An image transmission method, device, detector, terminal device and storage medium

Abstract

This application provides an image transmission method, apparatus, detector, terminal device, and storage medium, applied to a detector in an image processing system. The image processing system also includes a terminal device. The method includes: acquiring an image to be transmitted; determining a first position of an object region and a second position of an empty field region in the image to be transmitted, where the empty field region is a region in the image to be transmitted where no object exists; cropping an object image from the image to be transmitted based on the first position; calculating an empty field index corresponding to the empty field region based on the pixel values ​​of the empty field region corresponding to the second position; and transmitting the object image and the empty field index to the terminal device, so that the terminal device can perform image reconstruction based on the object image and the empty field index to obtain the transmitted image. This method only requires transmitting the object image and the empty field index to the terminal device, reducing the amount of data transmitted, improving image transmission efficiency, and lowering the cost and development complexity of image transmission.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to an image transmission method, apparatus, detector, terminal device and storage medium. Background Technology

[0002] Detectors are widely used in industrial and medical inspection fields. During their use, the images captured by the detector need to be transmitted to terminal devices for viewing and processing. However, the bandwidth of the data link during this transmission significantly limits the image frame rate. For low-frame-rate detectors, gigabit networks are a common interface. This interface is widely used between terminal devices and routers, thus placing lower demands on the hardware of the terminal devices and offering greater adaptability.

[0003] However, for high frame rate detectors, the most commonly used interfaces are 10 Gigabit Ethernet, dual network ports, and Camera-Link interfaces. Regardless of the interface used, the compatibility of the terminal device is relatively low, requiring a 10 Gigabit Ethernet card, two network interfaces, or an adapter for the Camera-Link interface. Developing drivers for different interfaces makes the software of the terminal device very complex, and also increases the hardware cost of the detector itself. Therefore, the cost and development complexity of transmitting images from the detector to the terminal device are both high. Summary of the Invention

[0004] The purpose of this application is to provide an image transmission method, apparatus, detector, terminal device, and storage medium to reduce the cost and development complexity of image transmission. The specific technical solution is as follows:

[0005] In a first aspect, embodiments of this application provide an image transmission method applied to a detector in an image processing system, the image processing system further including a terminal device, the method comprising:

[0006] Acquire images to be transmitted;

[0007] Determine a first position of an object region and a second position of an empty field region in the image to be transmitted, wherein the empty field region is a region in the image to be transmitted where no object exists;

[0008] Based on the first position, an object image is cropped from the image to be transmitted;

[0009] Based on the pixel values ​​of the empty area corresponding to the second position, the empty area index corresponding to the empty area is calculated;

[0010] The object image and the airspace index are transmitted to the terminal device so that the terminal device can reconstruct the image based on the object image and the airspace index to obtain the transmitted image.

[0011] Optionally, the step of determining the first position of the object region and the second position of the empty field region in the image to be transmitted includes:

[0012] An object recognition algorithm is used to identify the object regions in the image to be transmitted, and the first initial position of the object regions is obtained.

[0013] An empty field recognition algorithm is used to identify the empty field regions in the image to be transmitted, thereby obtaining the second initial position of the empty field regions;

[0014] The first initial position and the second initial position are compared to obtain the comparison result;

[0015] The first initial position is adjusted according to the comparison result to obtain the first position of the object region, and the second initial position is adjusted according to the comparison result to obtain the second position of the empty field region.

[0016] Optionally, the step of using an empty field recognition algorithm to identify empty field regions in the image to be transmitted and obtaining the second initial position of the empty field regions includes:

[0017] The empty field region in the image to be transmitted is identified based on the image characteristics corresponding to the empty field region to obtain the second initial position of the empty field region, wherein the image characteristics include at least the feature that the pixel values ​​of the image satisfy Gaussian noise.

[0018] Optionally, the step of adjusting the first initial position according to the comparison result to obtain the first position of the object region, and adjusting the second initial position according to the comparison result to obtain the second position of the empty field region, includes:

[0019] Based on the comparison results, a first boundary and a second boundary are determined within a preset deviation range for the positional deviation, wherein the first boundary is the boundary represented by the first initial position, and the second boundary is the boundary represented by the second initial position;

[0020] For the first boundary and the second boundary, calculate the average position of the first boundary and the second boundary, and use it as the boundary between the object region and the empty field region to obtain the first position of the object region and the second position of the empty field region.

[0021] Optionally, the image processing system further includes a sensor;

[0022] The step of determining the first position of the object region and the second position of the empty field region in the image to be transmitted includes:

[0023] Acquire sensor images captured by the sensor;

[0024] Based on the location of the object region in the sensor image and the positional relationship between the sensor and the detector, the first location of the object region in the image to be transmitted is determined;

[0025] Based on the first location, determine the second location of the open area.

[0026] Optionally, before the step of transmitting the object image and the airspace index to the terminal device, the method further includes:

[0027] The object image is compressed to obtain a compressed object image.

[0028] Optionally, the empty field index includes at least one of the following: mean, standard deviation, maximum, minimum, median, percentage of pixels within a preset multiple of the mean standard deviation, noise, and uniformity.

[0029] Secondly, embodiments of this application provide an image transmission method applied to a terminal device in an image processing system, wherein the image processing system further includes a detector, and the method includes:

[0030] The detector receives an object image and an empty field index transmitted by the detector, wherein the object image is cropped based on a first position of the object region in the image to be transmitted, and the empty field index is calculated based on the pixel values ​​of the empty field region in the image to be transmitted.

[0031] Image reconstruction is performed based on the object image and the airspace index to obtain the transmitted image.

[0032] Optionally, the step of reconstructing the image based on the object image and the airspace index to obtain the transmitted image includes:

[0033] The object image is filled into a preset blank image according to the first position to obtain a first image, wherein the size of the preset blank image is the same as the size of the image to be transmitted;

[0034] Based on the aforementioned empty field index, an empty field image is reconstructed to obtain a second image, wherein the size of the second image is the same as the size of the image to be transmitted;

[0035] Based on the first position, the region corresponding to the object region in the second image is removed to obtain an empty field image;

[0036] The first image is superimposed on the empty field image to obtain the transmitted image.

[0037] Optionally, before the step of overlaying the first image with the empty field image to obtain the transmitted image, the method further includes:

[0038] Based on the pixel values ​​of the empty field image, the empty field index of the empty field image is calculated and used as the reconstructed empty field index.

[0039] Calculate the difference between the reconstructed airfield index and the airfield index transmitted by the detector;

[0040] If the difference is not within the preset difference range, adjust the pixel values ​​of the empty field image to obtain the adjusted image;

[0041] The adjusted image is used as an empty field image, and the empty field index of the empty field image is calculated based on the pixel values ​​of the empty field image as a step to reconstruct the empty field index, until the difference is within the preset difference range.

[0042] Thirdly, embodiments of this application provide an image transmission device applied to a detector in an image processing system, the image processing system further including a terminal device, the device comprising:

[0043] The image acquisition module is used to acquire images to be transmitted.

[0044] A position determination module is used to determine a first position of an object region and a second position of an empty field region in the image to be transmitted, wherein the empty field region is a region in the image to be transmitted where no object exists;

[0045] An object image cropping module is used to crop an object image from the image to be transmitted based on the first position;

[0046] The empty field index calculation module is used to calculate the empty field index corresponding to the empty field area based on the pixel value of the empty field area corresponding to the second position.

[0047] An image and indicator transmission module is used to transmit the object image and the airspace indicator to the terminal device, so that the terminal device can perform image reconstruction based on the object image and the airspace indicator to obtain the transmitted image.

[0048] Optionally, the location determination module includes:

[0049] The first initial position acquisition submodule is used to identify the object region in the image to be transmitted using an object recognition algorithm, and obtain the first initial position of the object region;

[0050] The second initial position acquisition submodule is used to identify the empty field region in the image to be transmitted using an empty field recognition algorithm, and obtain the second initial position of the empty field region.

[0051] The comparison result acquisition submodule is used to compare the first initial position and the second initial position to obtain the comparison result;

[0052] The location acquisition submodule is used to adjust the first initial position according to the comparison result to obtain the first position of the object region, and to adjust the second initial position according to the comparison result to obtain the second position of the empty field region.

[0053] Optionally, the second initial position acquisition submodule includes:

[0054] The second initial position acquisition unit identifies the empty field region in the image to be transmitted based on the image characteristics corresponding to the empty field region, and obtains the second initial position of the empty field region. The image characteristics include at least the feature that the pixel values ​​of the image satisfy Gaussian noise.

[0055] Optionally, the location acquisition submodule includes:

[0056] A boundary determination unit is used to determine a first boundary and a second boundary within a preset deviation range based on the comparison result, wherein the first boundary is the boundary represented by the first initial position and the second boundary is the boundary represented by the second initial position.

[0057] The position acquisition unit is used to calculate the average position of the first boundary and the second boundary for the first boundary and the second boundary, and use it as the boundary between the object region and the empty field region to obtain the first position of the object region and the second position of the empty field region.

[0058] Optionally, the image processing system further includes a sensor;

[0059] The location determination module includes:

[0060] The sensor image determination submodule is used to acquire sensor images captured by the sensor;

[0061] The first position determination submodule is used to determine the first position of the object region in the image to be transmitted based on the position of the object region in the sensor image and the positional relationship between the sensor and the detector.

[0062] The second position determination submodule is used to determine the second position of the open area based on the first position.

[0063] Optionally, the device further includes:

[0064] The compressed object image acquisition module is used to compress the object image before the step of transmitting the object image and the airspace index to the terminal device, so as to obtain a compressed object image.

[0065] Optionally, the empty field index includes at least one of the following: mean, standard deviation, maximum, minimum, median, percentage of pixels within a preset multiple of the mean standard deviation, noise, and uniformity.

[0066] Fourthly, embodiments of this application provide an image transmission device applied to a terminal device in an image processing system, wherein the image processing system further includes a detector, and the device includes:

[0067] The image and index receiving module is used to receive the object image and the empty field index transmitted by the detector, wherein the object image is obtained by cropping the object region in the image to be transmitted, and the empty field index is calculated based on the pixel value of the empty field region in the image to be transmitted.

[0068] The image acquisition module is used to reconstruct the image based on the object image and the airspace index to obtain the transmitted image.

[0069] Optionally, the image acquisition module includes:

[0070] The first image acquisition submodule is used to fill the object image into a preset blank image according to the first position to obtain a first image, wherein the size of the preset blank image is the same as the size of the image to be transmitted;

[0071] The second image acquisition submodule is used to reconstruct the air field image based on the air field index to obtain a second image, wherein the size of the second image is the same as the size of the image to be transmitted;

[0072] The empty field image acquisition submodule is used to remove the region corresponding to the object region in the second image based on the first position to obtain an empty field image;

[0073] The image acquisition submodule is used to overlay the first image with the empty field image to obtain the transmitted image.

[0074] Optionally, the device further includes:

[0075] The reconstruction void field index calculation module is used to calculate the void field index of the void field image based on the pixel value of the void field image before the step of superimposing the first image with the void field image to obtain the transmitted image, and use it as the reconstruction void field index.

[0076] The difference calculation module is used to calculate the difference between the reconstructed airfield index and the airfield index transmitted by the detector.

[0077] The image acquisition module is adjusted to adjust the pixel values ​​of the empty field image if the difference is not within a preset difference range, so as to obtain an adjusted image.

[0078] The index calculation and return module is used to take the adjusted image as an empty field image and return the empty field index of the empty field image calculated based on the pixel value of the empty field image as a step of reconstructing the empty field index, until the difference is within the preset difference range.

[0079] Fifthly, embodiments of this application provide an image processing system, the system comprising a detector and a terminal device, wherein:

[0080] The detector is used to acquire an image to be transmitted; determine a first position of an object region and a second position of an empty field region in the image to be transmitted; crop an object image from the image to be transmitted based on the first position; calculate an empty field index corresponding to the empty field region based on the pixel value of the empty field region corresponding to the second position; and transmit the object image and the empty field index to the terminal device so that the terminal device can perform image reconstruction based on the object image and the empty field index to obtain the transmitted image; wherein, the empty field region is a region in the image to be transmitted where no object exists.

[0081] The terminal device is used to receive the object image and the air field index transmitted by the detector, and to perform image reconstruction based on the object image and the air field index to obtain the transmitted image; wherein, the object image is obtained by cropping the object region in the image to be transmitted, and the air field index is calculated based on the pixel value of the air field region in the image to be transmitted.

[0082] Optionally, the system further includes sensors, wherein:

[0083] The sensor is used to capture a sensor image so that the detector can acquire the sensor image, and determine a first position of the object region in the image to be transmitted based on the position of the object region in the sensor image and the positional relationship between the sensor and the detector; and determine a second position of the empty field region based on the first position.

[0084] Sixthly, embodiments of this application provide a detector, including:

[0085] Memory, used to store computer programs;

[0086] When a processor executes a program stored in memory, it implements any of the methods described in the first aspect above.

[0087] Seventhly, embodiments of this application provide a terminal device, including:

[0088] Memory, used to store computer programs;

[0089] When a processor executes a program stored in memory, it implements any of the methods described in the second aspect above.

[0090] Eighthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described in either the first or second aspect above.

[0091] Beneficial effects of the embodiments in this application:

[0092] In the solution provided in this application embodiment, a detector is applied to an image processing system. The image processing system also includes a terminal device. The detector can acquire an image to be transmitted, determine a first position of an object region and a second position of an empty field region in the image to be transmitted. The empty field region is a region in the image to be transmitted where no object exists. Based on the first position, an object image is cropped from the image to be transmitted. Based on the pixel value of the empty field region corresponding to the second position, an empty field index corresponding to the empty field region is calculated. The object image and the empty field index are transmitted to the terminal device so that the terminal device can perform image reconstruction based on the object image and the empty field index to obtain the transmitted image. Since the first position of the object region and the second position of the empty field region in the image to be transmitted can be determined after the image is acquired, the object image can be cropped from the image to be transmitted based on the first position, and the empty field index can be calculated based on the pixel value of the empty field region corresponding to the second position. Then, the object image and the empty field index are transmitted to the terminal device so that the terminal device can perform image reconstruction. This eliminates the need to transmit the entire image; only the object image and the empty field index need to be transmitted to the terminal device, reducing the amount of data transmitted and improving image transmission efficiency. It also eliminates the need for interfaces such as 10 Gigabit Ethernet and dual network ports, and eliminates the need for driver development for these interfaces, reducing the cost and development complexity of image transmission. Of course, implementing any product or method of this application does not necessarily require achieving all of the advantages described above simultaneously. Attached Figure Description

[0093] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other embodiments can be obtained based on these drawings.

[0094] Figure 1 This is a schematic diagram of the structure of an image processing system provided in an embodiment of this application;

[0095] Figure 2 A flowchart illustrating the first image transmission method provided in this application embodiment;

[0096] Figure 3 This is a schematic diagram of an empty field image;

[0097] Figure 4 This is a schematic diagram illustrating the location of the object region and the empty field region provided in an embodiment of this application.

[0098] Figure 5 for Figure 1 A specific flowchart of step S102 in the illustrated embodiment;

[0099] Figure 6 This is a first schematic diagram of the first initial position and the second initial position provided in the embodiments of this application;

[0100] Figure 7 for Figure 5 A specific flowchart of step S504 in the illustrated embodiment;

[0101] Figure 8(a) is a second schematic diagram of the first initial position and the second initial position provided in the embodiments of this application;

[0102] Figure 8(b) is a first schematic diagram of determining the boundary between the first position and the second position according to an embodiment of this application;

[0103] Figure 8(c) is a second schematic diagram of determining the boundary between the first position and the second position according to an embodiment of this application;

[0104] Figure 9 for Figure 1 Another specific flowchart of step S102 in the illustrated embodiment;

[0105] Figure 10 A flowchart illustrating the second image transmission method provided in the embodiments of this application;

[0106] Figure 11 for Figure 10 A specific flowchart of step S1002 in the illustrated embodiment;

[0107] Figure 12 For based on Figure 10 A specific flowchart of determining an empty field image in the illustrated embodiment;

[0108] Figure 13 This is a specific flowchart of an image transmission method provided in an embodiment of this application;

[0109] Figure 14 This is a schematic diagram of the structure of the image transmission method provided in an embodiment of this application;

[0110] Figure 15 This is a schematic diagram of an image transmission method provided in an embodiment of this application;

[0111] Figure 16 This is a schematic diagram of the structure of the first image transmission device provided in the embodiments of this application;

[0112] Figure 17 This is a schematic diagram of the structure of a second image transmission device provided in an embodiment of this application. Detailed Implementation

[0113] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art based on this application are within the scope of protection of this application.

[0114] To reduce the cost and development complexity of image transmission, embodiments of this application provide an image transmission method, apparatus, detector, terminal device, computer-readable storage medium, and computer program product. The first image transmission method provided in this application embodiment will be described below.

[0115] The first image transmission method provided in this application embodiment can be applied to, for example... Figure 1 The image processing system shown includes a detector 101 and a terminal device 102.

[0116] like Figure 2 As shown, an image transmission method includes:

[0117] S201, Acquire the image to be transmitted;

[0118] In the X-ray scanning detection scenario, the image to be transmitted can be an X-ray detection image of the object to be inspected, that is, an image collected by a detector after scanning the object by a radiation source.

[0119] S202, determine the first position of the object region and the second position of the empty field region in the image to be transmitted;

[0120] The empty area refers to the region in the image to be transmitted where no object exists.

[0121] S203, Based on the first position, crop the object image from the image to be transmitted;

[0122] S204, calculate the empty field index corresponding to the empty field area based on the pixel value of the empty field area corresponding to the second position;

[0123] Among them, the empty field index can be used to restore the empty field area in the image during the image reconstruction process.

[0124] S205, the object image and the airspace index are transmitted to the terminal device so that the terminal device can perform image reconstruction based on the object image and the airspace index to obtain the transmitted image.

[0125] As can be seen, in the solution provided in this application embodiment, a detector is applied to the image processing system, and the image processing system also includes a terminal device. The detector can acquire an image to be transmitted, determine a first position of the object region and a second position of the empty field region in the image to be transmitted, wherein the empty field region is a region in the image to be transmitted where no object exists. Based on the first position, an object image is cropped from the image to be transmitted. Based on the pixel value of the empty field region corresponding to the second position, an empty field index corresponding to the empty field region is calculated. The object image and the empty field index are transmitted to the terminal device so that the terminal device can perform image reconstruction based on the object image and the empty field index to obtain the transmitted image. After acquiring the image to be transmitted, the first position of the object region and the second position of the empty field region in the image can be determined. Then, the object image can be cropped from the image to be transmitted based on the first position, and the empty field index can be calculated based on the pixel value of the empty field region corresponding to the second position. Then, the object image and the empty field index are transmitted to the terminal device so that the terminal device can reconstruct the image. In this way, it is not necessary to transmit the entire image, but only the object image and the empty field index need to be transmitted to the terminal device, which can reduce the amount of data transmitted, improve the image transmission efficiency, and eliminate the need to use interfaces such as 10 Gigabit Ethernet and dual network ports, as well as the need to develop interface drivers, thereby reducing the cost and development complexity of image transmission.

[0126] In step S201, the detector can acquire the image to be transmitted. The detector can be a flat panel detector, a linear array detector, etc., and is not specifically limited here.

[0127] For example, in an X-ray scanning detection scenario, the detector can be a flat panel detector. The flat panel detector can perform three types of image correction based on its imaging characteristics, and the image to be transmitted is the corrected image. These three image corrections include Offset correction, Gain correction, and Defect correction. Offset correction addresses the inherent differences between the X-ray detector and the front-end processing unit; Gain correction addresses the differences in the X-ray detector's response to X-rays and the uneven illumination that occurs when X-rays are emitted; and Defect correction addresses the response of individual pixels in the X-ray detector, using algorithms to avoid defective pixels on the detector.

[0128] If the image to be transmitted acquired by the detector does not contain any objects, such as Figure 3 As shown, if the image to be transmitted exhibits uniform snowflake-like spots and its pixel value distribution conforms to the characteristics of Gaussian noise, then this type of image is called an empty-field image. If an object exists in the image to be transmitted, then the pixel value distribution of the area not covered by the object conforms to the characteristics of Gaussian noise, and this is called an empty-field region. During image acquisition, it is rare for an object to completely cover the entire active area of ​​the detector; in most cases, the proportion of the active area occupied by the object is relatively low, meaning that the object area in the image to be transmitted accounts for a low percentage of the entire image. Gaussian noise, also known as white noise or background noise, refers to noise whose pixel value distribution conforms to a normal distribution. For example, Gaussian noise is imaged according to the pattern of the pixels, and the image effect can be as follows: Figure 3 The image effects shown in the image.

[0129] For example, the image to be transmitted acquired by the detector, such as Figure 4 As shown, the image to be transmitted includes a first object region 401 and a second object region 402, which together account for less than 50% of the entire image. If the entire image is transmitted to the terminal device, the areas outside of the first and second object regions 401—the empty areas—will contain no useful information for the receiver, thus affecting the transmission efficiency. Since the pixel values ​​in the empty areas still conform to Gaussian noise characteristics after the image is transmitted to the terminal device, to reduce data transmission volume, only the images corresponding to the object regions and the empty area indicators can be transmitted.

[0130] The detector can then determine the first position of the object region and the second position of the empty field region in the image to be transmitted, i.e., execute step S202. The empty field region is the region in the image to be transmitted where no object exists. There can be one or more object regions, and therefore, the first position can also be one or more; no specific limitation is made here.

[0131] In one implementation, the detector can simultaneously determine a first position of an object region and a second position of an empty field region in the image to be transmitted. In another implementation, the detector can first determine the first position of the object region in the image to be transmitted, and then determine the second position of the empty field region based on the first position. Alternatively, the detector can first determine the second position of the empty field region in the image to be transmitted, and then determine the first position of the object region based on the second position.

[0132] For example, such as Figure 4 As shown, the detector can simultaneously determine the position of the first object region 401 and the second object region 402 in the image to be transmitted, as well as the position of the empty field region. Alternatively, the detector can first determine the position of the first object region 401 and the second object region 402 in the image to be transmitted, and then determine the position of the empty field region based on the positions of the first object region 401 and the second object region 402.

[0133] After determining the first position, the detector can crop the image corresponding to the object region from the image to be transmitted based on the first position to obtain the object image, i.e., execute step S203. In one embodiment, the first position is the location of the edge of the object region, so the boundary of the object image is the edge of the object region. In another embodiment, the first position is the location based on the edge extension of the object region, so the boundary of the object image includes the edge of the object region.

[0134] For example, such as Figure 4 As shown, for the first object region 401, the first position is the position 403 of the edge of the first object region 401. Therefore, the boundary of the object image cropped by the detector from the image to be transmitted is the edge of the first object region 401. For the second object region 402, the first position is the position 404 based on the edge extension of the second object region 402. Therefore, the boundary of the object image cropped by the detector from the image to be transmitted includes the edge of the second object region 402.

[0135] After the detector determines the second location of the empty field region, in step S204, the empty field index corresponding to the empty field region can be calculated based on the pixel values ​​of the empty field region corresponding to the second location. As one implementation, the empty field index includes at least one of the following: the mean, standard deviation, maximum, minimum, median, percentage of pixels within a preset multiple of the standard deviation of the mean, noise, and uniformity. That is, there can be one or more empty field indices. The empty field index can also be a parameter related to the actual scene, which is also reasonable.

[0136] For example, such as Figure 4As shown, the detector determines the location of the empty field region as the location of the first object region 401 and the location of the second object region 402. In this way, the detector can calculate the mean, standard deviation, maximum value, minimum value, median, proportion of pixels within 6 times the standard deviation of the mean, noise, and uniformity of the empty field region based on the pixel value of the empty field region corresponding to the location, as empty field indicators.

[0137] In step S205, the detector can transmit the object image and airspace indicators to the terminal device. After receiving the object image and airspace indicators, the terminal device can reconstruct the image based on the object image and airspace indicators to obtain the transmitted image. The physical form of the data link for transmitting the object image and airspace indicators can be wired, wireless, gigabit network, 10 gigabit network, etc., and is not specifically limited here.

[0138] For example, such as Figure 4 As shown, after the detector crops the image corresponding to the first object region 401 and the image corresponding to the second object region 402 from the image to be transmitted, and calculates the air field index corresponding to the air field region, namely mean, standard deviation, maximum value, minimum value, median, percentage of pixels within 6 times the standard deviation of the mean, noise, and uniformity, the two object images and the air field index can be transmitted to the terminal device through a gigabit network. In this way, the terminal device can perform image reconstruction based on the two object images and the air field index to obtain the transmitted image.

[0139] As one implementation method, in order to further reduce the amount of data transmitted, the detector can compress the object image to obtain a compressed object image, and then transmit the compressed object image and the air field index to the terminal device.

[0140] In this embodiment, after acquiring the image to be transmitted, the first position of the object region and the second position of the empty field region in the image to be transmitted can be determined. Then, the object image can be cropped from the image to be transmitted based on the first position, and the empty field index can be calculated based on the pixel value of the empty field region corresponding to the second position. Then, the object image and the empty field index are transmitted to the terminal device so that the terminal device can perform image reconstruction. In this way, it is not necessary to transmit the entire image, but only the object image and the empty field index need to be transmitted to the terminal device, which can reduce the amount of data transmitted, improve the image transmission efficiency, and eliminate the need to use interfaces such as 10 Gigabit Ethernet and dual network ports, as well as the need to develop interface drivers, thereby reducing the cost and development complexity of image transmission.

[0141] Especially for detectors that have just exceeded their bandwidth requirements, the elimination of the need for a 10 Gigabit Ethernet network improves image transmission efficiency, thereby reducing the bandwidth requirements of the data link. Furthermore, at the same image transmission frame rate, reducing the amount of data transmitted lowers data link utilization and reduces detector power consumption.

[0142] As one implementation method of this application, such as Figure 5 As shown, the steps described above for determining the first position of the object region and the second position of the empty field region in the image to be transmitted may include:

[0143] S501, an object recognition algorithm is used to identify the object region in the image to be transmitted, and the first initial position of the object region is obtained;

[0144] S502, an empty field recognition algorithm is used to identify the empty field region in the image to be transmitted, and the second initial position of the empty field region is obtained;

[0145] In order to determine the first position of the object region and the second position of the empty field region, the detector can use different recognition methods to first determine the first initial position of the object region and the second initial position of the empty field region respectively, and then further determine the first position of the object region and the second position of the empty field region based on the obtained first initial position and second initial position.

[0146] In one implementation, the detector can employ an object recognition algorithm to identify object regions in the transmitted image and obtain the first initial position of the object regions. The object recognition algorithm can be SIFT (Scale-Invariant Feature Transform) / SURF (Speeded-Up Robust Features), Haar features, generalized Hough transform, object detection algorithms, etc., and is not specifically limited here.

[0147] In one implementation, the detector can identify the empty field region in the transmitted image based on the image characteristics corresponding to the empty field region, thereby obtaining the second initial position of the empty field region. Since the empty field region appears as uniform snowflake spots, which conforms to the characteristics of Gaussian noise, the image characteristics at least include the fact that the pixel values ​​of the image satisfy the characteristics of Gaussian noise.

[0148] For example, such as Figure 4As shown, the detector can identify the first object region 401 and the second object region 402 in the image to be transmitted based on object edge features using a target edge detection algorithm, thereby obtaining the first initial position of the first object region 401 and the first initial position of the second object region 402. Furthermore, based on the characteristic that the pixel values ​​of the image satisfy Gaussian noise, the detector identifies empty areas in the image to be transmitted, thereby obtaining the second initial position of the empty areas.

[0149] S503, compare the first initial position and the second initial position to obtain the comparison result;

[0150] S504, the first initial position is adjusted according to the comparison result to obtain the first position of the object region, and the second initial position is adjusted according to the comparison result to obtain the second position of the empty field region.

[0151] Because the detector uses different recognition algorithms to identify the object region and the empty field region, the boundaries of the first initial position and the second initial position may not coincide. Therefore, the first initial position and the second initial position can be compared to obtain the comparison result. Then, the first initial position can be adjusted according to the comparison result to obtain the first position of the object region, and the second initial position can be adjusted according to the comparison result to obtain the second position of the empty field region. The detector may identify multiple object regions, thus resulting in multiple first positions.

[0152] In this embodiment, the first initial position is used to characterize the location of an object region in the image to be transmitted, and the second initial position is used to characterize the location of an empty region without objects in the image to be transmitted. During the process of comparing the first and second initial positions and adjusting them based on the comparison result, the first and second initial positions can specifically be location information indicating that the object region and the empty region may overlap or be close in location. Further exemplarily, the first and second initial positions can be region contour information used to characterize the locations of the object region and the empty region in the image to be transmitted, respectively.

[0153] In one implementation, based on the comparison results and the actual scenario, the recognition results of identifying the object region in the image to be transmitted using the object recognition algorithm can be adjusted to the recognition results of identifying the empty field region in the image to be transmitted using the empty field recognition algorithm, or the recognition results of identifying the empty field region in the image to be transmitted using the empty field recognition algorithm can be adjusted to the recognition results of identifying the object region in the image to be transmitted using the object recognition algorithm.

[0154] In other words, the detector can use the obtained first initial position as the first position of the object region based on the comparison results and reasonable requirements in the actual scene, and then adjust the second initial position based on the first position to obtain the second position of the empty field region. Alternatively, it can use the obtained second initial position as the second position of the empty field region based on the comparison results and reasonable requirements in the actual scene, and then adjust the first initial position based on the second position to obtain the first position of the object region.

[0155] For example, such as Figure 6 As shown, the first initial position 601 is (0, 0; 1000, 1000), and the second initial position 602 is (0, 1100; 1100, 0; 1100, 1100). Thus, the boundary of the first initial position 601 does not coincide with the boundary of the second initial position 602, requiring adjustment of both. The detector can use the first initial position 601 as a reference, determining it as the first position of the object region. Then, based on this first position, the second initial position 602 is adjusted to obtain the second position of the empty field region, i.e., (0, 1000; 1000, 0; 1000, 1000).

[0156] As can be seen, in this embodiment, after obtaining the first initial position of the object region and the second initial position of the empty field region, the detector can compare the first and second initial positions to obtain a comparison result. Then, based on the comparison result, the first initial position is adjusted to obtain the first position of the object region, and the second initial position is adjusted based on the comparison result to obtain the second position of the empty field region. This makes the obtained first and second positions more accurate, allowing for the cropping of an accurate object image based on the first position, and the calculation of reasonable empty field indices based on the empty field region corresponding to the second position.

[0157] As one implementation method of this application, such as Figure 7 As shown, the steps described above, adjusting the first initial position according to the comparison result to obtain the first position of the object region, and adjusting the second initial position according to the comparison result to obtain the second position of the empty field region, may include:

[0158] S701, determine the first and second boundaries of the position deviation within the preset deviation range based on the comparison results;

[0159] Wherein, the first boundary is the boundary represented by the first initial position, and the second boundary is the boundary represented by the second initial position;

[0160] S702, for the first boundary and the second boundary, calculate the average position of the first boundary and the second boundary, and use it as the boundary between the object region and the empty field region to obtain the first position of the object region and the second position of the empty field region.

[0161] After comparing the first initial position and the second initial position, the detector may obtain multiple comparison results, such as... Figure 6 As shown in Figure 8(a), the boundary represented by the first initial position 601 and the boundary represented by the second initial position 602 are a certain distance apart. As shown in Figure 8(a), the first initial position 801 and the second initial position 802 have an overlapping part. When the difference between the boundary represented by the first initial position and the boundary represented by the second initial position is within a certain range, the boundary between the object region and the empty field region can be redefined. Then, the first initial position and the second initial position can be adjusted according to the determined boundary to obtain the first position of the object region and the second position of the empty field region.

[0162] In one implementation, the detector can determine a first boundary and a second boundary within a preset deviation range based on the comparison results. The first boundary is the boundary represented by a first initial position, and the second boundary is the boundary represented by a second initial position. For both the first and second boundaries, the average position of the first and second boundaries is calculated as the boundary between the object region and the empty field region, thus obtaining the first position of the object region and the second position of the empty field region. The determination of the position deviation can be achieved by calculating the difference between the preset positions of the first and second boundaries, such as calculating the difference between the midpoints of the upper boundaries of the first and second boundaries, or calculating the difference between the midpoints of the lower boundaries of the first and second boundaries, etc., without specific limitations.

[0163] In another implementation, when the first boundary exceeds the second boundary or the second boundary exceeds the first boundary, the position of the outer boundary can be taken as the boundary between the object region and the empty field region, thereby obtaining the first position of the object region and the second position of the empty field region.

[0164] For example, as shown in Figure 8(a), the first initial position 801 and the second initial position 802 have an overlapping portion. The detector can determine the first boundary and the second boundary, which are within a preset deviation range, based on the comparison result of the first initial position 801 and the second initial position 802. As shown in Figure 8(b), the detector can calculate the average position 803 of the first boundary and the second boundary for the first boundary and the second boundary, as the boundary between the object region and the empty field region, and thus obtain the first position of the object region and the second position of the empty field region.

[0165] As shown in Figure 8(c), the detector can also take the outer position 804 of the first boundary and the second boundary as the boundary between the object region and the empty field region, thereby obtaining the first position of the object region and the second position of the empty field region.

[0166] As can be seen, in this embodiment, the detector can determine the first boundary and the second boundary, which are within a preset deviation range, based on the comparison results. For the first and second boundaries, the average position of the first and second boundaries is calculated as the boundary between the object region and the empty field region, thus obtaining the first position of the object region and the second position of the empty field region. This makes the obtained first and second positions more accurate, allowing for the cropping of an accurate object image based on the first position, and the calculation of reasonable empty field indices based on the empty field region corresponding to the second position.

[0167] As one embodiment of this application, the above-described image processing system may further include a sensor, which may be a laser, infrared light, visible light, radar, ultrasonic sensor, etc., which are different in principle from the detector that acquires the image to be transmitted, and are not specifically limited here.

[0168] like Figure 9 As shown, the steps described above for determining the first position of the object region and the second position of the empty field region in the image to be transmitted may include:

[0169] S901, acquire the sensor image captured by the sensor;

[0170] S902, determine the first position of the object region in the image to be transmitted based on the position of the object region in the sensor image and the positional relationship between the sensor and the detector;

[0171] S903, based on the first position, determine the second position of the open area.

[0172] To determine the location of both the object region and the empty field region, sensors can be installed in the image transmission system in a real-world scenario. The positions of the sensors and detectors are related. While the detector acquires the image to be transmitted, the sensor captures an image. Based on the location of the object region in the sensor image and the positional relationship between the sensor and detector, the detector can determine the first location of the object region in the image to be transmitted, and then, based on the first location, determine the second location of the empty field region.

[0173] In one implementation, the positional relationship between the sensor and the detector can reflect the mapping relationship of the coordinate system, so that the detector can determine the first position of the object region in the transmitted image based on the position of the object region in the sensor image.

[0174] For example, the sensor is a visible light sensor that captures an optical image of object A. After the detector acquires the optical image of object A, it can determine the position of the area of ​​object A. Then, based on the position of the area of ​​object A and the positional relationship between the visible light sensor and the detector, the first position of the area of ​​object A in the image to be transmitted can be determined, and then based on the first position, the second position of the empty field area can be determined.

[0175] As can be seen, in this embodiment, the detector can acquire sensor images captured by the sensor, determine the first position of the object region in the image to be transmitted based on the position of the object region in the sensor image and the positional relationship between the sensor and the detector, and then determine the second position of the empty field region based on the first position. In this way, the sensor can accurately determine the first position of the object region, and then determine the second position of the empty field region based on the first position. Then, an accurate object image can be obtained by cropping based on the first position, and a reasonable empty field index can be calculated based on the empty field region corresponding to the second position.

[0176] Corresponding to the first image transmission method described above, this application embodiment also provides another image transmission method. The second image transmission method provided in this application embodiment can be applied to, for example... Figure 1 The image processing system shown includes a terminal device 102, and the image processing system also includes a detector 101.

[0177] like Figure 10 As shown, an image transmission method includes:

[0178] S1001, Receive the object image and airspace index transmitted by the detector;

[0179] The object image is obtained by cropping the object region in the image to be transmitted, and the empty field index is calculated based on the pixel value of the empty field region in the image to be transmitted.

[0180] S1002, based on the object image and the airspace index, image reconstruction is performed to obtain the transmitted image.

[0181] As can be seen, in the solution provided in this application embodiment, a terminal device is applied to the image processing system. The image processing system also includes a detector. The terminal device can receive the object image and the airspace index transmitted by the detector. The object image is obtained by cropping the object region from the first position in the image to be transmitted, and the airspace index is calculated based on the pixel values ​​of the airspace region in the image to be transmitted. Image reconstruction is performed based on the object image and the airspace index to obtain the transmitted image. Since the object image is obtained by cropping the object region from the first position in the image to be transmitted, and the airspace index is calculated based on the pixel values ​​of the airspace region in the image to be transmitted, image reconstruction can be performed after receiving the object image and the airspace index to obtain the transmitted image. In this way, the detector does not need to transmit the entire image; only the object image and the airspace index need to be transmitted to the terminal device. This reduces the amount of data transmitted, improves image transmission efficiency, eliminates the need for interfaces such as 10 Gigabit Ethernet and dual network ports, and eliminates the need for driver development for the interfaces, thus reducing the cost and development complexity of image transmission.

[0182] In step S1001, the terminal device can receive the object image and the empty field index transmitted by the detector. The object image is obtained by cropping a first position of the object region in the image to be transmitted, and the empty field index is calculated based on the pixel values ​​of the empty field region in the image to be transmitted. The empty field index includes at least one of the following: the mean, standard deviation, maximum, minimum, median, percentage of pixels within a preset multiple of the mean standard deviation, noise, and uniformity. That is, there can be one or more empty field indices. The empty field index can also be a parameter related to the actual scene, which is also reasonable.

[0183] For example, the terminal device receives an image of an object transmitted by the detector, such as Figure 4 As shown, the images corresponding to the first object region 401 and the second object region 402 are shown. The empty field index is the mean, standard deviation, maximum value, minimum value, median, proportion of pixels within 6 times the standard deviation of the mean, noise, and uniformity, which are calculated based on the pixel values ​​of the empty field region.

[0184] After the terminal device receives the object image and the airspace index, it can perform image reconstruction based on the object image and the airspace index to obtain the transmitted image, i.e., execute step S1002. For example, following the example in step S1001 above, the terminal device can perform image reconstruction based on the image corresponding to the first object region 401 and the image corresponding to the second object region 402, as well as the mean, standard deviation, maximum value, minimum value, median, the proportion of pixels within 6 times the standard deviation of the mean, noise, and uniformity, to obtain the transmitted image, i.e., as shown. Figure 4 The image shown.

[0185] In this embodiment, since the object image is cropped from the first position of the object region in the image to be transmitted, and the empty field index is calculated based on the pixel values ​​of the empty field region in the image to be transmitted, image reconstruction can be performed based on the object image and the empty field index after receiving them to obtain the transmitted image. This eliminates the need for the detector to transmit the entire image; only the object image and the empty field index need to be transmitted to the terminal device. This reduces the amount of data transmitted, improves image transmission efficiency, and eliminates the need for interfaces such as 10 Gigabit Ethernet or dual network ports, as well as the need to develop interface drivers, thus reducing the cost and development complexity of image transmission.

[0186] As one implementation method of this application, such as Figure 11 As shown, the steps described above for image reconstruction based on the object image and the airspace index to obtain the transmitted image may include:

[0187] S1101, The object image is filled into a preset blank image according to the first position to obtain a first image;

[0188] The size of the preset blank image is the same as the size of the image to be transmitted.

[0189] S1102, Reconstruct the air field image based on the air field index to obtain the second image;

[0190] The second image is the same size as the image to be transmitted.

[0191] S1103, Based on the first position, remove the region corresponding to the object region in the second image to obtain an empty field image;

[0192] S1104, the first image is superimposed with the empty field image to obtain the transmitted image.

[0193] After receiving the object image and the airspace index, the terminal device can first reconstruct the airspace image based on the airspace index to obtain an airspace image. Then, the airspace image is superimposed on the object image to obtain a complete transmitted image. However, if the reconstructed airspace image is directly superimposed on the object image, the object region in the transmitted image will have low resolution because the corresponding regions of the object region in the object image are superimposed on the airspace image. Therefore, the terminal device can remove the regions corresponding to the object region in the reconstructed airspace image, and then superimpose the processed airspace image on the object image to obtain a clear transmitted image.

[0194] In one implementation, the terminal device can fill a preset blank image with an object image at a first position to obtain a first image; that is, the object region is reconstructed in the preset blank image to obtain an image covered with the object. The size of the preset blank image is the same as the size of the image to be transmitted. The terminal device then reconstructs the blank image based on a blank field index to obtain a second image. The pixel values ​​of the second image satisfy the characteristics of Gaussian noise, and may appear as uniform snowflake-like spots. The size of the second image is the same as the size of the image to be transmitted.

[0195] After obtaining the second image, the terminal device can remove the area corresponding to the object region in the second image based on the first position to obtain an empty field image, and then superimpose the first image and the empty field image to obtain the transmitted image.

[0196] For example, terminal devices can... Figure 4 The images corresponding to the first object region 401 and the second object region 402 shown are filled into a blank image of the same size as the image to be transmitted to obtain the first image. The blank image is then reconstructed based on the blank field index to obtain the image shown below. Figure 3 The second image shown is the same size as the image to be transmitted. Based on the positions of the first object region 401 and the second object region 402, the regions corresponding to the object regions in the second image are removed to obtain an empty field image. Then, the first image and the empty field image are superimposed to obtain the image shown. Figure 4 The image shown.

[0197] As can be seen, in this embodiment, the terminal device can fill a preset blank image with an object image according to a first position to obtain a first image, reconstruct the blank image according to the blank field index to obtain a second image, remove the region corresponding to the object area in the second image based on the first position to obtain a blank field image, and then superimpose the first image and the blank field image to obtain the transmitted image. In this way, by removing the region corresponding to the object area in the second image based on the first position to obtain a blank field image, and then superimposing the blank field image with the first image, the object area in the transmitted image can be made clearer.

[0198] As one implementation method of this application, such as Figure 12 As shown, before the step of superimposing the first image with the empty field image to obtain the transmitted image, the above method may further include:

[0199] S1201, Based on the pixel values ​​of the empty field image, calculate the empty field index of the empty field image, and use it as the reconstructed empty field index.

[0200] S1202, Calculate the difference between the reconstructed airfield index and the airfield index transmitted by the detector;

[0201] S1203, if the difference is not within the preset difference range, adjust the pixel values ​​of the empty field image to obtain the adjusted image;

[0202] S1204, the adjusted image is used as an empty field image, and the step of calculating the empty field index of the empty field image based on the pixel value of the empty field image as a reconstruction of the empty field index is returned until the difference is within the preset difference range.

[0203] Since there may be multiple or only one empty field index, the fewer the empty field indexes, the greater the difference between the empty field index of the reconstructed empty field image and the empty field index transmitted by the detector, and the less the pixel values ​​corresponding to the empty field region in the image to be transmitted will be.

[0204] In one implementation, the terminal device can calculate the spatial index of the spatial image based on the pixel values ​​of the spatial image, and use it as the reconstructed spatial index. Then, it calculates the difference between the reconstructed spatial index and the spatial index transmitted by the detector. If the difference is not within a preset difference range, it indicates that the difference between the reconstructed spatial index and the spatial index transmitted by the detector is large. The pixel values ​​of the spatial image can be adjusted to obtain an adjusted image. The adjusted image is then used as the spatial image, and the spatial index of the spatial image is recalculated based on the pixel values ​​of the spatial image, and used as the reconstructed spatial index. The difference between the reconstructed spatial index and the spatial index transmitted by the detector is calculated until the difference is within a preset difference range.

[0205] For example, the terminal device receives the airfield index as mean 1, standard deviation 1, maximum value 1, minimum value 1, and median 1. After reconstructing the image based on the airfield index and removing object regions, an airfield image is obtained. Based on the pixel values ​​of this airfield image, the airfield index of the airfield image is calculated, namely mean 2, standard deviation 2, maximum value 2, minimum value 2, and median 2, which are used as the reconstructed airfield index. Then, the difference between the mean 2, standard deviation 2, maximum value 2, minimum value 2, and median 2 and the mean 1, standard deviation 1, maximum value 1, minimum value 1, and median 1 transmitted by the detector is calculated.

[0206] If the differences are not within the preset difference range, it means that the difference between the reconstructed field index and the field index transmitted by the detector is large. The pixel values ​​of the field image can be adjusted to obtain the adjusted image. The field index is then recalculated based on the pixel values ​​of the adjusted image until the difference between the field index of the adjusted image and the field index transmitted by the detector is within the preset difference range.

[0207] As can be seen, in this embodiment, the terminal device can calculate the spatial index of the spatial image based on the pixel values ​​of the spatial image, and use it as the reconstructed spatial index. It then calculates the difference between the reconstructed spatial index and the spatial index transmitted by the detector. If the difference is not within a preset range, the pixel values ​​of the spatial image are adjusted to obtain an adjusted image. This adjusted image is then used as the spatial image, and the process of calculating the spatial index based on the pixel values ​​of the spatial image and using it as the reconstructed spatial index is repeated until the difference is within the preset range. This ensures that the difference between the spatial index of the spatial image and the spatial index transmitted by the detector is within the preset range, making the pixel values ​​of the spatial region close to the corresponding pixel values ​​of the spatial region in the image to be transmitted.

[0208] Figure 13 This is a specific flowchart of an image transmission method provided in an embodiment of this application. Figure 14 This is a schematic diagram of a detector provided in an embodiment of this application. Figure 14 As shown, the traditional image transmission mode involves directly transmitting the image to the data transmission module after the image module to be transmitted has acquired the image. The following section will combine... Figure 13 as well as Figure 14 The image transmission method provided in the embodiments of this application will be described by way of example.

[0209] like Figure 14 As shown, the detector may include an algorithm module and an image processing module. Specifically, it includes a module for acquiring images, an object recognition algorithm module, an empty field recognition algorithm module, an arbitrator, an empty field index statistics module, an image segmentation module, a data packaging module, and a data transmission module. The module for acquiring images is used to acquire images; the object recognition algorithm module is used to determine the location of object regions in the image; the empty field recognition algorithm module is used to determine the location of empty field regions in the image; the arbitrator is used to adjust the positions of the object regions and the empty field regions; the empty field index statistics module is used to calculate the empty field index corresponding to the empty field region; the image segmentation module is used to crop the object image from the image; the data packaging module is used to package the object image and the empty field index; and the data transmission module is used to transmit the packaged data to the terminal device.

[0210] like Figure 13 As shown, the image transmission method provided in this application embodiment may include the following steps:

[0211] S1301, Flat panel detector acquires images;

[0212] Flat panel detectors can acquire images, which are then transmitted. These images include both object areas and empty areas. For example, such as... Figure 15As shown, the flat panel detector 1501 acquires the image 1502 to be transmitted, and the original image acquired by the flat panel detector 1501 is 18M, that is, the image 1502 to be transmitted is 18M.

[0213] S1302, the algorithm identifies the location of object regions in the image;

[0214] like Figure 15 As shown, the flat panel detector 1501 can use an object recognition algorithm to identify the position of the object region in the image, and obtain the position of the object region as (0, 0; 1536, 1536).

[0215] S1303, the algorithm identifies the location of empty areas in the image and calculates the empty area index;

[0216] Flat panel detectors can use an empty field recognition algorithm to identify the location of empty field regions in an image. Then, they compare the location of the object region with the location of the empty field region, obtain the comparison result, and adjust the locations of the object region and the empty field region accordingly to obtain the adjusted locations. For example... Figure 15 As shown, the flat panel detector can crop the object image 1503 from the image to be transmitted based on the position of the adjusted object region. Based on the pixel values ​​of the empty field region after the position is adjusted, the empty field region indices x, y, and z, such as mean, maximum, and minimum values, are calculated.

[0217] S1304, transmits object images and airspace indicators;

[0218] Flat panel detectors can transmit object images and airspace indicators to terminal devices, such as... Figure 15 As shown, the flat panel detector 1501 can transmit object image 1503 and empty area indicators x, y, z to terminal device 1504. The position of the object area is (0, 0; 1536, 1536), and the object image 1503 transmitted to the PC is 4.5M.

[0219] S1305, the terminal device reconstructs the image based on the object image and the airspace index;

[0220] like Figure 15 As shown, after receiving the object image 1503 and the airspace index, the terminal device 1504 can perform image reconstruction based on the object image 1503 and the airspace index.

[0221] S1306, obtain the image transmitted by the flat panel detector.

[0222] like Figure 15As shown, after reconstructing the image on the PC, the transmitted image 1505 can be obtained. This reconstructed image is consistent with the image acquired by the flat panel detector, which does not affect its use, while its transmission bandwidth is reduced to 1 / 4 of the previous one, improving image transmission efficiency and reducing image transmission costs and development complexity.

[0223] As can be seen, in the solution provided in this application embodiment, a detector is applied to the image processing system, and the image processing system also includes a terminal device. The detector can acquire an image to be transmitted, determine a first position of the object region and a second position of the empty field region in the image to be transmitted, wherein the empty field region is a region in the image to be transmitted where no object exists. Based on the first position, an object image is cropped from the image to be transmitted. Based on the pixel value of the empty field region corresponding to the second position, an empty field index corresponding to the empty field region is calculated. The object image and the empty field index are transmitted to the terminal device so that the terminal device can perform image reconstruction based on the object image and the empty field index to obtain the transmitted image. After acquiring the image to be transmitted, the first position of the object region and the second position of the empty field region in the image can be determined. Then, the object image can be cropped from the image to be transmitted based on the first position, and the empty field index can be calculated based on the pixel value of the empty field region corresponding to the second position. Then, the object image and the empty field index are transmitted to the terminal device so that the terminal device can reconstruct the image. In this way, it is not necessary to transmit the entire image, but only the object image and the empty field index need to be transmitted to the terminal device, which can reduce the amount of data transmitted, improve the image transmission efficiency, and eliminate the need to use interfaces such as 10 Gigabit Ethernet and dual network ports, as well as the need to develop interface drivers, thereby reducing the cost and development complexity of image transmission.

[0224] Corresponding to the first image transmission method described above, this application also provides a first image transmission device, which will be described below.

[0225] like Figure 16 As shown, a detector is applied in an image processing system, which further includes a terminal device. The device includes:

[0226] Image acquisition module 1610 is used to acquire images to be transmitted.

[0227] The position determination module 1620 is used to determine a first position of an object region and a second position of an empty field region in the image to be transmitted, wherein the empty field region is a region in the image to be transmitted where no object exists;

[0228] The object image cropping module 1630 is used to crop an object image from the image to be transmitted based on the first position;

[0229] The empty field index calculation module 1640 is used to calculate the empty field index corresponding to the empty field area based on the pixel value of the empty field area corresponding to the second position.

[0230] The image and indicator transmission module 1650 is used to transmit the object image and the airspace indicator to the terminal device, so that the terminal device can perform image reconstruction based on the object image and the airspace indicator to obtain the transmitted image.

[0231] As can be seen, in the solution provided in this application embodiment, a detector is applied to the image processing system, and the image processing system also includes a terminal device. The detector can acquire an image to be transmitted, determine a first position of the object region and a second position of the empty field region in the image to be transmitted, wherein the empty field region is a region in the image to be transmitted where no object exists. Based on the first position, an object image is cropped from the image to be transmitted. Based on the pixel value of the empty field region corresponding to the second position, an empty field index corresponding to the empty field region is calculated. The object image and the empty field index are transmitted to the terminal device so that the terminal device can perform image reconstruction based on the object image and the empty field index to obtain the transmitted image. After acquiring the image to be transmitted, the first position of the object region and the second position of the empty field region in the image can be determined. Then, the object image can be cropped from the image to be transmitted based on the first position, and the empty field index can be calculated based on the pixel value of the empty field region corresponding to the second position. Then, the object image and the empty field index are transmitted to the terminal device so that the terminal device can reconstruct the image. In this way, it is not necessary to transmit the entire image, but only the object image and the empty field index need to be transmitted to the terminal device, which can reduce the amount of data transmitted, improve the image transmission efficiency, and eliminate the need to use interfaces such as 10 Gigabit Ethernet and dual network ports, as well as the need to develop interface drivers, thereby reducing the cost and development complexity of image transmission.

[0232] As one embodiment of this application, the position determination module 1620 may include:

[0233] The first initial position acquisition submodule is used to identify the object region in the image to be transmitted using an object recognition algorithm, and obtain the first initial position of the object region;

[0234] The second initial position acquisition submodule is used to identify the empty field region in the image to be transmitted using an empty field recognition algorithm, and obtain the second initial position of the empty field region.

[0235] The comparison result acquisition submodule is used to compare the first initial position and the second initial position to obtain the comparison result;

[0236] The location acquisition submodule is used to adjust the first initial position according to the comparison result to obtain the first position of the object region, and to adjust the second initial position according to the comparison result to obtain the second position of the empty field region.

[0237] As one embodiment of this application, the above-mentioned second initial position acquisition submodule may include:

[0238] The second initial position acquisition unit identifies the empty field region in the image to be transmitted based on the image characteristics corresponding to the empty field region, and obtains the second initial position of the empty field region. The image characteristics include at least the feature that the pixel values ​​of the image satisfy Gaussian noise.

[0239] As one embodiment of this application, the aforementioned location acquisition submodule may include:

[0240] A boundary determination unit is used to determine a first boundary and a second boundary within a preset deviation range based on the comparison result, wherein the first boundary is the boundary represented by the first initial position and the second boundary is the boundary represented by the second initial position.

[0241] The position acquisition unit is used to calculate the average position of the first boundary and the second boundary for the first boundary and the second boundary, and use it as the boundary between the object region and the empty field region to obtain the first position of the object region and the second position of the empty field region.

[0242] As one embodiment of this application, the image processing system described above may further include a sensor;

[0243] The aforementioned position determination module 1620 may include:

[0244] The sensor image determination submodule is used to acquire sensor images captured by the sensor;

[0245] The first position determination submodule is used to determine the first position of the object region in the image to be transmitted based on the position of the object region in the sensor image and the positional relationship between the sensor and the detector.

[0246] The second position determination submodule is used to determine the second position of the open area based on the first position.

[0247] As one embodiment of this application, the above-described apparatus may further include:

[0248] The compressed object image acquisition module is used to compress the object image before the step of transmitting the object image and the airspace index to the terminal device, so as to obtain a compressed object image.

[0249] As one embodiment of this application, the above-mentioned empty field index includes at least one of the following: mean, standard deviation, maximum, minimum, median, percentage of pixels within a preset multiple of the mean standard deviation, noise, and uniformity.

[0250] Corresponding to the second image transmission method described above, this application also provides a second image transmission device, which will be described below.

[0251] like Figure 17 As shown, an image transmission device is applied to a terminal device in an image processing system, the image processing system further including a detector, the device comprising:

[0252] The image and index receiving module 1710 is used to receive the object image and the empty field index transmitted by the detector, wherein the object image is obtained by cropping the object region in the image to be transmitted, and the empty field index is calculated based on the pixel value of the empty field region in the image to be transmitted.

[0253] The image acquisition module 1720 is used to reconstruct the image based on the object image and the airspace index to obtain the transmitted image.

[0254] As can be seen, in the solution provided in this application embodiment, a terminal device is applied to the image processing system. The image processing system also includes a detector. The terminal device can receive the object image and the airspace index transmitted by the detector. The object image is obtained by cropping the object region from the first position in the image to be transmitted, and the airspace index is calculated based on the pixel values ​​of the airspace region in the image to be transmitted. Image reconstruction is performed based on the object image and the airspace index to obtain the transmitted image. Since the object image is obtained by cropping the object region from the first position in the image to be transmitted, and the airspace index is calculated based on the pixel values ​​of the airspace region in the image to be transmitted, image reconstruction can be performed after receiving the object image and the airspace index to obtain the transmitted image. In this way, the detector does not need to transmit the entire image; only the object image and the airspace index need to be transmitted to the terminal device. This reduces the amount of data transmitted, improves image transmission efficiency, eliminates the need for interfaces such as 10 Gigabit Ethernet and dual network ports, and eliminates the need for driver development for the interfaces, thus reducing the cost and development complexity of image transmission.

[0255] As one embodiment of this application, the above-described image acquisition module 1720 may include:

[0256] The first image acquisition submodule is used to fill the object image into a preset blank image according to the first position to obtain a first image, wherein the size of the preset blank image is the same as the size of the image to be transmitted;

[0257] The second image acquisition submodule is used to reconstruct the air field image based on the air field index to obtain a second image, wherein the size of the second image is the same as the size of the image to be transmitted;

[0258] The empty field image acquisition submodule is used to remove the region corresponding to the object region in the second image based on the first position to obtain an empty field image;

[0259] The image acquisition submodule is used to overlay the first image with the empty field image to obtain the transmitted image.

[0260] As one embodiment of this application, the above-described apparatus may further include:

[0261] The reconstruction void field index calculation module is used to calculate the void field index of the void field image based on the pixel value of the void field image before the step of superimposing the first image with the void field image to obtain the transmitted image, and use it as the reconstruction void field index.

[0262] The difference calculation module is used to calculate the difference between the reconstructed airfield index and the airfield index transmitted by the detector.

[0263] The image acquisition module is adjusted to adjust the pixel values ​​of the empty field image if the difference is not within a preset difference range, so as to obtain an adjusted image.

[0264] The index calculation and return module is used to take the adjusted image as an empty field image and return the empty field index of the empty field image calculated based on the pixel value of the empty field image as a step of reconstructing the empty field index, until the difference is within the preset difference range.

[0265] This application also provides an image processing system, such as... Figure 1 As shown, the system includes a detector 101 and a terminal device 102, wherein:

[0266] The detector 101 is used to acquire an image to be transmitted; determine a first position of an object region and a second position of an empty field region in the image to be transmitted; crop an object image from the image to be transmitted based on the first position; calculate an empty field index corresponding to the empty field region based on the pixel value of the empty field region corresponding to the second position; and transmit the object image and the empty field index to the terminal device so that the terminal device can perform image reconstruction based on the object image and the empty field index to obtain the transmitted image; wherein, the empty field region is a region in the image to be transmitted where no object exists.

[0267] The terminal device 102 is used to receive the object image and the air field index transmitted by the detector, and to perform image reconstruction based on the object image and the air field index to obtain the transmitted image; wherein, the object image is obtained by cropping the object region in the image to be transmitted, and the air field index is calculated based on the pixel value of the air field region in the image to be transmitted.

[0268] As can be seen, in the solution provided in this application embodiment, a detector is applied to the image processing system, and the image processing system also includes a terminal device. The detector can acquire an image to be transmitted, determine a first position of the object region and a second position of the empty field region in the image to be transmitted, wherein the empty field region is a region in the image to be transmitted where no object exists. Based on the first position, an object image is cropped from the image to be transmitted. Based on the pixel value of the empty field region corresponding to the second position, an empty field index corresponding to the empty field region is calculated. The object image and the empty field index are transmitted to the terminal device so that the terminal device can perform image reconstruction based on the object image and the empty field index to obtain the transmitted image. After acquiring the image to be transmitted, the first position of the object region and the second position of the empty field region in the image can be determined. Then, the object image can be cropped from the image to be transmitted based on the first position, and the empty field index can be calculated based on the pixel value of the empty field region corresponding to the second position. Then, the object image and the empty field index are transmitted to the terminal device so that the terminal device can reconstruct the image. In this way, it is not necessary to transmit the entire image, but only the object image and the empty field index need to be transmitted to the terminal device, which can reduce the amount of data transmitted, improve the image transmission efficiency, and eliminate the need to use interfaces such as 10 Gigabit Ethernet and dual network ports, as well as the need to develop interface drivers, thereby reducing the cost and development complexity of image transmission.

[0269] As one embodiment of this application, the above system further includes a sensor, wherein:

[0270] The sensor is used to capture a sensor image so that the detector can acquire the sensor image, and determine a first position of the object region in the image to be transmitted based on the position of the object region in the sensor image and the positional relationship between the sensor and the detector; and determine a second position of the empty field region based on the first position.

[0271] This application also provides a detector, including:

[0272] Memory, used to store computer programs;

[0273] When the processor executes the program stored in the memory, it implements the steps of the first image transmission method described in any of the above embodiments.

[0274] Furthermore, the aforementioned detector may also include a communication bus and / or a communication interface, with the processor, communication interface, and memory communicating with each other via the communication bus.

[0275] As can be seen, in the solution provided in this application embodiment, a detector is applied to the image processing system, and the image processing system also includes a terminal device. The detector can acquire an image to be transmitted, determine a first position of the object region and a second position of the empty field region in the image to be transmitted, wherein the empty field region is a region in the image to be transmitted where no object exists. Based on the first position, an object image is cropped from the image to be transmitted. Based on the pixel value of the empty field region corresponding to the second position, an empty field index corresponding to the empty field region is calculated. The object image and the empty field index are transmitted to the terminal device so that the terminal device can perform image reconstruction based on the object image and the empty field index to obtain the transmitted image. After acquiring the image to be transmitted, the first position of the object region and the second position of the empty field region in the image can be determined. Then, the object image can be cropped from the image to be transmitted based on the first position, and the empty field index can be calculated based on the pixel value of the empty field region corresponding to the second position. Then, the object image and the empty field index are transmitted to the terminal device so that the terminal device can reconstruct the image. In this way, it is not necessary to transmit the entire image, but only the object image and the empty field index need to be transmitted to the terminal device, which can reduce the amount of data transmitted, improve the image transmission efficiency, and eliminate the need to use interfaces such as 10 Gigabit Ethernet and dual network ports, as well as the need to develop interface drivers, thereby reducing the cost and development complexity of image transmission.

[0276] The communication bus mentioned in the detector above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0277] The communication interface is used for communication between the aforementioned detector and other devices.

[0278] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0279] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0280] This application also provides a terminal device, including:

[0281] Memory, used to store computer programs;

[0282] When the processor executes the program stored in the memory, it implements the steps of the second image transmission method described in any of the above embodiments.

[0283] Furthermore, the aforementioned terminal equipment may also include a communication bus and / or a communication interface, with the processor, communication interface, and memory communicating with each other via the communication bus.

[0284] As can be seen, in the solution provided in this application embodiment, a terminal device is applied to the image processing system. The image processing system also includes a detector. The terminal device can receive the object image and the airspace index transmitted by the detector. The object image is obtained by cropping the object region from the first position in the image to be transmitted, and the airspace index is calculated based on the pixel values ​​of the airspace region in the image to be transmitted. Image reconstruction is performed based on the object image and the airspace index to obtain the transmitted image. Since the object image is obtained by cropping the object region from the first position in the image to be transmitted, and the airspace index is calculated based on the pixel values ​​of the airspace region in the image to be transmitted, image reconstruction can be performed after receiving the object image and the airspace index to obtain the transmitted image. In this way, the detector does not need to transmit the entire image; only the object image and the airspace index need to be transmitted to the terminal device. This reduces the amount of data transmitted, improves image transmission efficiency, eliminates the need for interfaces such as 10 Gigabit Ethernet and dual network ports, and eliminates the need for driver development for the interfaces, thus reducing the cost and development complexity of image transmission.

[0285] The communication bus mentioned in the aforementioned terminal equipment can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not indicate that there is only one bus or one type of bus.

[0286] The communication interface is used for communication between the aforementioned terminal devices and other devices.

[0287] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0288] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0289] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores a computer program that, when executed by a processor, implements the steps of any of the above-described image transmission methods.

[0290] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to perform any of the image transmission methods described above.

[0291] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a solid-state drive (SSD), etc.

[0292] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0293] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, detectors, terminal devices, computer-readable storage media, and computer program products are basically similar to the method embodiments, and therefore the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0294] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application are included within the scope of protection of this application.

Claims

1. An image transmission method, characterized in that, A detector applied in an image processing system, the image processing system further including a terminal device, the method comprising: Acquire images to be transmitted; Determine a first position of an object region and a second position of an empty field region in the image to be transmitted, wherein the empty field region is a region in the image to be transmitted where no object exists; Based on the first position, an object image is cropped from the image to be transmitted; Based on the pixel values ​​of the empty area corresponding to the second position, the empty area index corresponding to the empty area is calculated. The empty area index is used to restore the image of the empty area during the image reconstruction process. The empty area index includes at least one of the following: mean, standard deviation, maximum value, minimum value, median, proportion of pixels within a preset multiple of the mean standard deviation, and uniformity. The object image and the airspace index are transmitted to the terminal device so that the terminal device can reconstruct the image based on the object image and the airspace index to obtain the transmitted image.

2. The method according to claim 1, characterized in that, The step of determining the first position of the object region and the second position of the empty field region in the image to be transmitted includes: An object recognition algorithm is used to identify the object regions in the image to be transmitted, and the first initial position of the object regions is obtained. An empty field recognition algorithm is used to identify the empty field regions in the image to be transmitted, thereby obtaining the second initial position of the empty field regions; The first initial position and the second initial position are compared to obtain the comparison result; The first initial position is adjusted according to the comparison result to obtain the first position of the object region, and the second initial position is adjusted according to the comparison result to obtain the second position of the empty field region.

3. The method according to claim 2, characterized in that, The step of using an empty field recognition algorithm to identify empty field regions in the image to be transmitted and obtaining the second initial position of the empty field regions includes: The empty field region in the image to be transmitted is identified based on the image characteristics corresponding to the empty field region to obtain the second initial position of the empty field region, wherein the image characteristics include at least the feature that the pixel values ​​of the image satisfy Gaussian noise.

4. The method according to claim 2, characterized in that, The steps of adjusting the first initial position according to the comparison result to obtain the first position of the object region, and adjusting the second initial position according to the comparison result to obtain the second position of the empty field region, include: Based on the comparison results, a first boundary and a second boundary are determined within a preset deviation range for the positional deviation, wherein the first boundary is the boundary represented by the first initial position, and the second boundary is the boundary represented by the second initial position; For the first boundary and the second boundary, calculate the average position of the first boundary and the second boundary, and use it as the boundary between the object region and the empty field region to obtain the first position of the object region and the second position of the empty field region.

5. The method according to claim 1, characterized in that, The image processing system also includes sensors; The step of determining the first position of the object region and the second position of the empty field region in the image to be transmitted includes: Acquire sensor images captured by the sensor; Based on the location of the object region in the sensor image and the positional relationship between the sensor and the detector, the first location of the object region in the image to be transmitted is determined; Based on the first location, determine the second location of the open area.

6. The method according to any one of claims 1-5, characterized in that, Prior to the step of transmitting the object image and the airspace index to the terminal device, the method further includes: The object image is compressed to obtain a compressed object image.

7. An image transmission method, characterized in that, A terminal device applied in an image processing system, the image processing system further including a detector, the method comprising: The system receives an object image and an empty field index transmitted by the detector. The object image is obtained by cropping a first position of an object region in the image to be transmitted. The empty field index is calculated based on the pixel values ​​of the empty field region in the image to be transmitted. The empty field index is used to restore the image of the empty field region during the image reconstruction process. The empty field index includes at least one of the following: the mean, standard deviation, maximum value, minimum value, median, percentage of pixels within a preset multiple of the mean standard deviation, and uniformity of pixel values. Image reconstruction is performed based on the object image and the airspace index to obtain the transmitted image.

8. The method according to claim 7, characterized in that, The step of reconstructing the image based on the object image and the airspace index to obtain the transmitted image includes: The object image is filled into a preset blank image according to the first position to obtain a first image, wherein the size of the preset blank image is the same as the size of the image to be transmitted; Based on the aforementioned empty field index, an empty field image is reconstructed to obtain a second image, wherein the size of the second image is the same as the size of the image to be transmitted; Based on the first position, the region corresponding to the object region in the second image is removed to obtain an empty field image; The first image is superimposed on the empty field image to obtain the transmitted image.

9. The method according to claim 8, characterized in that, Before the step of overlaying the first image with the empty field image to obtain the transmitted image, the method further includes: Based on the pixel values ​​of the empty field image, the empty field index of the empty field image is calculated and used as the reconstructed empty field index. Calculate the difference between the reconstructed airfield index and the airfield index transmitted by the detector; If the difference is not within the preset difference range, adjust the pixel values ​​of the empty field image to obtain the adjusted image; The adjusted image is used as an empty field image, and the empty field index of the empty field image is calculated based on the pixel values ​​of the empty field image as a step to reconstruct the empty field index, until the difference is within the preset difference range.

10. An image transmission device, characterized in that, A detector used in an image processing system, the image processing system further including a terminal device, the device comprising: The image acquisition module is used to acquire images to be transmitted. A position determination module is used to determine a first position of an object region and a second position of an empty field region in the image to be transmitted, wherein the empty field region is a region in the image to be transmitted where no object exists; An object image cropping module is used to crop an object image from the image to be transmitted based on the first position; The empty field index calculation module is used to calculate the empty field index corresponding to the empty field area based on the pixel value of the empty field area corresponding to the second position. The empty field index is used to restore the image of the empty field area during the image reconstruction process. The empty field index includes at least one of the following: the mean, standard deviation, maximum value, minimum value, median, proportion of pixels within a preset multiple of the mean standard deviation, and uniformity of pixel values. An image and indicator transmission module is used to transmit the object image and the airspace indicator to the terminal device, so that the terminal device can perform image reconstruction based on the object image and the airspace indicator to obtain the transmitted image.

11. The apparatus according to claim 10, characterized in that, The location determination module includes: The first initial position acquisition submodule is used to identify the object region in the image to be transmitted using an object recognition algorithm, and obtain the first initial position of the object region; The second initial position acquisition submodule is used to identify the empty field region in the image to be transmitted using an empty field recognition algorithm, and obtain the second initial position of the empty field region. The comparison result acquisition submodule is used to compare the first initial position and the second initial position to obtain the comparison result; The location acquisition submodule is used to adjust the first initial position according to the comparison result to obtain the first position of the object region, and to adjust the second initial position according to the comparison result to obtain the second position of the empty field region. The second initial position acquisition submodule includes: The second initial position acquisition unit identifies the empty field region in the image to be transmitted based on the image characteristics corresponding to the empty field region, and obtains the second initial position of the empty field region. The image characteristics include at least the feature that the pixel values ​​of the image satisfy Gaussian noise. The location acquisition submodule includes: A boundary determination unit is used to determine a first boundary and a second boundary within a preset deviation range based on the comparison result, wherein the first boundary is the boundary represented by the first initial position and the second boundary is the boundary represented by the second initial position. The location acquisition unit is used to calculate the average position of the first boundary and the second boundary for the first boundary and the second boundary, and use it as the boundary between the object region and the empty field region to obtain the first position of the object region and the second position of the empty field region. The image processing system also includes sensors; The location determination module includes: The sensor image determination submodule is used to acquire sensor images captured by the sensor; The first position determination submodule is used to determine the first position of the object region in the image to be transmitted based on the position of the object region in the sensor image and the positional relationship between the sensor and the detector. The second position determination submodule is used to determine the second position of the open area based on the first position. The device further includes: The compressed object image acquisition module is used to compress the object image before the step of transmitting the object image and the airspace index to the terminal device, so as to obtain a compressed object image.

12. An image transmission device, characterized in that, A terminal device applied in an image processing system, the image processing system further including a detector, the device comprising: The image and index receiving module is used to receive the object image and the empty field index transmitted by the detector. The object image is obtained by cropping the object region in the image to be transmitted from a first position. The empty field index is calculated based on the pixel values ​​of the empty field region in the image to be transmitted. The empty field index is used to restore the image of the empty field region during the image reconstruction process. The empty field index includes at least one of the following: the mean, standard deviation, maximum value, minimum value, median, the proportion of pixels within a preset multiple of the mean standard deviation, and uniformity of pixel values. The image acquisition module is used to reconstruct the image based on the object image and the airspace index to obtain the transmitted image.

13. The apparatus according to claim 12, characterized in that, The image acquisition module includes: The first image acquisition submodule is used to fill the object image into a preset blank image according to the first position to obtain a first image, wherein the size of the preset blank image is the same as the size of the image to be transmitted; The second image acquisition submodule is used to reconstruct the air field image based on the air field index to obtain a second image, wherein the size of the second image is the same as the size of the image to be transmitted; The empty field image acquisition submodule is used to remove the region corresponding to the object region in the second image based on the first position to obtain an empty field image; The image acquisition submodule is used to overlay the first image with the empty field image to obtain the transmitted image; The device further includes: The reconstruction void field index calculation module is used to calculate the void field index of the void field image based on the pixel value of the void field image before the step of superimposing the first image with the void field image to obtain the transmitted image, and use it as the reconstruction void field index. The difference calculation module is used to calculate the difference between the reconstructed airfield index and the airfield index transmitted by the detector. The image acquisition module is adjusted to adjust the pixel values ​​of the empty field image if the difference is not within a preset difference range, so as to obtain an adjusted image. The index calculation and return module is used to take the adjusted image as an empty field image and return the empty field index of the empty field image calculated based on the pixel value of the empty field image as a step of reconstructing the empty field index, until the difference is within the preset difference range.

14. An image processing system, characterized in that, The system includes a detector and a terminal device, wherein: The detector is used to acquire an image to be transmitted; determine a first position of an object region and a second position of an empty field region in the image to be transmitted; crop an object image from the image to be transmitted based on the first position; calculate an empty field index corresponding to the empty field region based on the pixel value of the empty field region corresponding to the second position; transmit the object image and the empty field index to the terminal device, so that the terminal device can perform image reconstruction based on the object image and the empty field index to obtain the transmitted image; wherein, the empty field region is a region in the image to be transmitted where there is no object, and the empty field index is used to restore the image of the empty field region during the image reconstruction process. The empty field index includes at least one of the following: mean, standard deviation, maximum value, minimum value, median, percentage of pixels within a preset multiple of the mean standard deviation, and uniformity of pixel values. The terminal device is used to receive the object image and the air field index transmitted by the detector, and to perform image reconstruction based on the object image and the air field index to obtain the transmitted image; wherein, the object image is obtained by cropping the object region in the image to be transmitted, and the air field index is calculated based on the pixel value of the air field region in the image to be transmitted.

15. The system according to claim 14, characterized in that, The system also includes sensors, wherein: The sensor is used to capture a sensor image so that the detector can acquire the sensor image, and determine a first position of the object region in the image to be transmitted based on the position of the object region in the sensor image and the positional relationship between the sensor and the detector; and determine a second position of the empty field region based on the first position.

16. A detector, characterized in that, include: Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method of any one of claims 1-6.

17. A terminal device, characterized in that, include: Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method of any one of claims 7-9.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-9.

Images