High-resolution wide-format optical image intelligent fringe detection method and device

Abstract

The present disclosure provides a high-resolution large-width optical image intelligent stripe detection method and device, comprising: obtaining a high-resolution large-width image to be detected, the high-resolution large-width image to be detected comprising: an initial image block, determining at least one candidate image block from the initial image block, determining a first gray histogram corresponding to each candidate image block, and determining a second gray histogram corresponding to the high-resolution large-width image to be detected according to the first gray histogram corresponding to each candidate image block, determining a target region image from the high-resolution large-width image to be detected, determining a third gray histogram corresponding to the target region image, determining the matching degree between the third gray histogram and the second gray histogram, in the case that the matching degree is greater than or equal to a matching degree threshold, inputting the target region image into a stripe detection model and a quality evaluation model respectively, obtaining a stripe detection result output by the stripe detection model, and a quality evaluation result output by the quality evaluation model.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of artificial intelligence, in particular to a high-resolution wide-range optical image intelligent stripe detection method and device. BACKGROUND

[0002] With the continuous development of high-altitude optical camera imaging technology, more and more high-resolution wide-range image data is obtained. Due to the special nature of high-resolution wide-range images, i.e., large imaging area, the probability of image quality being affected by cloud and fog obstruction, atmospheric interference, lighting conditions, etc. is also increased, so that more stripe noise will appear in the image. Stripe noise, as a common interference, is usually caused by factors such as sensor scan lines and uneven sensor channel response. The stripe interference in the image will cause discontinuity of image brightness, color and texture, thereby affecting the quality and usability of high-resolution wide-range images.

[0003] In related technologies, there are problems of poor stripe detection effect and low timeliness of high-resolution wide-range image detection. SUMMARY

[0004] The present disclosure aims to at least partially solve one of the technical problems in the related art.

[0005] To this end, the purpose of the present disclosure is to propose a high-resolution wide-range optical image intelligent stripe detection method, device, electronic equipment and storage medium, which can determine a target area image from a large amount of data of a high-resolution wide-range image to be detected, thereby reducing the subsequent data processing amount, thereby improving the stripe detection efficiency, and since the processing complexity of the target area image is low, the stripe detection effect of the high-resolution wide-range image can be improved.

[0006] To achieve the above purpose, the high-resolution wide-range optical image intelligent stripe detection method according to the first aspect of the present disclosure comprises:

[0007] obtaining a high-resolution wide-range image to be detected, wherein the high-resolution wide-range image to be detected comprises a plurality of initial image blocks;

[0008] determining at least one candidate image block from the plurality of initial image blocks;

[0009] determining a first gray histogram corresponding to each candidate image block, and determining a second gray histogram corresponding to the high-resolution wide-range image to be detected according to the first gray histogram corresponding to each candidate image block;

[0010] determining a target area image from the high-resolution wide-range image to be detected, and determining a third gray histogram corresponding to the target area image;

[0011] determine a matching degree between the third gray histogram and the second gray histogram;

[0012] In a case where the matching degree is greater than or equal to a matching degree threshold, input the target region image into a stripe detection model and a quality evaluation model respectively to obtain a stripe detection result output by the stripe detection model and a quality evaluation result output by the quality evaluation model.

[0013] To achieve the above object, the second aspect embodiment of the present disclosure proposes a high-resolution large-width optical image intelligent stripe detection device, which comprises:

[0014] An acquisition module is configured to acquire a high-resolution large-width image to be detected, wherein the high-resolution large-width image to be detected comprises a plurality of initial image blocks.

[0015] A first determination module is configured to determine at least one candidate image block from the plurality of initial image blocks.

[0016] A second determination module is configured to determine a first gray histogram corresponding to each candidate image block, and determine a second gray histogram corresponding to the high-resolution large-width image to be detected according to the first gray histogram corresponding to each candidate image block.

[0017] A third determination module is configured to determine a target region image from the high-resolution large-width image to be detected, and determine a third gray histogram corresponding to the target region image.

[0018] A fourth determination module is configured to determine a matching degree between the third gray histogram and the second gray histogram.

[0019] A processing module is configured to, in a case where the matching degree is greater than or equal to a matching degree threshold, input the target region image into a stripe detection model and a quality evaluation model respectively to obtain a stripe detection result output by the stripe detection model and a quality evaluation result output by the quality evaluation model.

[0020] The third aspect embodiment of the present disclosure proposes an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the high-resolution large-width optical image intelligent stripe detection method according to the first aspect embodiment of the present disclosure when executing the program.

[0021] The fourth aspect embodiment of the present disclosure proposes a non-transitory computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the high-resolution large-width optical image intelligent stripe detection method according to the first aspect embodiment of the present disclosure.

[0022] The fifth aspect of the present disclosure provides a computer program product, when the instructions in the computer program product are executed by a processor, the high-resolution large-width optical image intelligent fringe detection method is executed.

[0023] The high-resolution large-width optical image intelligent fringe detection method, device, electronic device and storage medium provided by the present disclosure at least have the following beneficial effects: obtaining a high-resolution large-width image to be detected, wherein the high-resolution large-width image to be detected includes a plurality of initial image blocks, at least one candidate image block is determined from the plurality of initial image blocks, a first gray histogram corresponding to each candidate image block is determined, and a second gray histogram corresponding to the high-resolution large-width image to be detected is determined according to the first gray histogram corresponding to each candidate image block, a target region image is determined from the high-resolution large-width image to be detected, and a third gray histogram corresponding to the target region image is determined, the matching degree between the third gray histogram and the second gray histogram is determined, and in the case that the matching degree is greater than or equal to a matching degree threshold, the target region image is input into a fringe detection model and a quality evaluation model respectively to obtain a fringe detection result output by the fringe detection model and a quality evaluation result output by the quality evaluation model. Therefore, the target region image can be determined from the high-resolution large-width image to be detected with a large amount of data, thereby reducing the subsequent data processing amount and improving the fringe detection efficiency. In addition, the processing complexity of the target region image is low, thereby improving the fringe detection effect of the high-resolution large-width image.

[0024] The additional aspects and advantages of the present disclosure will be partially given in the following description, partially become obvious from the following description, or be understood through the practice of the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0025] The above and / or additional aspects and advantages of the present disclosure will become apparent and more readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:

[0026] Figure 1 is a flowchart of a high-resolution large-width optical image intelligent fringe detection method according to an embodiment of the present disclosure;

[0027] Figure 2A is a structural diagram of a fringe detection model according to an embodiment of the present disclosure;

[0028] Figure 2B is a model structure diagram of a quality evaluation model according to an embodiment of the present disclosure;

[0029] Figure 3 is a flowchart of a high-resolution large-width optical image intelligent fringe detection method according to another embodiment of the present disclosure;

[0030] Figure 4 is a structural schematic diagram of a high-resolution large-format optical image intelligent stripe detection device according to an embodiment of the present disclosure;

[0031] Figure 5 A block diagram of an exemplary electronic device suitable for implementing an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0032] Embodiments of the present disclosure are described in detail below with reference to the accompanying drawings, examples of which are shown in the drawings, wherein the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present disclosure and cannot be understood as a limitation of the present disclosure. On the contrary, the embodiments of the present disclosure include all changes, modifications and equivalents falling within the spirit and scope of the appended claims.

[0033] Figure 1 is a flowchart of a high-resolution large-format optical image intelligent stripe detection method according to an embodiment of the present disclosure.

[0034] It should be noted that the execution subject of the high-resolution large-format optical image intelligent stripe detection method of the present embodiment is a high-resolution large-format optical image intelligent stripe detection device, which can be realized by software and / or hardware. The device can be configured in an electronic device, which can include but is not limited to a terminal, a server end, etc. For example, the terminal can be a mobile phone, a palm computer, etc.

[0035] As shown in Figure 1 , the high-resolution large-format optical image intelligent stripe detection method comprises the following steps.

[0036] S101: Obtain a high-resolution large-format image to be detected, wherein the high-resolution large-format image to be detected comprises a plurality of initial image blocks.

[0037] The high-resolution large-format image has a large amount of image data, high image resolution, and large imaging area. For example, the high-resolution large-format image can be an optical remote sensing image, an image with geographic information, etc. without limitation.

[0038] The stripe noise is a kind of image interference that often occurs. The stripe noise is usually caused by factors such as uneven response of sensor scan lines and sensor channels. The stripe noise in the image will cause discontinuity of image brightness, color and texture, thereby affecting the image quality.

[0039] The high-resolution large-format image to be detected refers to a high-resolution large-format image currently to be subjected to stripe detection.

[0040] In the embodiments of the present disclosure, the high-resolution large-format image to be detected can be acquired by a remote sensing image acquisition device for a certain preset area, or any remote sensing image can be acquired from a remote sensing image database storing a plurality of remote sensing images as the high-resolution large-format image to be detected, and no limitation is made thereto.

[0041] The high-resolution large-format image to be detected includes a plurality of initial image blocks, and the plurality of initial image blocks are obtained by rasterizing the high-resolution large-format image to be detected.

[0042] That is, in the embodiments of the present disclosure, the high-resolution large-format image to be detected can be rasterized based on a preset image block size to obtain a plurality of initial image blocks of the same size.

[0043] S102: Determine at least one candidate image block from the plurality of initial image blocks.

[0044] In the embodiments of the present disclosure, after the high-resolution large-format image to be detected is acquired, at least one candidate image block can be determined from the plurality of initial image blocks.

[0045] It can be understood that after the high-resolution large-format image to be detected is divided into a plurality of initial image blocks, some initial image blocks can not contain semantic information. Therefore, at least one candidate image block can be determined from the plurality of initial image blocks by deleting the initial image blocks in the plurality of initial image blocks that do not contain semantic information, and the remaining initial image blocks are taken as candidate image blocks.

[0046] Optionally, in some embodiments, determining at least one candidate image block from the plurality of initial image blocks can include determining a second number of second pixel points in each initial image block, and taking the initial image block corresponding to the second number as a candidate image block if the second number is greater than or equal to a number threshold.

[0047] The number of pixel points in each initial image block is the second number.

[0048] That is, in the embodiments of the present disclosure, after the high-resolution large-format image to be detected is acquired, the second number of second pixel points in each initial image block in the high-resolution large-format image to be detected can be determined, and the initial image block corresponding to the second number is taken as a candidate image block if it is determined that the second number is greater than or equal to a number threshold.

[0049] For example, the initial image block can be deleted and the remaining initial image blocks are taken as candidate image blocks if it is determined that the second number of second pixel points in the initial image block is less than 5000*5000.

[0050] S103: determine a first gray scale histogram corresponding to each candidate image block, and determine a second gray scale histogram corresponding to the high-resolution wide-format image to be detected according to the first gray scale histogram corresponding to each candidate image block.

[0051] The gray scale histogram corresponding to the candidate image block is the first gray scale histogram, and the gray scale histogram corresponding to the high-resolution wide-format image to be detected is the second gray scale histogram.

[0052] That is to say, in the embodiment of the present disclosure, after determining at least one candidate image block from the plurality of initial image blocks, the gray scale histogram of each candidate image block can be counted respectively to obtain the first gray scale histogram corresponding to each candidate image block.

[0053] In the embodiment of the present disclosure, after determining the first gray scale histogram corresponding to each candidate image block, the second gray scale histogram corresponding to the high-resolution wide-format image to be detected can be determined according to the first gray scale histogram corresponding to each candidate image block.

[0054] Optionally, in some embodiments, the second gray scale histogram corresponding to the high-resolution wide-format image to be detected can be determined according to the first gray scale histogram corresponding to each candidate image block, which can be to determine the quantity average of the first quantity corresponding to each gray scale level in the plurality of first gray scale histograms, and then generate the second gray scale histogram corresponding to the high-resolution wide-format image to be detected according to the quantity average of the first pixel points corresponding to each gray scale level.

[0055] The first gray scale histogram includes the first quantity of the first pixel points corresponding to each gray scale level.

[0056] In the first gray scale histogram, the pixel points corresponding to each gray scale level are the first pixel points, and the quantity of the first pixel points is the first quantity.

[0057] That is to say, in the embodiment of the present disclosure, the quantity average of the first quantity corresponding to each gray scale level in the plurality of first gray scale histograms can be determined, and then the second gray scale histogram corresponding to the high-resolution wide-format image to be detected can be generated according to the quantity average of the first pixel points corresponding to each gray scale level.

[0058] S104: determine a target region image from the high-resolution wide-format image to be detected, and determine a third gray scale histogram corresponding to the target region image.

[0059] The target region image determined from the high-resolution wide-format image to be detected for subsequent stripe detection is a local image, and the target region image has the typical ground feature of the high-resolution wide-format image to be detected.

[0060] The gray scale histogram corresponding to the target region image is the third gray scale histogram.

[0061] In some embodiments, the target region image can be determined from the high-resolution wide image to be detected based on a preset image size to determine a local image located at a center position of the image as the target region image.

[0062] In other embodiments, the target region image can also be determined from the high-resolution wide image to be detected by processing the high-resolution wide image to be detected based on a pre-trained image segmentation model, that is, the high-resolution wide image to be detected can be input into the pre-trained image segmentation model to obtain the target region image output by the image segmentation model, and no limitation is made thereto.

[0063] In the embodiments of the present disclosure, the size of the high-resolution wide image to be detected is h*w.

[0064] Optionally, in some embodiments, the target region image can be determined from the high-resolution wide image to be detected by determining a local image located at the center of the image with an image size of x*w as the target region image, where x<h.

[0065] In this regard, it is found through a large number of experiments that the typical object size usually accounts for 1 / 4 of the full image, and the position is usually in the middle of the panoramic image, because the image stripe noise usually runs through the entire panoramic image, and the middle part has a stripe, and the panoramic image must have a stripe.

[0066] For example, according to the mechanism that the image stripe noise runs through the entire image, the middle h / 2 can be selected as the starting row of the target region image, and a data block with an image size of x*w (1000*w) can be determined as the target region image.

[0067] S105: Determine the matching degree between the third gray scale histogram and the second gray scale histogram.

[0068] The matching degree between the third gray scale histogram and the second gray scale histogram can refer to the similarity between the two gray scale histograms (for example, histogram intersection, chi-square distance, and Bhattacharyya distance), and no limitation is made thereto.

[0069] That is, in the embodiments of the present disclosure, the Bhattacharyya distance or the chi-square distance between the second gray scale histogram and the third gray scale histogram can be determined, and the Bhattacharyya distance or the chi-square distance between the second gray scale histogram and the third gray scale histogram determined as described above can be taken as the matching degree between the second gray scale histogram and the third gray scale histogram, and no limitation is made thereto.

[0070] S106: in the case of determining that the matching degree is greater than or equal to the matching degree threshold, inputting the target region image into the stripe detection model and the quality evaluation model respectively to obtain a stripe detection result output by the stripe detection model and a quality evaluation result output by the quality evaluation model.

[0071] In the embodiments of the present disclosure, referring to Figure 2A , Figure 2A is a structural schematic diagram of a stripe detection model according to an embodiment of the present disclosure, as shown in Figure 2A The model structure of the stripe detection model sequentially includes a first standard convolution module CBL, a first backbone network, a channel type lightweight re-encoding module CLR, a second CBL and a second backbone network.

[0072] In the embodiments of the present disclosure, referring to Figure 2B , Figure 2B is a model structure schematic diagram of a quality evaluation model according to an embodiment of the present disclosure, as shown in Figure 2B The model structure of the quality evaluation model sequentially includes a third CBL, a third backbone network, a fourth backbone network and a fourth CBL.

[0073] The CBL module contains a convolution layer, a batch normalization layer and a Leaky activation layer. The convolution layer is used for feature extraction, the normalization layer helps the stability of the network, and the Leaky activation function is as follows:

[0074] f(x) = a * x x < 0;

[0075] f(x) = x x >= 0;

[0076] In the embodiments of the present disclosure, the backbone network of the quality evaluation model adopts a residual structure.

[0077] In the embodiments of the present disclosure, a lightweight model is designed by using a residual network structure, a CBL (convolution, batch normalization and Leaky activation function) module is used to replace the traditional convolution layer to extract features of different scales, and a CLR module is used to fuse features of different characteristics, so that the stripe detection neural network has smaller network parameters and faster detection speed without reducing the feature expression ability of the neural network.

[0078] In the embodiments of the present disclosure, the stripe detection model is pre-trained according to a first mapping relationship between a sample high-score large-width image and a labeled stripe detection result corresponding to the sample high-score large-width image, and the quality evaluation model is pre-trained according to a second mapping relationship between the sample high-score large-width image and a labeled signal-to-noise ratio corresponding to the sample high-score large-width image.

[0079] That is to say, in the embodiments of the present disclosure, the initial stripe detection model can be iteratively trained based on the sample high-resolution wide image and the labeled stripe detection result corresponding to the sample high-resolution wide image until the initial stripe detection model converges to obtain the stripe detection model. In addition, the initial quality evaluation model can be iteratively trained based on the sample high-resolution wide image and the labeled signal-to-noise ratio corresponding to the sample high-resolution wide image until the initial stripe detection model converges to obtain the quality evaluation model. Then, the subsequent high-resolution wide optical image intelligent stripe detection method can be performed based on the trained stripe detection model and quality evaluation model. For details, please refer to the subsequent embodiments.

[0080] wherein the stripe detection result is 0 or 1, 0 indicating that there is no stripe noise in the high-resolution wide image to be detected, and 1 indicating that there is stripe noise in the high-resolution wide image to be detected.

[0081] wherein the quality evaluation result can be used to quantitatively evaluate the image quality of the high-resolution wide image to be detected. The quality evaluation result can be, for example, the image signal-to-noise ratio, which is not limited in this regard.

[0082] In the embodiments of the present disclosure, after determining the matching degree between the third gray histogram and the second gray histogram, the matching degree can be compared with the pre-determined matching degree threshold, and in the case that the matching degree is greater than or equal to the matching degree threshold, the target region image is input into the stripe detection model and the quality evaluation model respectively to obtain the stripe detection result output by the stripe detection model and the quality evaluation result output by the quality evaluation model.

[0083] In the embodiments of the present disclosure, by obtaining the high-resolution wide image to be detected, wherein the high-resolution wide image to be detected includes a plurality of initial image blocks, at least one candidate image block is determined from the plurality of initial image blocks, a first gray histogram corresponding to each candidate image block is determined, and a second gray histogram corresponding to the high-resolution wide image to be detected is determined according to the first gray histogram corresponding to each candidate image block. A target region image is determined from the high-resolution wide image to be detected, and a third gray histogram corresponding to the target region image is determined. The matching degree between the third gray histogram and the second gray histogram is determined. In the case that the matching degree is greater than or equal to the matching degree threshold, the target region image is input into the stripe detection model and the quality evaluation model respectively to obtain the stripe detection result output by the stripe detection model and the quality evaluation result output by the quality evaluation model. In this way, the target region image can be determined from the high-resolution wide image to be detected with a large amount of data, thereby reducing the subsequent data processing amount and improving the stripe detection efficiency. In addition, since the processing complexity of the target region image is low, the stripe detection effect of the high-resolution wide image can be improved.

[0084] FIG. 2 is a flowchart of a high-resolution large-format wide optical image intelligent fringe detection method according to another embodiment of the present disclosure.

[0085] As shown in FIG. 2, the high-resolution large-format wide optical image intelligent fringe detection method includes the following steps.

[0086] S301: Obtain a high-resolution large-format wide image to be detected, wherein the high-resolution large-format wide image to be detected includes a plurality of initial image blocks.

[0087] S302: Determine at least one candidate image block from the plurality of initial image blocks.

[0088] S303: Determine a first gray histogram corresponding to each candidate image block, and determine a second gray histogram corresponding to the high-resolution large-format wide image to be detected according to the first gray histogram corresponding to each candidate image block.

[0089] S304: Determine a target region image from the high-resolution large-format wide image to be detected, and determine a third gray histogram corresponding to the target region image.

[0090] S305: Determine a matching degree between the third gray histogram and the second gray histogram.

[0091] S306: In a case where the matching degree is greater than or equal to a matching degree threshold, input the target region image into a fringe detection model and a quality evaluation model respectively to obtain a fringe detection result output by the fringe detection model and a quality evaluation result output by the quality evaluation model.

[0092] The descriptions of S301-S306 can refer to the above embodiments, and will not be repeated here.

[0093] S307: In a case where the matching degree is less than the matching degree threshold, return to perform the operation of determining the target region image from the high-resolution large-format wide image to be detected, wherein in the operation of returning to perform the operation of determining the target region image from the high-resolution large-format wide image to be detected, the image size of the target region image is y*w, and x<y.

[0094] In the embodiments of the present disclosure, after the matching degree between the third gray histogram and the second gray histogram is determined, the matching degree can be compared with a predetermined matching degree threshold, and in a case where the matching degree is less than the matching degree threshold, the operation of determining the target region image from the high-resolution large-format wide image to be detected is returned to perform.

[0095] In an embodiment of the present disclosure, when returning to perform the operation of determining the target region image from the to-be-detected high-resolution wide-width image, it may be to select the target region image with a larger size (y*w, x < y) in the intersection initial operation, that is, it may be to extend 500 pixels in the h dimension direction of the target region image determined in the initial operation to form a new target region image of 3000*w pixels.

[0096] In an embodiment of the present disclosure, by obtaining a to-be-detected high-resolution wide-width image, where the to-be-detected high-resolution wide-width image includes: a plurality of initial image blocks, then determining at least one candidate image block from the plurality of initial image blocks, then determining a first gray level histogram corresponding to each candidate image block, and according to the first gray level histogram corresponding to each candidate image block, determining a second gray level histogram corresponding to the to-be-detected high-resolution wide-width image, then determining the target region image from the to-be-detected high-resolution wide-width image, and determining a third gray level histogram corresponding to the target region image, then determining the matching degree between the third gray level histogram and the second gray level histogram. When it is determined that the matching degree is greater than or equal to the matching degree threshold, inputting the target region image into the stripe detection model and the quality evaluation model respectively to obtain the stripe detection result output by the stripe detection model and the quality evaluation result output by the quality evaluation model. When the matching degree is less than the matching degree threshold, returning to perform the operation of determining the target region image from the to-be-detected high-resolution wide-width image. Thus, the target region image can be determined from the to-be-detected high-resolution wide-width image with a large data volume, thereby reducing the subsequent data processing volume, improving the stripe detection efficiency, and since the processing complexity of the target region image is relatively low, improving the stripe detection effect of the high-resolution wide-width image.

[0097] Figure 4 It is a schematic structural diagram of a high-resolution wide-width optical image intelligent stripe detection device proposed in an embodiment of the present disclosure.

[0098] As Figure 4 shown, the high-resolution wide-width optical image intelligent stripe detection device 40 includes:

[0099] An obtaining module 401, configured to obtain a to-be-detected high-resolution wide-width image, where the to-be-detected high-resolution wide-width image includes: a plurality of initial image blocks;

[0100] A first determining module 402, configured to determine at least one candidate image block from the plurality of initial image blocks;

[0101] A second determining module 403, configured to determine a first gray level histogram corresponding to each candidate image block, and according to the first gray level histogram corresponding to each candidate image block, determine a second gray level histogram corresponding to the to-be-detected high-resolution wide-width image;

[0102] The third determination module 404 is configured to determine a target region image from the high-score wide image to be detected, and determine a third gray scale histogram corresponding to the target region image.

[0103] The fourth determination module 405 is configured to determine a matching degree between the third gray scale histogram and the second gray scale histogram.

[0104] The processing module 406 is configured to, in a case where the matching degree is greater than or equal to a matching degree threshold, input the target region image into a stripe detection model and a quality evaluation model respectively, to obtain a stripe detection result output by the stripe detection model and a quality evaluation result output by the quality evaluation model.

[0105] In some embodiments of the present disclosure, the first gray scale histogram includes: a first number of first pixel points corresponding to each gray scale level; and the second determination module 403 is further configured to:

[0106] determine a number average of the first number of first pixel points corresponding to each gray scale level in the plurality of first gray scale histograms.

[0107] generate the second gray scale histogram corresponding to the high-score wide image to be detected according to the number average of the first number of first pixel points corresponding to each gray scale level.

[0108] In some embodiments of the present disclosure, the size of the high-score wide image to be detected is h*w; and the fourth determination module 305 is further configured to:

[0109] determine, from the high-score wide image to be detected, a local image with a size of x*w located at a center of the image as the target region image, where x<h.

[0110] In some embodiments of the present disclosure, the processing module 406 is further configured to:

[0111] in a case where the matching degree is less than the matching degree threshold, return to perform the operation of determining the target region image from the high-score wide image to be detected, where, in the operation of returning to perform the operation of determining the target region image from the high-score wide image to be detected, the size of the target region image is y*w, and x<y.

[0112] In some embodiments of the present disclosure, the model structure of the stripe detection model comprises, in sequence:

[0113] a first standard convolution module CBL, a first backbone network, a channel lightweight re-encoding module CLR, a second CBL and a second backbone network.

[0114] The model structure of the quality evaluation model comprises, in sequence:

[0115] a third CBL, a third backbone network, a fourth backbone network and a fourth CBL.

[0116] In some embodiments of the present disclosure, the stripe detection model is pre-trained according to a first mapping relationship between sample high-resolution wide-format images and labeled stripe detection results corresponding to the sample high-resolution wide-format images, and the quality evaluation model is pre-trained according to a second mapping relationship between the sample high-resolution wide-format images and labeled signal-to-noise ratios corresponding to the sample high-resolution wide-format images.

[0117] In some embodiments of the present disclosure, the first determination module 402 is further configured to:

[0118] determine a second number of the second pixel points in each initial image block;

[0119] in a case where the second number is greater than or equal to a number threshold, the initial image block corresponding to the second number is taken as a candidate image block.

[0120] It should be noted that the foregoing explanation and description of the high-resolution wide-format optical image intelligent stripe detection method also apply to the high-resolution wide-format optical image intelligent stripe detection device of the present embodiment, which will not be described here again.

[0121] In the embodiments of the present disclosure, a high-resolution wide-format image to be detected is obtained, wherein the high-resolution wide-format image to be detected includes a plurality of initial image blocks, at least one candidate image block is determined from the plurality of initial image blocks, a first gray level histogram corresponding to each candidate image block is determined, and a second gray level histogram corresponding to the high-resolution wide-format image to be detected is determined according to the first gray level histogram corresponding to each candidate image block. A target region image is determined from the high-resolution wide-format image to be detected, and a third gray level histogram corresponding to the target region image is determined. The matching degree between the third gray level histogram and the second gray level histogram is determined, and in a case where the matching degree is greater than or equal to a matching degree threshold, the target region image is input into a stripe detection model and a quality evaluation model, respectively, to obtain a stripe detection result output by the stripe detection model and a quality evaluation result output by the quality evaluation model. In this way, the target region image can be determined from the high-resolution wide-format image to be detected with a large amount of data, thereby reducing the amount of subsequent data processing, improving the stripe detection efficiency, and improving the stripe detection effect of the high-resolution wide-format image due to the low processing complexity of the target region image.

[0122] Figure 5 A block diagram of an exemplary electronic device suitable for use in implementing embodiments of the present disclosure is shown. Figure 5 The electronic device 12 shown is merely one example and should not be taken as limiting the functionality or use of embodiments of the present disclosure.

[0123] As Figure 5As shown, the electronic device 12 is in the form of a general-purpose computing device. The components of the electronic device 12 can include, but are not limited to, one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 to the processing unit 16.

[0124] The bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration bus, a processor or local bus using any of a variety of bus architectures including Industry Standard Architecture (ISA), Micro Channel Architecture (MCA), Enhanced ISA (EISA), Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0125] The electronic device 12 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by the electronic device 12 and includes both volatile and non- volatile media, removable and non-removable media.

[0126] The memory 28 can include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 can further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, a storage system 34 can be provided for reading from and writing to non-removable, non-volatile magnetic media (e.g., a "hard drive"). Figure 5 not shown, is typically provided as residual storage space on the storage system 34.

[0127] Although Figure 5A disk drive, a floppy disk drive, a CD-ROM drive, a DVD-ROM drive, or other removable media drive, can be provided, as shown in FIG. 1, for reading from and writing to a removable n on-volatile magnetic media (e.g., a "floppy disk"), and to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media). In such cases, each will include a drive mechanism and optical or other storage media interface for accessing data in the form of physical marks, pits, or other changes to the media. Each drive will be connected to the system bus 18 through one or more data media interfaces. The memory 28 can include, among other things, at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the disclosure.

[0128] The program / utility 40, having a set (at least one) of program modules 42, can be stored in memory 28 by way of example, and not limitation, as well as an operating system, one or more application programs, other program modules, and program data, each or some combination thereof, can include implementation of a network environment. The program modules 42 generally carry out the functions and / or methodologies of embodiments of the disclosure as described herein.

[0129] The electronic device 12 can also communicate with one or more external devices 14 such as a keyboard or a pointing device, displays 24, etc.; other devices such as devices that enable a human body to interact with the electronic device 12; and / or with any devices (e.g., a network card, a modem, etc.) that enable the electronic device 12 to communicate with one or more other computing devices. Such communication can occur via the input / output (I / O) interface 22. Still yet, the electronic device 12 can communicate with one or more networks such as a local area network (LAN), a wide area network (WAN), and / or the Internet through a network adapter 20. As depicted, the network adapter 20 communicates with the other components of the electronic device 12 via the bus 18. It should be appreciated that although the network adapter 20 is depicted as a single component, the network adapter 20 can comprise two or more components that operate together to facilitate the communication of data and signals between the electronic device 12 and the one or more networks. As should be appreciated, a variety of I / O devices 14 can be present in the electronic device 12, e.g., a keyboard, a pointing device, a display 24, etc. It is also contemplated that input and output means can include devices other than keyboard or pointing devices, as well as devices that enable a human body to interact with the electronic device 12, and / or devices that enable the electronic device 12 to interact with one or more other computing devices. Still further, as

[0130] The processing unit 16 executes the various functions of the application and data processing by running programs stored in the system memory 28, such as implementing the high-resolution wide swath optical image intelligent striping detection method described in the foregoing embodiments.

[0131] To achieve the above-mentioned embodiments, the present disclosure further proposes a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the high-score wide-format optical image intelligent fringe detection method as proposed in the foregoing embodiments of the present disclosure.

[0132] To achieve the above-mentioned embodiments, the present disclosure further proposes a computer program product, when the instructions in the computer program product are executed by a processor, the high-score wide-format optical image intelligent fringe detection method as proposed in the foregoing embodiments of the present disclosure is executed.

[0133] Other embodiments of the present disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure following, in general, the principles of the present disclosure and including such features that are evident to those skilled in the art to which the present disclosure pertains. The specification and examples are to be considered exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0134] It should be understood that the present disclosure is not limited to the precise structures as herein described and illustrated in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the claims appended hereto.

[0135] It should be noted that in the description of the present disclosure, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present disclosure, the meaning of "a plurality of" is two or more, unless otherwise specified.

[0136] Any process or method descriptions or descriptions of the flow diagrams in the present disclosure can be understood as representing modules, segments, or portions of code that include one or more executable instructions for implementing specific logical functions or steps in the process, and the scope of the preferred embodiments of the present disclosure includes additional implementation in which the functions are carried out in different orders, in substantially simultaneous fashion, or in reverse order, according to the functions involved, as will be understood by those skilled in the art of the embodiments of the present disclosure.

[0137] It should be understood that portions of the present disclosure can be realized with hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be realized with software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if realized with hardware, and as in another embodiment, any one or a combination of the following technologies known in the art can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0138] Those skilled in the art of the present technology can understand that all or part of the steps carried out by the above-mentioned embodiment methods can be completed by programs instructing related hardware, and the programs can be stored in a computer readable storage medium. When the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0139] In addition, each functional unit in each embodiment of the present disclosure can be integrated into one processing module, or each unit can be physically present separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be realized in the form of hardware or in the form of a software function module. The integrated module, if realized in the form of a software function module and sold or used as an independent product, can also be stored in a computer readable storage medium.

[0140] The above-mentioned storage medium can be a read-only memory, a magnetic disk or an optical disk, etc.

[0141] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present disclosure. In the present specification, the illustrative description of the above terms does not necessarily mean the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0142] Although the embodiments of the present disclosure have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and cannot be understood as limiting the present disclosure, and those skilled in the art can make changes, modifications, replacements and variations to the above-mentioned embodiments within the scope of the present disclosure.

Claims

1. A method for intelligent stripe detection in high-resolution, wide-swath optical images, characterized in that, The method includes: Acquire a high-resolution wide-swath image to be detected, wherein the high-resolution wide-swath image to be detected includes: multiple initial image blocks; At least one candidate image block is determined from the plurality of initial image blocks; A first gray-level histogram corresponding to each candidate image block is determined, and a second gray-level histogram corresponding to the high-resolution wide-width image to be detected is determined based on the first gray-level histogram corresponding to each candidate image block. The target region image is determined from the high-resolution wide-swath image to be detected, and a third gray-level histogram corresponding to the target region image is determined. Determine the degree of matching between the third grayscale histogram and the second grayscale histogram; If the matching degree is determined to be greater than or equal to the matching degree threshold, the target region image is input into the stripe detection model and the quality evaluation model respectively to obtain the stripe detection result output by the stripe detection model and the quality evaluation result output by the quality evaluation model.

2. The method as described in claim 1, characterized in that, The first grayscale histogram includes: the first number of first pixels corresponding to each grayscale level; The step of determining the second grayscale histogram corresponding to the high-resolution wide-area image to be detected based on the first grayscale histogram corresponding to each candidate image block includes: Determine the average number of first quantities corresponding to each gray level in multiple first gray-level histograms; A second grayscale histogram corresponding to the high-resolution wide-area image to be detected is generated based on the average number of first pixels corresponding to each grayscale level.

3. The method as described in claim 1, characterized in that, The size of the high-resolution wide-width image to be detected is h*w; The step of determining the target region image from the high-resolution, wide-swath image to be detected includes: The target region image is determined from the high-resolution, wide-swath image to be detected, with a local image located at the image center and an image size of x*w, where x <h。 4. The method as described in claim 3, characterized in that, The method further includes: If the matching degree is less than the matching degree threshold, the operation of determining the target region image from the high-resolution wide-angle image to be detected is returned, wherein, in the operation of determining the target region image from the high-resolution wide-angle image to be detected, the image size of the target region image is y*w, x... <y。 5. The method as described in claim 1, characterized in that, The model structure of the stripe detection model includes, in sequence: The network consists of a first standard convolutional module (CBL), a first backbone network, a channel-based lightweight recoding module (CLR), a second CBL, and a second backbone network. The quality assessment model structure includes, in sequence: The third CBL, the third backbone network, the fourth backbone network, and the fourth CBL.

6. The method as described in claim 5, characterized in that, The stripe detection model is pre-trained based on a first mapping relationship between the sample high-resolution wide-width image and the labeled stripe detection results corresponding to the sample high-resolution wide-width image. The quality evaluation model is pre-trained based on a second mapping relationship between the sample high-resolution wide-width image and the labeled signal-to-noise ratio corresponding to the sample high-resolution wide-width image.

7. The method according to any one of claims 1-6, characterized in that, Determining at least one candidate image block from the plurality of initial image blocks includes: Determine a second number of second pixels in each of the initial image blocks; If the second quantity is greater than or equal to the quantity threshold, the initial image block corresponding to the second quantity is used as the candidate image block.

8. A high-resolution, wide-swath optical image intelligent stripe detection device, characterized in that, The device includes: The acquisition module is used to acquire a high-resolution wide-swath image to be detected, wherein the high-resolution wide-swath image to be detected includes: multiple initial image blocks; A first determining module is configured to determine at least one candidate image block from the plurality of initial image blocks; The second determining module is used to determine a first gray-level histogram corresponding to each of the candidate image blocks, and to determine a second gray-level histogram corresponding to the high-resolution wide-width image to be detected based on the first gray-level histogram corresponding to each of the candidate image blocks. The third determining module is used to determine the target region image from the high-resolution wide-angle image to be detected, and to determine the third gray-level histogram corresponding to the target region image; The fourth determining module is used to determine the degree of matching between the third grayscale histogram and the second grayscale histogram; The processing module is used to input the target region image into the stripe detection model and the quality evaluation model respectively when the matching degree is determined to be greater than or equal to the matching degree threshold, so as to obtain the stripe detection result output by the stripe detection model and the quality evaluation result output by the quality evaluation model.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, in, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-7.

Images