Map generation method, apparatus and device, and readable medium

Abstract

The embodiment of the invention provides a map generation method and device, equipment and a medium. The method comprises the following steps: acquiring a to-be-processed satellite remote sensing image; a map tile is generated based on the satellite remote sensing image to be processed, and the generation of the map tile comprises the following steps: performing sliding prediction on the satellite remote sensing image to be processed by using a window with a preset size and a preset step length to obtain one or more pixel values corresponding to each pixel point of the map tile; and taking the aggregation value of one or more pixel values corresponding to each pixel point of the map tile as the pixel value of the pixel point in the map tile. Therefore, the time required for generating the map can be shortened, the labor cost is reduced, and the accuracy and timeliness of the map are improved.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computer technology, and more particularly, to a method, apparatus, device, and computer-readable storage medium for map generation. Background Art

[0002] Mapping is usually done by surveying, that is, manually conducting field measurements to draw maps. In the field measurement process, surveying involves multiple links and requires a large amount of data collection, processing and analysis, which takes a long time and has high labor costs. In addition, the accuracy and timeliness of the data are difficult to guarantee. Summary of the invention

[0003] In a first aspect of the present disclosure, a map generation method is provided, comprising: acquiring a satellite remote sensing image to be processed; generating a map tile based on the satellite remote sensing image to be processed, wherein the generation of the map tile comprises: performing sliding prediction on the satellite remote sensing image to be processed with a window of a preset size and a preset step size to obtain one or more pixel values ​​corresponding to each pixel point of the map tile; and using an aggregate value of the one or more pixel values ​​corresponding to each pixel point of the map tile as the pixel value of the pixel point in the map tile.

[0004] In a second aspect of the present disclosure, a map generation device is provided, including: an acquisition module, configured to acquire a satellite remote sensing image to be processed; a generation module, configured to generate a map tile based on the satellite remote sensing image to be processed, wherein the generation of the map tile includes: performing sliding prediction on the satellite remote sensing image to be processed with a window of a preset size and a preset step size to obtain one or more pixel values ​​corresponding to each pixel point of the map tile; and using an aggregate value of the one or more pixel values ​​corresponding to each pixel point of the map tile as the pixel value of the pixel point in the map tile.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The electronic device includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit, and when the instructions are executed by the at least one processing unit, the electronic device executes the method of the first aspect of the present disclosure.

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to perform the method according to the first aspect of the present disclosure.

[0007] In a fifth aspect of the present disclosure, a computer program product is provided, comprising computer executable instructions, wherein the computer executable instructions implement the method according to the first aspect of the present disclosure when executed by a processor.

[0008] It should be understood that the contents described in the summary of the invention are not intended to limit the key features or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In the following, in conjunction with the accompanying drawings and with reference to the following detailed description, the above and other features, advantages and aspects of various implementations of the present disclosure will become more apparent. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;

[0011] Figure 2 A flowchart showing a process of map generation according to some embodiments of the present disclosure;

[0012] Figure 3 A schematic diagram showing a data pair according to some embodiments of the present disclosure;

[0013] Figure 4 A schematic diagram showing the structure of a U-shaped high-resolution network according to some embodiments of the present disclosure;

[0014] Figure 5 A schematic diagram showing a process of training a map generation model according to some embodiments of the present disclosure;

[0015] Figure 6 A block diagram showing an apparatus for map generation according to some embodiments of the present disclosure; and

[0016] Figure 7 A block diagram of an electronic device is shown in which one or more embodiments of the present disclosure may be implemented. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0018] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below.

[0019] It should be noted that the acquisition, storage and application of user personal information involved in the technical solution of the present disclosure are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0020] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0021] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information, so that the user can independently choose whether to provide personal information to software or hardware such as electronic devices, applications, servers or storage media that execute operations of the technical solution of the present disclosure based on the prompt message.

[0022] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information is sent to the user in a manner such as a pop-up window, in which the prompt information can be presented in text form. In addition, the pop-up window can also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0023] As briefly mentioned above, mapping is usually done by surveying, that is, manually conducting field measurements to draw maps. For example, the process of manual field measurements may include the following steps:

[0024] 1) Project preparation, determine the purpose and scope of surveying and mapping, clarify the requirements and constraints of the surveying task, and prepare the surveying and mapping plan;

[0025] 2) Ground control measurement: select some ground control points in the surveying area and measure their coordinates and elevations using surveying instruments such as a global instrument and GPS;

[0026] 3) Remote sensing image acquisition, using aerial photography and satellite remote sensing methods to obtain high-definition images for the extraction of ground features and image correction;

[0027] 4) Ownership investigation, investigating and studying all ownership of land and real estate, including land parcel boundaries, cadastral records, etc.;

[0028] 5) Topographic survey, using surveying instruments to conduct topographic survey, including the measurement and recording of ground features, landforms, etc.;

[0029] 6) Extraction of ground feature: based on remote sensing images or field measurement data, ground feature information can be obtained through image interpretation, point, line and surface feature extraction and other methods;

[0030] 7) Data processing and analysis, quality control, center of gravity calculation, coordinate transformation, etc. of measurement data, and analysis and arrangement of drawings;

[0031] 8) Mapping and report writing: based on the survey results, use relevant software to draw maps and write detailed surveying and mapping reports;

[0032] 9) Quality inspection and correction: conduct quality inspection on the drawn maps and reports, correct any problems found, and ensure the accuracy and completeness of the maps;

[0033] 10) Map delivery and archiving: deliver completed maps and reports to customers or relevant departments and archive them for safekeeping.

[0034] In the above-mentioned method, surveying and mapping involves multiple links, requiring a large amount of data collection, processing and analysis, which takes a long time and has high labor costs. In addition, surveying and mapping involves multiple measurement links, and any error in any link will directly affect the accuracy of the map; when the map changes (such as new buildings or roads), these changes cannot be reflected in the surveying and mapping map in a timely manner, making it difficult to ensure the timeliness of the map.

[0035] The embodiments of the present disclosure provide a solution for map generation. In various embodiments of the present disclosure, a satellite remote sensing image to be processed can be obtained, and a map tile can be generated based on the satellite remote sensing image to be processed. Among them, the generation of map tiles may include the following steps: sliding prediction of the satellite remote sensing image to be processed with a window of a preset size and a preset step size to obtain one or more pixel values ​​corresponding to each pixel point of the map tile; and using the aggregate value of one or more pixel values ​​corresponding to each pixel point of the map tile as the pixel value of the pixel point in the map tile. In this way, the time required for map generation can be shortened, labor costs can be reduced, and the accuracy and timeliness of the map can be improved.

[0036] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

[0037] Figure 1 1 is a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. Figure 1As shown, the environment 100 includes a server 110 and image acquisition devices 120-1, 120-2, ..., 120-N. For ease of discussion, the image acquisition devices 120-1, 120-2, ..., 120-N may be collectively or individually referred to as image acquisition devices 120.

[0038] The image acquisition device 120 may be a high-altitude device such as a drone, an airplane, or a satellite. The image acquisition device 120 may acquire remote sensing images of the ground and send the acquired remote sensing images to the server 110. The server 110 may generate a map based on the received remote sensing images.

[0039] The server 110 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, and big data and artificial intelligence platforms. The server 110 may include, for example, a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like.

[0040] The communication connection between the server 110 and the image acquisition device 120 can be established in a wired manner or a wireless manner. The communication connection may include, but is not limited to, a Bluetooth connection, a mobile network connection, a Universal Serial Bus (USB) connection, a Wireless Fidelity (WiFi) connection, etc., and the embodiments of the present disclosure are not limited in this respect.

[0041] It should be understood that Figure 1 The components and arrangements in the environment 100 shown are merely examples, and a computing system suitable for implementing the exemplary implementation described in the present disclosure may include one or more different components, other components, and / or different arrangements. The implementation of the present disclosure is not limited in this respect.

[0042] Some example embodiments of the present disclosure will be described below with continued reference to the accompanying drawings.

[0043] Figure 2 FIG. 2 is a flowchart of a map generation process 200 according to some embodiments of the present disclosure. Figure 1 For example, the map generation process 200 may be implemented by the server 110 .

[0044] In block 210 , the server 110 acquires a satellite remote sensing image to be processed.

[0045] Satellite remote sensing images refer to images obtained by aerial photography of the earth's surface by the image acquisition device 120 from an aerial perspective. The images can cover various geographical features, such as artificial landmarks, natural mountains and rivers, etc. With the improvement of resolution, satellite remote sensing images can provide detailed features of smaller-scale objects.

[0046] In some embodiments, the server 110 may obtain the satellite remote sensing image to be processed from the image acquisition device 120. In other embodiments, the image acquisition device 120 may send the acquired satellite remote sensing image to other devices, and the server 110 may obtain the satellite remote sensing image to be processed from the other devices.

[0047] In block 220 , the server 110 generates map tiles based on the satellite remote sensing image to be processed.

[0048] Specifically, the server 110 performs sliding prediction on the satellite remote sensing image to be processed with a window of preset size and a preset step size to obtain one or more pixel values ​​corresponding to each pixel point of the map tile, and uses the aggregate value of the one or more pixel values ​​corresponding to each pixel point of the map tile as the pixel value of the pixel point in the map tile.

[0049] For example, the server 110 may start from the upper left corner of the satellite remote sensing image to be processed, and extract multiple satellite remote sensing sub-images in sequence from left to right with a window of a predetermined size and a preset step size. After the extraction is completed, the window of the predetermined size may be moved downward by a preset step size from the upper left corner, and multiple satellite remote sensing sub-images may be extracted in sequence from left to right. In this way, the entire satellite remote sensing image to be processed is processed to obtain multiple satellite remote sensing sub-images. The server 110 may determine the pixel value of each pixel in each satellite remote sensing sub-image respectively to determine one or more pixel values ​​corresponding to each pixel of the map tile, and use the aggregate value of the one or more pixel values ​​corresponding to each pixel of the map tile as the pixel value of the pixel in the map tile, thereby obtaining the map tile. For example, the window of the predetermined size may be a window of 1024×1024, and the preset step size may be 512.

[0050] In some embodiments, the aggregate value may be an average value, a median value, or a value randomly selected from a plurality of pixel values.

[0051] In some embodiments, the server 110 may generate map tiles based on the satellite remote sensing images to be processed by means of a trained map generation model. The trained map generation model may be deployed in the server 110, or the server 110 may call the trained map generation model from outside.

[0052] Taking the training process of the map generation model executed by the server 110 as an example, the server 110 can obtain multiple sample satellite remote sensing images and sample map tiles corresponding to each of the multiple sample satellite remote sensing images, form a data pair with each sample satellite remote sensing image and the sample map tile corresponding to the sample satellite remote sensing image, and then process each data pair to generate training samples.

[0053] For example, see Figure 3 , Figure 3 An example of a data pair 300 is shown. Figure 3 In the figure, the left side is a sample satellite remote sensing image, and the right side is a sample map tile corresponding to the sample satellite remote sensing image.

[0054] The server 110 may cut the sample satellite remote sensing image and the sample map tile in each data pair into a predetermined size, thereby obtaining a corresponding sample satellite remote sensing image of a predetermined size and a sample map tile of a predetermined size. For example, the predetermined size may be 1024×1024. For example, the server 110 may cut the sample satellite remote sensing image and the sample map tile in a convolution manner.

[0055] In some embodiments, to ensure the edge effect of the sample satellite remote sensing image, the server 110 may fill the sample satellite remote sensing image. For example, a predetermined number of pixels may be filled at the edge of the sample satellite remote sensing image. For example, 100 black pixels may be filled at the upper edge, lower edge, left edge, and right edge of the sample satellite remote sensing image, respectively.

[0056] The server 110 may determine the corresponding sample satellite remote sensing image of a predetermined size and the sample map tile of a predetermined size as a training sample, and train the map generation model based on the multiple training samples.

[0057] In some embodiments, the map generation model may include a feature extraction network and a conditional generative adversarial network (cGAN) connected to the feature extraction network. The conditional generative adversarial network may include a generator and a discriminator, the generator may be used to generate corresponding map tiles based on satellite remote sensing images, and the discriminator may be used to classify the generated images, for example, classifying the generated images as satellite remote sensing images or map tiles. The generator may be connected to the vital signs extraction network.

[0058] In some embodiments, the feature extraction network may use a U-shaped High-Resolution Network (U-HRNet). Since lower-resolution satellite remote sensing images often contain stronger speech information, they need to go through more layers to fuse with higher-resolution satellite remote sensing images; and for higher-resolution satellite remote sensing images, the computational cost of each convolutional layer is large, so a U-shaped high-resolution network is used to extract features of sample satellite remote sensing images, so that more stages are added after the sample satellite remote sensing images with stronger semantic representation, relaxing the constraint that all resolutions need to perform parallel computations on the newly added stages.

[0059] For example, the network structure of the U-shaped high-resolution network can be seen in Figure 4 , Figure 4 A schematic diagram of a structure 400 of a U-shaped high-resolution network is shown in FIG. Figure 4 As shown, when the U-shaped high-resolution network extracts features from sample satellite remote sensing images, it can be implemented through stage 1 (Stage 1), stage 2 (Stage 2), stage 3 (Stage 3), stage 4 (Stage 4), stage 5 (Stage 5), stage 6 (Stage 6), stage 7 (Stage 7), stage 8 (Stage 8) and stage 9 (Stage 9). For example, the sample satellite remote sensing image is downsampled through stages 1, 2, 3, 4 and 5, and the sample satellite remote sensing image is upsampled through stages 6, 7, 8 and 9, and stage 6 can fuse the image obtained in stage 4, stage 7 can fuse the image obtained in stage 3, and stage 8 can fuse the image obtained in stage 2. Note that Figure 4 What is provided is only an example network structure. In other embodiments, any other appropriate network structure may be configured according to actual needs.

[0060] In some embodiments, the generator may include a series of encoder-decoders of U-Net structures. Both the encoder and the decoder may include a convolution layer, a random inactivation layer, a batch normalization layer, and an activation layer. When generating an image, the generator may downsample the sample satellite remote sensing image processed by the feature extraction network to generate a feature vector, and then upsample the feature vector to generate an image to be classified for classification by the discriminator.

[0061] In some embodiments, the discriminator may be a Markovian discriminator.

[0062] The discriminator can ensure the authenticity of the generated image at high frequencies. For example, by dividing the input image into multiple NxN image blocks, and then performing the discriminator's authenticity judgment on each image block, different image blocks are parallelized through channels. Such an operation actually implies an assumption: the pixels between more than one image block are independent, which is equivalent to the discriminator modeling the image blocks obtained by segmentation according to the Markov random field (MRF). Considering the high frequency and locality of the discriminator, it can be understood as a loss of texture / detailed style. Therefore, the loss function of the discriminator is as follows:

[0063] Among them, D(x,y) represents the discrimination result of the discriminator on the sample satellite remote sensing image, D(x,G(x,z)) represents the discrimination result of the discriminator on the generated image, x represents the sample satellite remote sensing image, y represents the sample map tile, and z represents random noise. Represents the average of the absolute differences between the sample satellite remote sensing image and the sample map tile, Represents the average of the absolute differences between sample satellite remote sensing images and random noise.

[0064] In order to further improve the quality of the generated image, additional loss terms can be added to the above loss function. For example, L1 loss. The L1 loss is as follows:

[0065] Among them, f(x i ) represents the generated image generated by the generator based on the i-th sample satellite remote sensing image, y i represents the i-th sample map tile, n represents the number of samples, and MAE represents the mean absolute error.

[0066] Figure 5 A schematic diagram of a process 500 of training a map generation model according to some embodiments of the present disclosure is shown. For example, the process of training a map generation model may be implemented by the server 110 .

[0067] like Figure 5As shown, the server 110 inputs a plurality of sample satellite remote sensing images of predetermined sizes into a feature extraction network, and the feature extraction network inputs the extracted features into the generator 510, so that the generator 510 outputs a plurality of generated images. Further, the server 110 determines a plurality of sample satellite remote sensing images of predetermined sizes and a plurality of generated images as a plurality of first image pairs, and determines a plurality of sample satellite remote sensing images of predetermined sizes and a plurality of map tiles of predetermined sizes as a plurality of second image pairs. Further, the server 110 trains the discriminator 520 through a plurality of first image pairs, a plurality of first image pairs respectively corresponding to a first predetermined label, a plurality of second image pairs, and a plurality of second image pairs respectively corresponding to a second predetermined label. It should be understood that when training the discriminator 520, the parameters of the generator 510 are fixed.

[0068] After training the discriminator 520, the server 110 can train the feature extraction network and the generator 510 through a plurality of sample satellite remote sensing images of a predetermined size and the trained discriminator 520 to obtain a map generation model. It should be understood that when training the generator 510, the parameters of the discriminator 520 are fixed.

[0069] Therefore, the server 110 can use the trained map generation model to generate corresponding map tiles based on the satellite remote sensing images to be processed. Compared with the manual surveying method, it can shorten the time required for map generation, reduce labor costs, and improve the accuracy and timeliness of the map.

[0070] Figure 6 FIG. 6 is a block diagram of a map generating apparatus 600 according to some embodiments of the present disclosure. The apparatus 600 may be implemented as or include the server 110 .

[0071] The device 600 includes an acquisition module 610 configured to acquire a satellite remote sensing image to be processed; and a generation module 620 configured to generate a map tile based on the satellite remote sensing image to be processed. The generation of the map tile includes: performing sliding prediction on the satellite remote sensing image to be processed with a window of a preset size and a preset step length to obtain one or more pixel values ​​corresponding to each pixel point of the map tile; and using the aggregate value of the one or more pixel values ​​corresponding to each pixel point of the map tile as the pixel value of the pixel point in the map tile.

[0072] In some embodiments, the trained map generation model is configured to generate map tiles based on the satellite remote sensing images to be processed, and the map generation model is trained based on multiple training samples, each training sample including a corresponding sample satellite remote sensing image of a predetermined size and a sample map tile of a predetermined size.

[0073] In some embodiments, the device 600 also includes a training module configured to obtain a plurality of sample satellite remote sensing images and a plurality of sample map tiles that correspond one to one; segment each sample satellite remote sensing image to obtain a plurality of sample satellite remote sensing images of a predetermined size; segment each sample map tile to obtain a plurality of sample map tiles of a predetermined size; and determine a plurality of training samples based on the plurality of sample satellite remote sensing images of a predetermined size and the plurality of sample map tiles of a predetermined size.

[0074] In some embodiments, the map generation model includes a feature extraction network and a conditional adversarial generation network connected to the feature extraction network, and the training module is further configured to input a plurality of sample satellite remote sensing images of a predetermined size into the feature extraction network so that a generator of the conditional adversarial generation network outputs a plurality of generated images; determine a plurality of sample satellite remote sensing images of a predetermined size and a plurality of generated images as a first image pair, and determine a plurality of sample satellite remote sensing images of a predetermined size and a plurality of map tiles of a predetermined size as a plurality of second image pairs; train a discriminator of the conditional adversarial generation network through the plurality of first image pairs and the plurality of second image pairs; and train the feature extraction network and the generator in the conditional adversarial generation network through the plurality of sample satellite remote sensing images of a predetermined size and the trained discriminator to obtain a map generation model.

[0075] In some embodiments, the training module is further configured to train a discriminator of the conditional adversarial generation network through a plurality of first image pairs, first predetermined labels corresponding to each of the plurality of first image pairs, a plurality of second image pairs, and second predetermined labels corresponding to each of the plurality of second image pairs.

[0076] In some embodiments, the feature extraction network comprises a U-shaped high-resolution network.

[0077] The modules included in the device 600 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units can be implemented using software and / or firmware, such as machine executable instructions stored on a storage medium. In addition to or as an alternative to machine executable instructions, some or all of the units in the device 600 can be implemented at least in part by one or more hardware logic components. As an example and not limitation, exemplary types of hardware logic components that can be used include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0078] Figure 7 1 shows a block diagram of an electronic device 700 in which one or more embodiments of the present disclosure may be implemented. It should be understood that Figure 7The electronic device 700 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein.

[0079] like Figure 7 As shown, the electronic device 700 is in the form of a general electronic device. The components of the electronic device 700 may include, but are not limited to, one or more processors or processing units 710, a memory 720, a storage device 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. The processing unit 710 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 720. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 700.

[0080] The electronic device 700 typically includes a plurality of computer storage media. Such media can be any available media accessible to the electronic device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 720 can be a volatile memory (e.g., register, cache, random access memory (RAM)), a non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory) or some combination thereof. The storage device 730 can be a removable or non-removable medium, and can include a machine-readable medium, such as a flash drive, a disk, or any other medium, which can be used to store information and / or data and can be accessed within the electronic device 700.

[0081] The electronic device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 7 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 720 may include a computer program product 725 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0082] The communication unit 740 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 700 can be implemented with a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 700 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0083] The input device 750 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 760 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 700 may also communicate with one or more external devices (not shown) through the communication unit 740 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 700, or communicate with any device that allows the electronic device 700 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0084] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which one or more computer instructions are stored, wherein the one or more computer instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0085] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0086] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0087] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0088] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0089] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the marketplace, or to enable other persons of ordinary skill in the art to understand the implementations disclosed herein.

Claims

1. A map generation method, comprising: Obtain satellite remote sensing images to be processed; Based on the satellite remote sensing image to be processed, a map tile is generated, wherein the generation of the map tile includes: Perform sliding prediction on the satellite remote sensing image to be processed with a window of a preset size and a preset step size to obtain one or more pixel values ​​corresponding to each pixel point of the map tile; as well as An aggregate value of one or more pixel values ​​corresponding to each pixel point of the map tile is used as the pixel value of the pixel point in the map tile.

2. The method according to claim 1, wherein the trained map generation model is configured to generate map tiles based on the satellite remote sensing image to be processed, and The map generation model is trained based on multiple training samples, each training sample includes a corresponding sample satellite remote sensing image of a predetermined size and a sample map tile of a predetermined size.

3. The method according to claim 2, wherein the plurality of training samples are determined as follows: Obtaining multiple sample satellite remote sensing images and multiple sample map tiles in one-to-one correspondence; Segmenting each sample satellite remote sensing image to obtain a plurality of sample satellite remote sensing images of the predetermined size; Segmenting each sample map tile to obtain a plurality of sample map tiles of the predetermined size; as well as The plurality of training samples are determined based on the plurality of sample satellite remote sensing images of the predetermined size and the plurality of sample map tiles of the predetermined size.

4. The method according to claim 2, wherein the map generation model comprises a feature extraction network and a conditional adversarial generation network connected to the feature extraction network, and wherein the map generation model is trained as follows: Inputting the plurality of sample satellite remote sensing images of the predetermined size into the feature extraction network, so that the generator of the conditional adversarial generation network outputs a plurality of generated images; Determine the plurality of sample satellite remote sensing images of the predetermined size and the plurality of generated images as a plurality of first image pairs, and determine the plurality of sample satellite remote sensing images of the predetermined size and the plurality of map tiles of the predetermined size as a plurality of second image pairs; Training a discriminator of the conditional adversarial generation network through the plurality of first image pairs and the plurality of second image pairs; as well as The map generation model is obtained by training the feature extraction network and the generator in the conditional adversarial generation network using a plurality of sample satellite remote sensing images of the predetermined size and the trained discriminator.

5. The method according to claim 4, wherein training a discriminator of the conditional adversarial generative network through the plurality of first image pairs and the plurality of second image pairs comprises: The discriminator of the conditional adversarial generation network is trained by using the plurality of first image pairs, the first predetermined labels corresponding to the plurality of first image pairs, the plurality of second image pairs, and the second predetermined labels corresponding to the plurality of second image pairs.

6. The method of claim 4, wherein the feature extraction network comprises a U-shaped high-resolution network.

7. A map generating device, comprising: An acquisition module is configured to acquire a satellite remote sensing image to be processed; A generation module is configured to generate a map tile based on the satellite remote sensing image to be processed, wherein the generation of the map tile includes: Perform sliding prediction on the satellite remote sensing image to be processed with a window of a preset size and a preset step size to obtain one or more pixel values ​​corresponding to each pixel point of the map tile; as well as An aggregate value of one or more pixel values ​​corresponding to each pixel point of the map tile is used as the pixel value of the pixel point in the map tile.

8. An electronic device comprising: at least one processing unit; as well as At least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the electronic device to perform the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 6.

10. A computer program product comprising computer executable instructions, wherein the computer executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 6.

Images