission, comprising:

[0006] Acquire the infrared image to be transmitted and the network bandwidth of the network environment where the infrared image to be transmitted is located;

[0007] When the data volume of the infrared image to be transmitted is greater than a data volume threshold, performing image recognition on the infrared image to determine a plurality of feature areas in the infrared image to be transmitted;

[0008] Based on the image features and sub-data amounts corresponding to the feature regions, the compression ratios corresponding to the feature regions are matched, and image compression operations are performed on the feature regions in combination with the compression ratios to obtain compressed target data packets for the feature regions;

[0009] Determining the transmission priority corresponding to each of the characteristic areas according to the network bandwidth and each of the target data packets;

[0010] The infrared image to be transmitted is transmitted according to the transmission priority corresponding to each of the characteristic areas.

[0011] In a second aspect of the present application, a control system for infrared image compression and transmission is provided, the system comprising:

[0012] An information acquisition module, used for acquiring the infrared image to be transmitted and the network bandwidth of the network environment where the infrared image to be transmitted is located;

[0013] A feature region determination module, configured to perform image recognition on the infrared image to be transmitted and determine a plurality of feature regions in the infrared image to be transmitted when the data volume of the infrared image to be transmitted is greater than a data volume threshold;

[0014] An image compression module, used to match the compression ratio corresponding to each of the feature regions based on the image features and sub-data amounts corresponding to each of the feature regions, and perform image compression operations on each of the feature regions in combination with each of the compression ratios to obtain a compressed target data packet for each of the feature regions;

[0015] The image transmission module is used to determine the transmission priority corresponding to each of the characteristic areas according to the network bandwidth and each of the target data packets; and to perform data transmission on the infrared image to be transmitted according to the transmission priority corresponding to each of the characteristic areas.

[0016] In a third aspect of the present application, an electronic device is provided, comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein the program can implement a control method for infrared image compression and transmission when loaded and executed by the processor.

[0017] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements a control method for infrared image compression and transmission.

[0018] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0019] By adopting the above technical scheme, the network bandwidth of the infrared image to be transmitted and its network environment is obtained, and the transmission conditions can be evaluated in real time. When the data volume of the infrared image to be transmitted exceeds the preset threshold, the scheme further adopts image recognition technology to accurately determine multiple feature areas in the image. These feature areas match the appropriate compression ratio based on their respective image features and sub-data volume, and on this basis, targeted image compression operations are performed on each feature area to generate compressed target data packets. Through this regional and differentiated compression method, the overall data volume is effectively reduced, and the image quality and information integrity are ensured. When determining the transmission priority, the network bandwidth and the specific conditions of each target data packet are comprehensively considered to reasonably allocate transmission resources. According to the transmission priority corresponding to the feature area, it is ensured that the data in the key information area is transmitted first under limited network bandwidth conditions, thereby improving the efficiency of data transmission. This dynamic infrared image compression and transmission method avoids the loss of important information caused by the uniform compression ratio when transmitting infrared images with large data volumes, and improves the accuracy of infrared image compression and transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flowchart of a control method for infrared image compression and transmission provided in an embodiment of the present application;

[0021] Figure 2 It is a structural schematic diagram of a control system for infrared image compression and transmission provided in an embodiment of the present application;

[0022] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0023] Description of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0024] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0025] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0026] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0027] The present application embodiment provides a control method for infrared image compression and transmission. In one embodiment, please refer to Figure 1 , Figure 1 The flowchart of the control method for infrared image compression and transmission provided by the embodiment of the present application can be implemented by a computer program, which can be integrated into an application or run as an independent tool application. The method can also be implemented by a single-chip microcomputer or run on a control system for infrared image compression and transmission based on the von Neumann system. Specifically, the method can include the following steps:

[0028] Step 101: Obtain the infrared image to be transmitted and the network bandwidth of the network environment where the infrared image to be transmitted is located.

[0029] The infrared image to be transmitted refers to a thermal image obtained by infrared imaging that needs to be transmitted through a network. In the embodiment of the present application, the infrared image to be transmitted can be understood as an image obtained by an infrared detection device, which is used to represent the infrared radiation information of the detection scene or target.

[0030] Network bandwidth refers to the information transmission capacity of the network, and is an indicator of the amount of data that can be successfully transmitted per unit time of the network. In the embodiment of the present application, network bandwidth can be understood as the maximum transmission rate of the data transmission channel in the network environment where the current infrared image is located.

[0031] Specifically, in order to achieve effective compression transmission of infrared images, it is necessary to obtain the data information of infrared images and network environment parameters as the basis for optimizing the compression scheme. First, it is necessary to obtain the infrared image to be transmitted. As an image form with important application value, the file size of infrared images is often large, and direct transmission will occupy a large amount of network bandwidth. Therefore, it is necessary to compress them to reduce the amount of data. At the same time, the system needs to detect the real-time network bandwidth of the network environment where the infrared image is located. The network bandwidth directly limits the maximum data transmission volume of the transmission system. Matching the network bandwidth parameters allows the compression control system to dynamically adjust the compression scheme to achieve the best compression effect under different network conditions. Obtaining infrared image information and network bandwidth parameters can provide basic data support for subsequent image analysis, dynamic compression ratio matching, and compression transmission. In this way, the optimal compression transmission scheme can be designed according to the image content and network conditions to ensure the recognition effect of the reconstructed image under limited network bandwidth.

[0032] Step 102: When the data volume of the infrared image to be transmitted is greater than the data volume threshold, image recognition is performed on the infrared image to determine a plurality of feature areas in the infrared image to be transmitted.

[0033] The data volume refers to the information capacity of a digital product, which is a measure of the amount of information. In the embodiment of the present application, the data volume can be understood as the total data volume of the infrared image to be transmitted, which is used to indicate the amount of image information contained in the infrared image.

[0034] The characteristic region refers to a sub-region in the infrared image that contains representative characteristic information. In the embodiment of the present application, the characteristic region can be understood as an important local region extracted from the infrared image through image analysis, which is used to represent the key information content of the infrared image.

[0035] Specifically, when it is detected that the data volume of the infrared image to be transmitted is greater than the preset data volume threshold, the system will start the image recognition process and process the infrared image to determine multiple feature areas. Feature area extraction is performed because infrared images with large data volumes are not suitable for compression using a uniform compression ratio. Direct compression can easily lead to the loss of many important feature information and the inability to accurately transmit the image content. The system will call the image processing algorithm to first detect the edge contour of the infrared image and extract the shape characteristics of the target; then analyze the temperature heat map of the image to determine the hot spot area with higher temperature; and at the same time calculate the area and shape complexity of each initial extracted area. After image analysis and processing, the system can obtain multiple sub-areas with representative features in the infrared image, such as hot target areas, contour target areas, and complex shape areas, as feature areas. These feature areas contain the key information of the infrared image. After obtaining these feature areas, differential compression processing can be performed, that is, each area is compressed using different compression ratios, and then priority transmission is performed. This can ensure that important feature details will not be lost under network bandwidth constraints, thereby achieving the purpose of accurately and efficiently transmitting infrared image content.

[0036] Based on the above embodiment, as an optional embodiment, in step 102: performing image recognition on the infrared image to determine multiple feature areas in the infrared image to be transmitted, this step may also include the following steps:

[0037] Step 201: Acquire temperature distribution information of the infrared image to be transmitted, and construct a temperature gradient map based on the temperature distribution information.

[0038] The temperature distribution information refers to the distribution of temperature values ​​at various locations in the infrared image. In the embodiment of the present application, the temperature distribution information can be understood as a two-dimensional temperature matrix composed of the temperature values ​​detected by each pixel of the infrared image, which is used to represent the thermal distribution state of the infrared image.

[0039] The temperature gradient map refers to a thermal distribution visualization image generated based on the temperature distribution information of the infrared image. In the embodiment of the present application, the temperature gradient map can be understood as an image that uses different colors to represent the change law of temperature from low to high, which is used to more intuitively represent the thermal distribution of the infrared image.

[0040] Specifically, in order to accurately identify the characteristic areas of infrared images, it is necessary to obtain the temperature distribution information of infrared images and construct a temperature gradient map. The temperature distribution information is obtained because the visual information of infrared images is mainly reflected in the difference in temperature distribution. Hot spots, target boundaries, etc. can be extracted from temperature information. The temperature distribution directly reflects the characteristics of the image area. The system will first parse the temperature values ​​of each position from the infrared image to obtain the two-dimensional temperature matrix information of the image, and then construct a temperature gradient map according to the temperature value size, that is, different colors are used to represent the temperature from low to high, showing the thermal distribution of the image. On the temperature gradient map, points with similar temperatures will gather to form areas, and the boundaries of areas with different temperatures will also be more obvious. Therefore, based on the temperature gradient map, the characteristic areas in the image, such as hot areas, boundaries, etc., can be judged more intuitively and accurately. The system can obtain multiple characteristic areas in the infrared image by analyzing the temperature gradient map to provide support for subsequent compression processing. This feature extraction based on the actual temperature distribution can make the compression more accurately fit the image content.

[0041] Step 202: on the temperature gradient map, segment the infrared image to be transmitted into a plurality of initial feature regions in different temperature ranges.

[0042] The initial feature region refers to a set of regions initially extracted from the infrared image by temperature interval segmentation. In the embodiment of the present application, the initial feature region can be understood as a sub-region block with relatively uniform temperature obtained by segmenting the temperature gradient map according to the temperature difference, which is used for subsequent feature extraction and compression processing.

[0043] Specifically, after obtaining the temperature gradient map of the infrared image, the system will perform image segmentation based on the temperature gradient map, and divide the infrared image into multiple initial feature regions of different temperature intervals. The temperature interval segmentation is performed because temperature is important information for distinguishing the characteristics of infrared images. Regions with similar temperatures may have similar characteristics. Therefore, the image can be segmented according to the temperature difference first. The system will first analyze the temperature gradient map and determine multiple appropriate temperature thresholds, such as 20 degrees Celsius, 50 degrees Celsius, etc. Then, these temperature thresholds are used to perform regional growth segmentation on the temperature gradient map, that is, points with the same temperature interval are gathered to form a region. In this way, the entire infrared image can be segmented into multiple initial feature regions with different temperature intervals, such as 0-20 degrees Celsius region, 20-50 degrees Celsius region, etc. These initial feature regions have a certain uniformity in temperature. After segmentation based on temperature intervals, the system can obtain the initial feature region set of the infrared image, which provides input for further feature extraction and compression transmission. The extraction of this temperature corresponding region also makes the compression more consistent with the thermal distribution of the image.

[0044] Step 203: Calculate the shape complexity and temperature change rate of each initial feature region, and perform weighted summation on the shape complexity and temperature change rate of each initial feature region to obtain a feature value of each initial feature region.

[0045] The shape complexity refers to a characteristic parameter for judging the complexity of the regional shape. In the embodiment of the present application, the shape complexity can be understood as a quantitative index of the complexity of the initial characteristic regional shape obtained by calculating the ratio of the regional perimeter to the area, which is used to evaluate the complexity and uniformity of the regional shape.

[0046] The temperature change rate refers to a characteristic parameter for evaluating the rapidity of temperature change in an area. In the embodiment of the present application, the temperature change rate can be understood as a quantitative index of the temperature change gradient in the initial characteristic area obtained by calculating the difference between the highest temperature and the lowest temperature in the area and the area ratio, which is used to judge the uniformity of temperature distribution in the area.

[0047] The eigenvalue refers to the comprehensive calculation result of various indicators for evaluating the characteristics of the initial characteristic region. In the embodiment of the present application, the eigenvalue can be understood as a comprehensive regional characteristic quantitative index obtained by weighted calculation of the shape complexity and temperature change rate of the initial characteristic region, which is used to compare the characteristic degree of different regions.

[0048] Specifically, after obtaining the initial feature area, the system needs to calculate the shape complexity and temperature change rate of each area, and perform weighted summation to obtain the eigenvalue to further determine the characteristics of the area. Because it is not enough to accurately determine the feature area based on the temperature interval segmentation alone, it is also necessary to consider the regional shape and temperature change to determine the representativeness of the regional features. The system will calculate the area and perimeter of each initial feature area, and obtain the highest and lowest temperature values. Then the system can obtain the ratio of perimeter to area as the shape complexity, and the ratio of temperature difference to area as the temperature change rate. Then the system will preset weights, perform weighted summation, and calculate the eigenvalue of the initial feature area. The area with larger shape complexity and temperature change rate also has larger eigenvalues. After calculation, the characteristic index of each initial feature area can be obtained. Combined with the eigenvalue, the initial feature area can be further screened and merged to obtain the final feature area. The system can use this method to judge the initial feature area, extract the target feature area of ​​the image, and provide support for subsequent compression transmission.

[0049] Based on the above embodiment, as an optional embodiment, in step 203: calculating the shape complexity and temperature change rate of each initial feature area, this step may also include the following steps:

[0050] Step 213: Obtain the perimeter and area of ​​each initial feature region, as well as the maximum temperature and minimum temperature in each initial feature region.

[0051] Among them, the perimeter and area of ​​the initial feature region refer to the contour perimeter value and occupied area value of the initial feature region obtained by image segmentation. In the embodiment of the present application, they can be understood as the perimeter information of the extracted initial feature region boundary and the pixel area information of the region itself, which are used to calculate the regional shape complexity.

[0052] The highest temperature and the lowest temperature in the initial characteristic region refer to the maximum temperature value and the minimum temperature value existing inside the initial characteristic region determined by statistical calculation. In the embodiment of the present application, they can be understood as the temperature of the hot spot and the cold spot in the region, which are used for the subsequent calculation of the temperature change rate inside the region.

[0053] Specifically, after obtaining the initial feature area, the system needs to obtain the perimeter, area, and maximum and minimum temperatures of each area. The purpose of obtaining this information is to calculate the shape complexity and temperature change rate of the initial feature area. These two indicators need to rely on the perimeter, area, and temperature range of the area. The system will traverse each initial feature area obtained by division and calculate the contour perimeter, area size, maximum temperature value, and minimum temperature value of the area. Among them, the perimeter reflects the complexity of the shape of the area, and the area reflects the scale of the area. The maximum temperature and minimum temperature determine the range of temperature changes in the area. After obtaining these basic data for each initial feature area, the system can calculate the shape complexity and temperature change rate to further judge the regional characteristics.

[0054] Step 223: For each initial characteristic region, the ratio of the perimeter to the area is used as the shape complexity of the initial characteristic region, and the difference between the highest temperature and the lowest temperature is divided by the area to obtain the temperature change rate of the initial characteristic region.

[0055] Specifically, after obtaining the perimeter, area, and maximum and minimum temperature data of the initial feature area, the system will calculate the shape complexity and temperature change rate of each area. The calculation of shape complexity is to take the ratio of perimeter to area. Because the longer the perimeter and the smaller the area, the more irregular the shape. The temperature change rate is the difference between the highest temperature and the lowest temperature and then divided by the area. The greater the temperature change, the more uneven the temperature distribution in the area. In this way, the shape complexity value and temperature change rate value of each initial feature area can be obtained. These two indicators reflect the characteristic representativeness of the region from the two dimensions of shape and temperature. The calculation of shape complexity and temperature change rate is to be able to quantitatively describe the shape and internal temperature changes of the initial feature area, so as to further judge the characteristic representativeness of the region.

[0056] Step 204: clustering the feature values ​​of each initial feature region to obtain a plurality of initial feature region sets, and merging the initial feature regions in each initial feature region set to obtain a plurality of feature regions in the infrared image to be transmitted.

[0057] The initial feature region set refers to a class set composed of initial feature regions with similar feature values ​​after feature value clustering. In the embodiment of the present application, the initial feature region set can be understood as a region subset that uses a clustering algorithm to classify initial feature regions with similar feature values ​​into the same category for subsequent feature region merging processing.

[0058] Specifically, after calculating the eigenvalues ​​of the initial feature regions, the system will cluster these eigenvalues ​​and merge the regions in each class, and finally determine multiple feature regions of the infrared image. Clustering and merging are performed because the initial feature regions based on temperature segmentation are large in number and small in scale, and need to be further integrated into more representative feature regions to reduce the number of regions and improve processing efficiency. The system will use a clustering algorithm to classify according to the eigenvalue results of the initial feature regions. Initial feature regions with similar eigenvalues ​​are clustered into the same class. Then the system merges the initial feature regions in each eigenvalue class, that is, multiple small initial feature regions in the class are merged into a larger region as the representative feature region of the class. After clustering and merging the initial feature regions, the system can obtain feature regions with larger scale and fewer number, which are marked as the final extracted infrared image feature regions. These feature regions are easier to control in number, and retain the feature information in the initial region, so that subsequent compression and transmission processing can be performed more efficiently and accurately.

[0059] Step 103: Based on the image features and sub-data amounts corresponding to each feature region, the compression ratio corresponding to each feature region is matched, and image compression operations are performed on each feature region in combination with each compression ratio to obtain a compressed target data packet of each feature region.

[0060] The image features and sub-data volume refer to the type of image information contained in each feature area of ​​the infrared image and the specific data volume of the area. In the embodiment of the present application, they can be understood as the visual information composition in each feature area, such as boundaries, heat changes, etc., and the pixel data scale of the area, which are used to match and determine a reasonable compression ratio.

[0061] The compression ratio refers to the ratio of the data volume before and after compression during the image compression process. In the embodiment of the present application, it can be understood as the ratio between the original data volume and the compressed data volume in the compression process adopted for each feature area, which is used to control the compression effect of each area.

[0062] The target data packet refers to the overall data packet composed of the compressed characteristic regions. In the embodiment of the present application, it can be understood as a whole data block generated by merging the compressed regional data after compressing each characteristic region with a matching compression ratio for transmission.

[0063] Specifically, after determining each characteristic area of ​​the infrared image, the system will match and determine the corresponding compression ratio based on the image features and data size of each area, and perform differential compression to finally obtain the compressed target data packet. The purpose of this processing is to reasonably set the compression ratio according to the image information features and size of different areas to achieve a balance between the retention of key information and transmission efficiency. The system will first analyze the image information type of each characteristic area, such as heat distribution, boundary features, etc., as well as the size of the regional data volume. Then, according to the regional data features and size, determine the appropriate compression ratio. For key characteristic areas with more complex image information or larger data volume, the system will set a smaller compression ratio to retain more original information. For ordinary areas with simpler information or smaller data size, a larger compression ratio can be set to improve the compression effect. Then, the system uses different compression ratios to compress each characteristic area separately to ensure compression efficiency without losing important characteristic information. Finally, a compressed target data packet for transmission is generated.

[0064] Based on the above embodiment, as an optional embodiment, in step 103: matching the compression ratio corresponding to each feature area based on the image features and sub-data amount corresponding to each feature area, this step may also include the following steps:

[0065] Step 301: Based on a preset image feature-compression ratio mapping table, match the initial compression ratio corresponding to each image feature, and calculate the compression ratio mean of each initial compression ratio.

[0066] Among them, the preset image feature-compression ratio mapping table refers to a list of recommended compression ratios corresponding to different image features established in advance. In the embodiment of the present application, it can be understood as a lookup table that stores the matching relationship between image information type and compression ratio, which is used to provide a reference for the initial compression ratio selection. The construction process of the preset image feature-compression ratio mapping table is: collect representative sample infrared images to ensure that they contain various typical scenes and feature areas, such as image samples containing hot areas, boundaries, backgrounds and other areas; manually annotate the feature areas of the sample images, for example, manually annotate the feature areas such as hot areas, boundaries, and backgrounds; determine a preliminary compression ratio range for each type of feature area, for example, the hot area compression ratio range is [2-4], the boundary compression ratio range is [1-2], etc.; try different compression ratios within the compression ratio range, and evaluate the image compression effect to determine the optimal compression ratio corresponding to each type of feature area; based on the trial compression results, summarize the optimal compression ratio corresponding to each type of image features, and form a mapping relationship table from image features to compression ratios.

[0067] The initial compression ratio refers to the first recommended compression ratio of each feature area obtained by matching the mapping table. In the embodiment of the present application, it can be understood as the compression ratio recommendation value obtained by referring to the mapping table according to the image information type of each feature area, which is used to provide a reference for determining the compression ratio.

[0068] Specifically, after acquiring each feature area of ​​the image, the system will determine the image features of each area based on the preset mapping relationship table of image features and compression ratios, match the corresponding initial compression ratio, and calculate the average of all initial compression ratios. This is done because it is necessary to first obtain a benchmark compression ratio based on the regional feature mapping table, and calculate the mean as a reference for subsequent optimization. The system will consult the mapping table and match the corresponding initial compression ratio according to the type of image information contained in each feature area, such as hot spots, boundaries, etc. For example, for hot spot features, the initial compression ratio is 2; for boundary features, the initial compression ratio is 1, and then the system calculates the average of the initial compression ratios of all areas, such as 1.5. This mean can reflect the information distribution of the entire image.

[0069] Step 302: Divide the amount of each sub-data by the amount of data of the infrared image to be transmitted to obtain a compression ratio correction coefficient of each characteristic area.

[0070] The compression ratio correction coefficient refers to a correction parameter obtained based on the ratio of the sub-data volume of the feature region to the total data volume of the original image. In the embodiment of the present application, it can be understood as a ratio value of the actual data volume of each feature region relative to the total data volume of the entire image, which is used to correct the initial compression ratio based on the feature.

[0071] Specifically, after obtaining the initial compression ratio, the system will calculate the proportion of the data volume of each feature area to the total data volume of the original image as the compression ratio correction coefficient. In this way, the compression ratio can be corrected according to the actual proportion of data occupied by each area, so that it is more in line with the actual data distribution of the image. The system will count the image data volume of each feature area, that is, the sub-data volume. Then calculate the ratio of the sub-data volume to the total data volume of the entire original image. For example, if the sub-data volume of a region is 50KB and the total data volume of the original image is 200KB, the compression ratio correction coefficient of the region is 50 / 200=0.25. In this way, the compression ratio correction coefficient of each region can be obtained. This reflects the proportion of the region in the entire image data. The larger the regional sub-data, the larger the correction coefficient, and a smaller compression ratio should be used in the overall compression. Therefore, this correction can make up for the shortcomings of compression ratio selection based only on feature extraction, making the compression ratio setting more accurate.

[0072] Step 303: Based on each compression ratio correction coefficient, adjust the initial compression ratio of each feature region to obtain the compression ratio corresponding to each feature region.

[0073] Specifically, after obtaining the compression ratio correction coefficient, the system will adjust the initial compression ratio of each feature area based on the correction coefficient to obtain the final compression ratio. In this way, the considerations based on feature extraction and data volume distribution can be integrated to make the compression ratio setting more comprehensive and accurate. The system will use the compression ratio correction coefficient to correct the initial compression ratio: if the correction coefficient of a certain area is large, it means that the data in this area accounts for a large proportion, then the corresponding initial compression ratio needs to be reduced, and a smaller final compression ratio is used. Conversely, if the correction coefficient is small, the initial compression ratio can be appropriately increased, and a larger final compression ratio can be used. After this correction and adjustment, the visual features and data distribution of the image can be reasonably and comprehensively considered, so that the compression ratio matches the image information distribution characteristics, and compression optimization is achieved. In this way, areas with large amounts of important data use lower compression ratios, and areas with small amounts of unimportant data use higher compression ratios, thereby achieving a balance between fidelity and efficiency.

[0074] Based on the above embodiment, as an optional embodiment, in step 303: adjusting the initial compression ratio of each feature area based on each compression ratio correction coefficient, this step may also include the following steps:

[0075] Step 313: For each feature region, when the amount of sub-data in the feature region is greater than or equal to the compression ratio mean, the initial compression ratio of the feature region is increased by the compression ratio amount corresponding to the compression ratio correction coefficient.

[0076] The compression ratio corresponding to the compression ratio correction coefficient refers to the adjustment amount of the actual compression ratio mapped according to the correction coefficient value. In the embodiment of the present application, it can be understood as a specific adjustment value of the initial compression ratio mapped based on the compression ratio correction coefficient, which is used to accurately determine the final compression ratio according to the data ratio.

[0077] Specifically, after obtaining the sub-data volume and compression ratio mean of each feature region, the system will determine whether the sub-data volume of each region is greater than or equal to the compression ratio mean. If the sub-data volume is greater than or equal to the mean, it is necessary to increase the compression ratio corresponding to the compression ratio correction coefficient to obtain the adjusted initial compression ratio. This is done because the region with a larger sub-data volume should occupy more original data to maintain fidelity, and a lower compression ratio needs to be used. If the sub-data volume of a region is 100KB, the compression ratio mean is 2, and the compression ratio correction coefficient is 0.3, then the sub-data volume is greater than the mean, and it is necessary to increase the compression ratio corresponding to the compression ratio correction coefficient of 0.3, for example, increase it by 0.5, and the initial compression ratio of the region is adjusted from 2 to 2 minus 0.5, which is 1.5. In this way, feature regions with large sub-data volumes will use a smaller compression ratio, which can retain more original information, thereby taking into account the data distribution within the region, so that the compression system can selectively retain key information.

[0078] Step 323: When the sub-data volume of the feature region is smaller than the compression ratio mean value, the initial compression ratio of the feature region is reduced by the compression ratio amount corresponding to the compression ratio correction coefficient.

[0079] Specifically, when it is determined that the sub-data volume of the feature area is less than the mean compression ratio, the system will reduce the compression ratio corresponding to the compression ratio correction coefficient to obtain the adjusted initial compression ratio. This is done because areas with smaller sub-data volumes can use higher compression ratios to improve compression efficiency. If the sub-data volume of a region is 50KB, the compression ratio mean is 2, and the compression ratio correction coefficient is 0.2, then if the sub-data volume is less than the mean, it is necessary to reduce the compression ratio corresponding to the compression ratio correction coefficient of 0.2, for example, by reducing it by 0.3, then the initial compression ratio of the region is adjusted from 2 to 2 plus 0.3 = 2.3. In this way, feature areas with small sub-data volumes will use a larger compression ratio, which can improve the compression effect, thereby rationally utilizing the information distribution characteristics of each region, compressing less important data at a high ratio, and reducing the size of the transmission package.

[0080] Step 104: Determine the transmission priority corresponding to each feature area according to the network bandwidth and each target data packet; and perform data transmission on the infrared image to be transmitted according to the transmission priority corresponding to each feature area.

[0081] The transmission priority refers to the transmission order level determined according to the importance of the target data packet. In the embodiment of the present application, it can be understood as the transmission sorting level assigned to each compressed characteristic area data packet according to its importance, which is used to guide the transmission order of the data packet.

[0082] Specifically, after obtaining the compressed target data packet, the system will determine the transmission priority of each feature area according to the network bandwidth and the size of each packet. Then the image data is transmitted in order of priority, so that limited network resources can be reasonably allocated and important data can be transmitted first. The system will count the current available bandwidth of the network. At the same time, the size of each target data packet is analyzed, and high transmission priority is given to the key areas with smaller data packets. For data with large packet size, a low priority is set. Then the system gradually transmits each target data packet in order from high to low priority. The high-priority data packets will be transmitted first, and important image information can reach the receiving end faster. In this way, in the case of limited bandwidth resources, low-latency transmission of important information can be ensured to avoid the loss of key image features.

[0083] Based on the above embodiment, as an optional embodiment, in step 104: determining the transmission priority corresponding to each characteristic area according to the network bandwidth and each target data packet, this step may also include the following steps:

[0084] Step 401: Obtain the target data volume of each target data packet; calculate the estimated transmission time of each target data packet according to the network bandwidth and the data volume.

[0085] The estimated transmission duration refers to the theoretical transmission time of the data packet calculated based on the target data packet size and the network bandwidth. In the embodiment of the present application, it can be understood as the expected transmission duration calculated by counting the data volume of each target packet after compression and combining it with the network bandwidth, which is used to evaluate the transmission efficiency of different data packets and guide the determination of transmission priority.

[0086] Specifically, after obtaining each target data packet, the system needs to obtain the specific data size of each data packet. Then, based on the current network bandwidth, the estimated transmission time of each packet is calculated, so that the transmission time of different packets can be evaluated, providing a basis for transmission sorting. The system will count the amount of compressed data in each target data packet, that is, the target data volume, and measure the current available bandwidth of the network. Then, based on the packet size and bandwidth, the theoretical transmission time of each packet can be calculated. For example, a 100KB data packet is expected to take 10 seconds to transmit at a network bandwidth of 10KB / s. The estimated transmission time can evaluate the actual transmission efficiency of different data packets, so that the system can sort and schedule the priority of different packets according to the transmission time to achieve optimal configuration of transmission resources.

[0087] Step 402: The ratio of the data volume of each target data packet to the estimated transmission duration is used as the transmission efficiency index of the characteristic area corresponding to each target data packet.

[0088] The transmission efficiency index refers to the ratio of the data volume of the target data packet to its estimated transmission time. In the embodiment of the present application, it can be understood as a quantitative index of the transmission efficiency performance of each compressed target data packet, which is used to evaluate the transmission efficiency of different data packets as a basis for determining the transmission priority.

[0089] Specifically, after obtaining the estimated transmission time of each data packet, the system will calculate the ratio of the target data volume to the transmission time as the transmission efficiency index of the area corresponding to the data packet. This can evaluate the transmission efficiency of the data in each area and guide the setting of transmission priority. The system divides the target data volume of each packet by the estimated transmission time. For example, if the target data volume of a packet is 100KB and the estimated duration is 10 seconds, the transmission efficiency index is 100 / 10=10KB / second. The higher the efficiency index, the larger the amount of data that can be transmitted per unit time and the higher the transmission efficiency. The system can prioritize the transmission of high-efficiency packets according to the transmission efficiency index. In this way, more critical data can be transmitted when bandwidth is limited, improving resource utilization efficiency.

[0090] Step 403: combining the transmission efficiency indexes, assigning the corresponding transmission priority to each characteristic area in descending order.

[0091] Specifically, after calculating the transmission efficiency index of the data packets in each characteristic area, the system will sort the areas from high to low according to the index and assign transmission priorities. In this way, data packets can be reasonably scheduled according to the transmission efficiency and the utilization of limited network resources can be optimized. The system will arrange the data packets in all areas from large to small according to the value of the transmission efficiency index, and then give them transmission priorities from high to low. Areas with large efficiency indexes will receive high priority. For example, the top three areas with the highest index are assigned the highest transmission priority of 1-3. Transmitting data packets in the order of priority 1-3 allows the data with the highest transmission efficiency to be completed first, so that the system can sort them scientifically and allow key data to be transmitted quickly, thereby improving the overall transmission efficiency.

[0092] Based on the above embodiment, as an optional embodiment, in step 104: data transmission of the infrared image to be transmitted is performed according to the transmission priority corresponding to each characteristic area. After this step, the following steps may also be included:

[0093] Step 501: when the network bandwidth is less than the network bandwidth threshold, it is determined that a network failure occurs in the network environment where the infrared image to be transmitted is located, and a plurality of untransmitted feature areas in the infrared image to be transmitted are determined.

[0094] Specifically, during the image data transmission process, the system will monitor the current network bandwidth in real time. When it is detected that the network bandwidth is less than the preset network bandwidth threshold, it will be determined that the network environment has a fault or blockage. At the same time, the system will also confirm which characteristic areas have not completed the transmission of data packets when the network failure occurs. In this way, when a network failure occurs, the remaining untransmitted data packets can be quickly determined so that countermeasures can be taken. The system continuously detects network bandwidth data. If it is detected that the bandwidth drops below the threshold of 20KB, it is determined that a network failure has occurred. At the same time, based on the data packets that have been transmitted, it is determined that there are still data in the hot zone and the boundary area that have not been transmitted. After obtaining this information, the system can start the emergency handling process for network failures, so that data transmission can be ensured even when the network environment deteriorates.

[0095] Step 502: Switch the network channel for data transmission of the infrared image to be transmitted to the standby network channel, and transmit the infrared image to be transmitted according to the transmission priority corresponding to each feature area that has not been transmitted.

[0096] Among them, the network channel refers to the main network link used to transmit image data. The backup network channel refers to the alternative network link other than the main network channel. In the embodiment of the present application, they can be understood as the main network and the alternative network used for image data transmission. The main network is used for image data transmission under normal circumstances, and the alternative network is used to switch to use when the main network fails to ensure the continuity of data transmission.

[0097] Specifically, when a network failure is detected, the system will switch the network channel for data transmission. After switching from the original faulty network channel to the backup network channel, the system will continue to transmit according to the priority of the untransmitted area, so that the image data transmission can be quickly restored after the network failure and reduce the impact of the failure. When a network failure is detected, the system will directly switch to the backup network channel, and then the system will first transmit high-priority data packets such as hot areas according to the transmission priority of the untransmitted area. In this way, critical data can be quickly transmitted through the backup channel to avoid data loss. When the main channel is restored, the system can switch back to the main channel to continue transmission.

[0098] It should be noted that when the data volume of the infrared image to be transmitted is less than or equal to the data volume threshold, it indicates that the data volume of the infrared image to be transmitted is small at this time, and the infrared image to be transmitted can be compressed and transmitted using the set reference compression ratio. The specific process includes: after obtaining the specific data volume of the image to be transmitted, the system will determine whether the data volume is less than or equal to the preset data volume threshold. If it is determined that this condition is met, that is, the data volume is small, the system will use the preset reference compression ratio to compress the entire image, and then transmit the data. In this way, when the image data volume itself is small, the complex compression ratio calculation process can be skipped, and the reference compression ratio can be directly used for compression and transmission, simplifying the operation process. The system will preset a reference compression ratio, for example, set to 5. When it is detected that the data volume of a certain image is 100KB and the threshold is set to 200KB, the 100KB data volume less than the threshold will trigger the reference compression ratio compression, and the system will skip the subsequent compression ratio calculation, directly compress the image uniformly with the reference compression ratio of 5, and then transmit it. In this way, when the amount of data to be processed is not large, the processing flow can be accelerated and the processing efficiency can be improved.

[0099] Reference Figure 2 , a control system for infrared image compression and transmission provided in an embodiment of the present application, the system comprises: an information acquisition module, a feature area determination module, an image compression module, and an image transmission module, wherein:

[0100] An information acquisition module, used for acquiring the infrared image to be transmitted and the network bandwidth of the network environment where the infrared image to be transmitted is located;

[0101] A feature region determination module, used to perform image recognition on the infrared image to be transmitted and determine a plurality of feature regions in the infrared image to be transmitted when the data volume of the infrared image to be transmitted is greater than a data volume threshold;

[0102] An image compression module is used to match the compression ratio corresponding to each feature area based on the image features and sub-data volume corresponding to each feature area, and perform image compression operations on each feature area in combination with each compression ratio to obtain a compressed target data packet of each feature area;

[0103] The image transmission module is used to determine the transmission priority corresponding to each feature area according to the network bandwidth and each target data packet; and to transmit the infrared image to be transmitted according to the transmission priority corresponding to each feature area.

[0104] On the basis of the above-mentioned embodiment, the feature area determination module is also used to obtain the temperature distribution information of the infrared image to be transmitted, and construct a temperature gradient map based on the temperature distribution information; on the temperature gradient map, the infrared image to be transmitted is divided into multiple initial feature areas in different temperature ranges; the shape complexity and temperature change rate of each initial feature area are calculated, and the shape complexity and temperature change rate of each initial feature area are weightedly summed to obtain the feature value of each initial feature area; the feature values ​​of each initial feature area are clustered to obtain multiple initial feature area sets, and each initial feature area in each initial feature area set is merged to obtain multiple feature areas in the infrared image to be transmitted.

[0105] Based on the above embodiment, the feature area determination module is also used to obtain the perimeter and area of ​​each initial feature area, as well as the maximum temperature and minimum temperature in each initial feature area; for each initial feature area, the ratio of the perimeter to the area is used as the shape complexity of the initial feature area, and the difference between the maximum temperature and the minimum temperature is divided by the area to obtain the temperature change rate of the initial feature area.

[0106] On the basis of the above-mentioned embodiment, the image compression module is also used to match the initial compression ratio corresponding to each image feature based on a preset image feature-compression ratio mapping table, and calculate the compression ratio mean of each initial compression ratio; divide each sub-data volume by the data volume of the infrared image to be transmitted to obtain the compression ratio correction coefficient of each feature area; based on each compression ratio correction coefficient, adjust the initial compression ratio of each feature area to obtain the compression ratio corresponding to each feature area.

[0107] On the basis of the above embodiment, the image compression module is also used for each feature area. When the amount of sub-data in the feature area is greater than or equal to the mean compression ratio, the initial compression ratio of the feature area is increased by the compression ratio amount corresponding to the compression ratio correction coefficient; when the amount of sub-data in the feature area is less than the mean compression ratio, the initial compression ratio of the feature area is reduced by the compression ratio amount corresponding to the compression ratio correction coefficient.

[0108] Based on the above embodiments, the image transmission module is also used to obtain the target data volume of each target data packet; calculate the estimated transmission time of each target data packet based on the network bandwidth and the data volume; use the ratio of the data volume of each target data packet to the estimated transmission time as the transmission efficiency index of the characteristic area corresponding to each target data packet; and assign the corresponding transmission priority to each characteristic area in descending order based on the transmission efficiency index.

[0109] On the basis of the above embodiment, the image transmission module is also used to determine that a network failure has occurred in the network environment where the infrared image to be transmitted is located when the network bandwidth is less than the network bandwidth threshold, and to determine multiple untransmitted feature areas in the infrared image to be transmitted; switch the network channel for data transmission of the infrared image to be transmitted to a backup network channel, and transmit data of the infrared image to be transmitted according to the transmission priority corresponding to each untransmitted feature area.

[0110] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0111] The present application also discloses an electronic device. Figure 3 , Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0112] The communication bus 302 is used to realize the connection and communication between these components.

[0113] The user interface 303 may include a display interface and a camera interface. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0114] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0115] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface diagrams and applications, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0116] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program for a control method for infrared image compression and transmission.

[0117] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program stored in the memory 305 for a control method for infrared image compression and transmission. When executed by one or more processors 301, the electronic device 300 executes one or more methods in the above-mentioned embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described order of actions, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0118] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0119] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0120] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0121] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0122] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0123] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0124] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not recorded in the present disclosure. The description and examples are to be regarded as exemplary only.

Claims

1. A control method for infrared image compression and transmission, characterized in that: include: Acquire the infrared image to be transmitted and the network bandwidth of the network environment where the infrared image to be transmitted is located; When the data volume of the infrared image to be transmitted is greater than a data volume threshold, performing image recognition on the infrared image to determine a plurality of feature areas in the infrared image to be transmitted; Based on the image features and sub-data amounts corresponding to the feature regions, the compression ratios corresponding to the feature regions are matched, and image compression operations are performed on the feature regions in combination with the compression ratios to obtain compressed target data packets for the feature regions; Determining the transmission priority corresponding to each of the characteristic areas according to the network bandwidth and each of the target data packets; Transmitting the infrared image to be transmitted according to the transmission priority corresponding to each of the characteristic areas; The performing image recognition on the infrared image to determine a plurality of feature areas in the infrared image to be transmitted includes: Acquiring temperature distribution information of the infrared image to be transmitted, and constructing a temperature gradient map based on the temperature distribution information; On the temperature gradient map, dividing the infrared image to be transmitted into a plurality of initial feature regions in different temperature intervals; Calculating the shape complexity and temperature change rate of each of the initial feature regions, and performing weighted summation of the shape complexity and temperature change rate of each of the initial feature regions to obtain a feature value of each of the initial feature regions; Clustering the characteristic values ​​of each of the initial characteristic regions to obtain a plurality of initial characteristic region sets, and merging the initial characteristic regions in each of the initial characteristic region sets to obtain a plurality of characteristic regions in the infrared image to be transmitted; The matching of the compression ratio corresponding to each of the feature regions based on the image features and the amount of sub-data corresponding to each of the feature regions includes: Based on a preset image feature-compression ratio mapping table, matching the initial compression ratio corresponding to each of the image features, and calculating the compression ratio mean of each of the initial compression ratios; Dividing the amount of each sub-data by the amount of data of the infrared image to be transmitted, to obtain a compression ratio correction coefficient of each characteristic area; Based on the compression ratio correction coefficients, the initial compression ratios of the characteristic regions are adjusted to obtain the compression ratios corresponding to the characteristic regions.

2. The control method for infrared image compression and transmission according to claim 1, characterized in that: The calculating of the shape complexity and the temperature change rate of each of the initial feature regions comprises: Obtaining the perimeter and area of ​​each of the initial characteristic regions, and the highest temperature and the lowest temperature in each of the initial characteristic regions; For each of the initial characteristic regions, the ratio of the perimeter to the area is taken as the shape complexity of the initial characteristic region, and the difference between the highest temperature and the lowest temperature is divided by the area to obtain the temperature change rate of the initial characteristic region.

3. The control method for infrared image compression and transmission according to claim 1, characterized in that: The adjusting the initial compression ratio of each of the feature regions based on each of the compression ratio correction coefficients includes: For each of the characteristic regions, when the amount of sub-data of the characteristic region is greater than or equal to the compression ratio mean value, the initial compression ratio of the characteristic region is increased by the compression ratio amount corresponding to the compression ratio correction coefficient; When the sub-data amount of the characteristic region is smaller than the compression ratio mean value, the initial compression ratio of the characteristic region is reduced by the compression ratio amount corresponding to the compression ratio correction coefficient.

4. The control method for infrared image compression and transmission according to claim 1, characterized in that: The determining, according to the network bandwidth and each of the target data packets, the transmission priority corresponding to each of the characteristic areas comprises: Obtaining a target data volume of each target data packet; Calculating the estimated transmission time of each target data packet according to the network bandwidth and the data volume; The ratio of the data volume of each target data packet to the estimated transmission duration is used as the transmission efficiency index of the characteristic area corresponding to each target data packet; In combination with the transmission efficiency indexes, the transmission priority corresponding to each of the characteristic regions is assigned in descending order.

5. The control method for infrared image compression and transmission according to claim 1, characterized in that: After the infrared image to be transmitted is transmitted according to the transmission priority corresponding to each of the feature areas, the method further includes: When the network bandwidth is less than a network bandwidth threshold, determining that a network failure occurs in the network environment where the infrared image to be transmitted is located, and determining a plurality of untransmitted feature areas in the infrared image to be transmitted; The network channel for data transmission of the infrared image to be transmitted is switched to a standby network channel, and data transmission of the infrared image to be transmitted is performed according to the transmission priority corresponding to each of the feature areas that have not been transmitted.

6. A control system for infrared image compression and transmission, characterized in that: The system comprises: An information acquisition module, used for acquiring the infrared image to be transmitted and the network bandwidth of the network environment where the infrared image to be transmitted is located; A feature region determination module, configured to perform image recognition on the infrared image to be transmitted and determine a plurality of feature regions in the infrared image to be transmitted when the data volume of the infrared image to be transmitted is greater than a data volume threshold; An image compression module, used to match the compression ratio corresponding to each of the feature regions based on the image features and sub-data amounts corresponding to each of the feature regions, and perform image compression operations on each of the feature regions in combination with each of the compression ratios to obtain a compressed target data packet for each of the feature regions; An image transmission module is used to determine the transmission priority corresponding to each of the characteristic areas according to the network bandwidth and each of the target data packets; and to perform data transmission on the infrared image to be transmitted according to the transmission priority corresponding to each of the characteristic areas; The performing image recognition on the infrared image to determine a plurality of feature areas in the infrared image to be transmitted includes: Acquiring temperature distribution information of the infrared image to be transmitted, and constructing a temperature gradient map based on the temperature distribution information; On the temperature gradient map, dividing the infrared image to be transmitted into a plurality of initial feature regions in different temperature intervals; Calculating the shape complexity and temperature change rate of each of the initial feature regions, and performing weighted summation of the shape complexity and temperature change rate of each of the initial feature regions to obtain a feature value of each of the initial feature regions; Clustering the characteristic values ​​of each of the initial characteristic regions to obtain a plurality of initial characteristic region sets, and merging the initial characteristic regions in each of the initial characteristic region sets to obtain a plurality of characteristic regions in the infrared image to be transmitted; The matching of the compression ratio corresponding to each of the feature regions based on the image features and the amount of sub-data corresponding to each of the feature regions includes: Based on a preset image feature-compression ratio mapping table, matching the initial compression ratio corresponding to each of the image features, and calculating the compression ratio mean of each of the initial compression ratios; Dividing the amount of each sub-data by the amount of data of the infrared image to be transmitted, to obtain a compression ratio correction coefficient of each characteristic area; Based on the compression ratio correction coefficients, the initial compression ratios of the characteristic regions are adjusted to obtain the compression ratios corresponding to the characteristic regions.

7. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the control method for infrared image compression and transmission as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the control method for infrared image compression and transmission as described in any one of claims 1 to 5 is executed.

Images