CN114283343B

CN114283343B - Map updating method, training method and device based on remote sensing satellite image

Info

Publication number: CN114283343B
Application number: CN202111567400.7A
Authority: CN
Inventors: 王紫玉; 吴彬; 钟开; 杨建忠; 张通滨; 卢振
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2021-12-20
Filing date: 2021-12-20
Publication date: 2023-09-26
Anticipated expiration: 2041-12-20
Also published as: CN114283343A

Abstract

The disclosure provides a map updating method, training method and device based on remote sensing satellite images, relates to the field of data processing, and particularly relates to the technical field of road networks. The specific implementation scheme is as follows: acquiring a remote sensing satellite image; carrying out semantic segmentation processing on the remote sensing satellite image to obtain a first topological graph, wherein the first topological graph comprises a road at a position corresponding to the remote sensing satellite image; determining a three-dimensional tensor map according to the remote sensing satellite image, wherein the three-dimensional tensor map represents the coding information of the road at the position corresponding to the remote sensing satellite image; decoding the three-dimensional tensor map to obtain a second topological map, wherein the second topological map comprises roads at positions corresponding to the remote sensing satellite images; and determining a road topological graph according to the first topological graph and the second topological graph, and updating the map according to the road topological graph.

Description

Map updating method, training method and device based on remote sensing satellite image

Technical Field

The disclosure relates to the technical field of road networks in the field of data processing, in particular to a map updating method, a training method and a device based on remote sensing satellite images.

Background

With the development of mobile internet and intelligent devices, maps have become an important basis for people to travel. The roads in the road network change, and the map needs to be updated.

In the prior art, the data of the road can be manually collected according to the collection equipment, and then the map is updated based on the data of the road.

However, in the prior art, a great deal of manpower and material resources are required to be consumed for manually collecting the data of the road, so that the cost for updating the map is higher; moreover, the operation efficiency of the mode is low, errors are easy to occur, and the map updating is not timely and is wrong.

Disclosure of Invention

The disclosure provides a map updating method, a training method and a device based on remote sensing satellite images.

According to a first aspect of the present disclosure, there is provided a map updating method based on remote sensing satellite images, including:

acquiring a remote sensing satellite image;

carrying out semantic segmentation processing on the remote sensing satellite image to obtain a first topological graph, wherein the first topological graph comprises roads at positions corresponding to the remote sensing satellite image; determining a three-dimensional tensor map according to the remote sensing satellite image, wherein the three-dimensional tensor map represents the coding information of the road at the position corresponding to the remote sensing satellite image;

Decoding the three-dimensional tensor map to obtain a second topological map, wherein the second topological map comprises roads at positions corresponding to the remote sensing satellite images;

and determining a road topological graph according to the first topological graph and the second topological graph, and updating a map according to the road topological graph.

According to a second aspect of the present disclosure, there is provided a training method of a graph coding model applied to map updating, including:

acquiring a plurality of remote sensing satellite images to be trained, wherein the remote sensing satellite images to be trained have a standard three-dimensional tensor graph;

repeating the following steps until reaching the preset condition: inputting the remote sensing satellite image to be trained into a graph coding model to obtain a predicted three-dimensional tensor graph, wherein the predicted three-dimensional tensor graph represents coding information of a road at a position corresponding to the remote sensing satellite image to be trained; parameter adjustment is carried out on the graph coding model according to the predicted three-dimensional tensor graph and the standard three-dimensional tensor graph;

the map coding model obtained when the preset condition is reached is used for determining a three-dimensional tensor map of the remote sensing satellite image in the method of the first aspect of the disclosure.

According to a third aspect of the present disclosure, there is provided a map updating apparatus based on a remote sensing satellite image, including:

the acquisition unit is used for acquiring remote sensing satellite images;

the first determining unit is used for carrying out semantic segmentation processing on the remote sensing satellite image to obtain a first topological graph, wherein the first topological graph comprises a road at a position corresponding to the remote sensing satellite image; determining a three-dimensional tensor map according to the remote sensing satellite image, wherein the three-dimensional tensor map represents the coding information of the road at the position corresponding to the remote sensing satellite image;

the second determining unit is used for decoding the three-dimensional tensor graph to obtain a second topological graph, wherein the second topological graph comprises a road at a position corresponding to the remote sensing satellite image;

and the third determining unit is used for determining a road topological graph according to the first topological graph and the second topological graph and updating a map according to the road topological graph.

According to a fourth aspect of the present disclosure, there is provided a training device of a graph coding model applied to map updating, including:

the first acquisition unit is used for acquiring a plurality of remote sensing satellite images to be trained, wherein the remote sensing satellite images to be trained have a standard three-dimensional tensor map;

A first determining unit, configured to repeat the following steps until a preset condition is reached: inputting the remote sensing satellite image to be trained into a graph coding model to obtain a predicted three-dimensional tensor graph, wherein the predicted three-dimensional tensor graph represents coding information of a road at a position corresponding to the remote sensing satellite image to be trained; parameter adjustment is carried out on the graph coding model according to the predicted three-dimensional tensor graph and the standard three-dimensional tensor graph;

the map coding model obtained when the preset condition is reached is used for determining a three-dimensional tensor map of the remote sensing satellite image in the device according to the third aspect of the disclosure.

According to a fifth aspect of the present disclosure, there is provided a computer device comprising: at least one processor; and

a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first or second aspect.

According to a sixth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of the first or second aspect.

According to a seventh aspect of the present disclosure, there is provided a computer program product comprising: a computer program stored in a readable storage medium, from which the computer program can be read by at least one processor of a computer device, the at least one processor executing the computer program causing the computer device to perform the method of the first or second aspect.

The technology solves the problems of high map updating cost and map updating errors caused by manual road data acquisition.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a schematic diagram according to a first embodiment of the present disclosure;

FIG. 2 is a schematic illustration of a remote sensing satellite image according to a first embodiment of the present disclosure;

FIG. 3 is a schematic diagram according to a second embodiment of the present disclosure;

FIG. 4 is a schematic diagram of a local feature map generation process according to a second embodiment of the present disclosure;

FIG. 5 is a schematic diagram according to a third embodiment of the present disclosure;

FIG. 6 is a schematic diagram according to a fourth embodiment of the present disclosure;

FIG. 7 is a schematic diagram of a user labeling road keypoints in a remote sensing satellite image to be trained according to a fourth embodiment of the disclosure;

FIG. 8 is a diagram showing statistics of the number of other road keypoints adjacent to a pixel point of the road keypoint according to a fourth embodiment of the disclosure;

FIG. 9 is a three-dimensional tensor map and encoded data for each pixel of a remote sensing satellite image to be trained according to a fourth embodiment of the present disclosure;

FIG. 10 is a schematic diagram according to a fifth embodiment of the present disclosure;

FIG. 11 is a schematic diagram according to a sixth embodiment of the present disclosure;

FIG. 12 is a schematic diagram according to a seventh embodiment of the present disclosure;

FIG. 13 is a schematic diagram according to an eighth embodiment of the disclosure;

FIG. 14 is a schematic diagram according to a ninth embodiment of the disclosure;

FIG. 15 is a schematic diagram according to a tenth embodiment of the present disclosure;

FIG. 16 is a block diagram of a computer device used to implement a remote sensing satellite image based map updating method of an embodiment of the present disclosure;

FIG. 17 is a block diagram of a computer device used to implement a training method of a graph coding model applied to map updating in accordance with an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

The present disclosure is applicable to a scenario where map information is collected, some road information may be missing in the current map information, especially internal roads, i.e. some roads in a cell. If the remote sensing satellite images are processed by semantic segmentation alone or by image coding alone, the problem of incomplete recalled map information can occur.

The disclosure provides a map updating method, training method and device based on remote sensing satellite images, which are applied to the technical field of road networks in the field of data processing and are used for solving the problems of higher map updating cost and map updating errors caused by manual road data acquisition.

Fig. 1 is a schematic diagram according to a first embodiment of the present disclosure, as shown in fig. 1, fig. 1 shows a map updating method based on a remote sensing satellite image, the method including:

s101, acquiring a remote sensing satellite image.

Illustratively, the remote sensing satellite image refers to films or photos for recording electromagnetic wave sizes of various ground objects, and has high resolution, wherein the resolution includes spatial resolution, spectral resolution, radiation resolution and time resolution. The spatial resolution is the size or the dimension of the minimum unit which can be distinguished in detail on the remote sensing satellite image, or refers to the measurement of the minimum angle or the linear distance of the remote sensor for distinguishing two targets. Spectral resolution refers to the minimum wave separation that a remote sensor can resolve when receiving target radiation. The radiation resolution is the minimum difference in irradiance that a remote sensor sensing element can resolve when receiving a spectral signal. The time resolution is a performance index related to the time interval of remote sensing satellite images.

S102, carrying out semantic segmentation processing on a remote sensing satellite image to obtain a first topological graph, wherein the first topological graph comprises a road at a position corresponding to the remote sensing satellite image; and determining a three-dimensional tensor map according to the remote sensing satellite image, wherein the three-dimensional tensor map represents the coding information of the road at the position corresponding to the remote sensing satellite image.

Illustratively, the semantic segmentation process refers to segmenting the remote sensing satellite image according to regions, wherein each region is composed of pixel points with the same attribute. The semantic segmentation process can be divided into an encoder network and a decoder network, wherein the encoder network is a pre-trained classification network, and the decoder network projects the recognition feature semantics learned by the encoder onto a pixel space to obtain dense classification. Further, the speech segmentation process requires not only differentiation at the pixel level, but also a mechanism to project the differentiating features learned by the encoder at different stages onto the pixel space. For example, FIG. 2 shows a schematic representation of a remote sensing satellite image. The road structure of the ground can be seen by analyzing the remote sensing satellite image of fig. 2.

After the remote sensing satellite image shown in fig. 2 is subjected to semantic segmentation, a first topological graph can be obtained. The first topological graph can represent the limit of a road and a background in a remote sensing satellite image.

In this embodiment, the three-dimensional tensor chart characterizes the encoded information of the road at the position corresponding to the remote sensing satellite image. The three-dimensional tensor graph refers to an image consisting of three parts, and can characterize parameters of a remote sensing satellite image. The first part can represent whether the current pixel point is a road key point, the second part can represent whether the current pixel point has an adjacent road key point, and the third part can represent the position relation between the current pixel point and other pixel points, wherein the position relation can be the position offset of the current pixel point and the other pixel points.

And S103, decoding the three-dimensional tensor graph to obtain a second topological graph, wherein the second topological graph comprises roads at positions corresponding to the remote sensing satellite images.

Illustratively, the decoding process of the three-dimensional tensor map is to reversely interpret the coded data bits of the three parts of the three-dimensional tensor map according to the meaning of the coded data bits of each part, so as to obtain a second topological map. The second topological graph can also represent the limit of a road and a background in the remote sensing satellite image.

S104, determining a road topological graph according to the first topological graph and the second topological graph, and updating the map according to the road topological graph.

The first topology map and the second topology map are compared, differences between the first topology map and the second topology map are determined, and a road topology map is obtained according to the differences between the first topology map and the second topology map. After the road topology map is obtained, the map is updated by the latest road topology map.

The present disclosure provides a map updating method based on remote sensing satellite images, comprising: the method comprises the steps of acquiring historical positioning information of a vehicle on a historical track, determining weight information of a frame according to the strength of a positioning signal corresponding to the frame indicated by global positioning information of the frame, and determining optimized positioning information of the frame according to the global positioning information of the frame, the inter-frame positioning information and the weight information. Through the technical scheme, the problems of high map updating cost and map updating errors caused by manual road data acquisition can be solved.

Fig. 3 is a schematic diagram according to a second embodiment of the present disclosure, and as shown in fig. 3, fig. 3 shows a map updating method based on a remote sensing satellite image, the method including:

s301, acquiring a remote sensing satellite image.

For example, this step may refer to step S101, which is not described herein.

S302, carrying out semantic segmentation processing on the remote sensing satellite image to obtain a first topological graph, wherein the first topological graph comprises roads at positions corresponding to the remote sensing satellite image.

For example, this step may refer to step S102, which is not described herein.

S303, inputting the remote sensing satellite image into a graph coding model to obtain a three-dimensional tensor graph; the image coding model is obtained by training based on remote sensing satellite images with standard three-dimensional tensor images.

The image coding model is a model for outputting a three-dimensional tensor image, and a plurality of remote sensing satellite images to be identified are input into the image coding model, so that the three-dimensional tensor image corresponding to each remote sensing satellite image to be identified can be obtained respectively. Wherein, the graph coding model is obtained by training in advance. The advantage of this arrangement is that the end-to-end input and output can be achieved using the graph coding model, and the three-dimensional tensor graph corresponding to the remote sensing satellite image can be rapidly output.

Illustratively, inputting the remote sensing satellite image into the image coding model to obtain a three-dimensional tensor image, including:

performing feature extraction on the remote sensing satellite image based on the image coding model to obtain a global feature image and a local feature image; the global feature map characterizes global features of the remote sensing satellite image, and the local feature map characterizes road features of the remote sensing satellite image;

feature fusion is carried out on the global feature map and the local feature map based on the map coding model, and a fused feature map is obtained;

and generating a three-dimensional tensor graph according to the fused feature graph.

Illustratively, the global feature map is an overall feature that is used to describe color features, texture features, and/or shape features of the remote sensing satellite image. The local feature map is used for describing local features of the remote sensing satellite image, and specifically, features extracted from the remote sensing satellite image, including edges, corner points, lines, curves, areas with special properties and the like. The local feature map has small correlation among features, and detection and matching of other local features cannot be affected due to disappearance of part of local features under the shielding condition. The global feature map and the local feature map are fused through the map coding model, the fused feature map consists of the global feature map and the local feature map, and the global feature map and the local feature map are not modified by the fused feature map, but are taken as a whole. And generating a corresponding three-dimensional tensor image from the remote sensing satellite image according to the fused characteristic image. The method has the advantages that the global features and the local features of the remote sensing satellite images can be fully combined, and the information of the generated three-dimensional tensor image is more accurate and rich.

Illustratively, performing feature extraction on a remote sensing satellite image based on a graph coding model to obtain a global feature graph and a local feature graph, including:

performing feature extraction on the remote sensing satellite image based on the image coding model to obtain a global feature image;

binarizing the global feature map to obtain a binarized feature map, wherein the binarized feature map comprises features of roads;

determining a road position area corresponding to the road point in the global feature map based on the road point in the binarized feature map; and generating a local feature map according to the road position area corresponding to the road point.

After the global feature map is obtained, binarization processing is carried out on the global feature map, the road points in the global feature map are taken as 1, the non-road points in the global feature map are taken as 0, the binarization feature map is obtained, one road point is selected at will in the binarization feature map, the corresponding road point is found in the global feature map, and the road position area is determined by the road point, wherein the number and the shape of the road position area are not limited. For example, the road location area may be a circle defined by taking the road point as a center and taking a preset distance as a radius, and the circle is taken as the road location area of the road point. The road point may be taken as a centroid, 4 rectangles are taken in a preset range, and the 4 rectangles are taken as road position areas of the road point. It should be noted that the road location area is a range including the road point, and the dividing standard of the range is not limited. In particular, reference may be made to a schematic diagram of a local feature map generation process shown in fig. 4. As can be seen from the figure, after the remote sensing satellite image a outputs the global feature map a through the first layer neural network model of the map coding model, binarizing the global feature map a to obtain a binarized feature map B, selecting a road point C from the binarized feature map B, and determining a road position area in the global feature map a, wherein the road position area in the figure is 4 rectangles.

The method has the advantages that the global characteristic diagram and the local characteristic diagram are respectively acquired through the two-layer neural network model structure in the diagram coding model, so that the information acquired by the method is more comprehensive than the information acquired by a single-layer neural network model.

Illustratively, feature fusion is performed on the global feature map and the local feature map based on the map coding model, so as to obtain a fused feature map, which comprises the following steps:

performing up-sampling treatment on the local feature map to obtain an up-sampled local feature map; the size of the local feature map after upsampling is the same as the size of the global feature map;

and carrying out feature fusion on the global feature map and the up-sampled local feature map based on the map coding model to obtain a fused feature map.

The upsampling process is, illustratively, to generate the same number of samples as the number of samples with a larger data amount, with the number of samples with a smaller data amount being the standard. For example, in the present embodiment, the local feature map may be 4×4×n, and the global feature map may be 8×8×n, and the local feature map obtained by upsampling the local feature map with the global feature map as a standard is 8×8×n. And (3) obtaining a fused characteristic diagram 8 x (N+n) based on the diagram coding model by combining the up-sampled local characteristic diagram 8 x N with the global characteristic diagram 8 x N. The advantage of this arrangement is that the global feature map and the local feature map can be compared in the same dimension, which is a more reasonable way.

S304, decoding the three-dimensional tensor map to obtain a second topological map, wherein the second topological map comprises roads at positions corresponding to the remote sensing satellite images.

For example, this step may refer to step S103, which is not described herein.

S305, if the road pixel points in the first topological graph are determined to be not in the second topological graph, the road pixel points in the first topological graph are added into the second topological graph, so that the road topological graph is generated.

The method includes the steps of searching for a road pixel point in a first topological graph according to coordinate information in the first topological graph, adding the road pixel point in the first topological graph to a second topological graph if the coordinate information is a non-road pixel point in the second topological graph, and taking the modified second topological graph as the road topological graph.

For example, if the coordinate information a (a, b) in the first topological graph is a road pixel, searching whether the pixel of the coordinate information a (a, b) is a road pixel in the second topological graph, if so, not performing any processing on the second topological graph, and if not, adding the pixel of the coordinate information a (a, b) in the second topological graph as the road pixel. It should be noted that the division criteria of the coordinate information in the second topological graph and the first topological graph are the same, for example, the lower left corners of the first topological graph and the second topological graph are all the origins, the lowest horizontal edge of the first topological graph and the second topological graph is the x-axis, and the leftmost vertical edge of the first topological graph and the second topological graph is the y-axis. The road topology map combining method has the advantages that the road topology map can be comprehensively determined by combining the two topology maps, and the problem that one topology map is insufficient in recall of the road can be solved.

Further, the first topological graph is a binary graph, and the second topological graph is a binary graph. The advantage of this arrangement is that the efficiency of the comparison of the first and second topology can be improved.

S306, performing image enhancement processing on the road topological graph to obtain the enhanced road topological graph.

The image enhancement process may be classified into spatial and frequency domain based methods, for example, depending on the space in which the process is located. The method based on the airspace directly processes the road topological graph; the frequency domain-based method is to correct the transformation coefficient of the road topological graph in a certain transformation domain of the road topological graph, and then inversely transform the transformation coefficient into the original airspace to obtain the road topological graph after the enhancement processing. The arrangement has the advantages that the visual effect of the road topological graph is improved, and the definition of the road topological graph is improved; or aiming at the application occasion of the road topological graph, some interesting features are highlighted, and uninteresting features are restrained, so that the differences among different object features in the road topological graph are enlarged.

Fig. 5 is a schematic diagram according to a third embodiment of the disclosure, and as shown in fig. 5, fig. 5 shows a training method of a graph coding model applied to map updating, the method comprising:

S501, acquiring a plurality of remote sensing satellite images to be trained, wherein the remote sensing satellite images to be trained have a standard three-dimensional tensor map.

Each of the remote sensing satellite images to be trained has a unique standard three-dimensional tensor map, and the plurality of remote sensing satellite images to be trained correspond to the plurality of standard three-dimensional tensor maps.

S502, repeating the following steps until reaching preset conditions: inputting the remote sensing satellite image to be trained into a graph coding model to obtain a predicted three-dimensional tensor graph, wherein the predicted three-dimensional tensor graph represents the coding information of the road at the position corresponding to the remote sensing satellite image to be trained; parameter adjustment is carried out on the graph coding model according to the predicted three-dimensional tensor graph and the standard three-dimensional tensor graph; the map coding model obtained when the preset condition is reached is used for determining a three-dimensional tensor map of the remote sensing satellite image in the method of the embodiment.

The image coding model is a model formed by two layers of neural networks, a remote sensing satellite image to be trained is input into the image coding model, a predicted three-dimensional tensor image is output by the image coding model, then the predicted three-dimensional tensor image is compared with a standard three-dimensional tensor image through a loss function, parameters of each layer of neural network in the image coding model are obtained until the remote sensing satellite image to be trained is input into the image coding model, the standard three-dimensional tensor image can be output, and then the image coding model which reaches preset conditions at the moment is used for determining the three-dimensional tensor image of the remote sensing satellite image to be identified.

The present disclosure provides a training method applied to map updating of a map coding model, which trains the map coding model through a plurality of standard three-dimensional tensor maps of a plurality of remote sensing satellite images to be trained and a plurality of remote sensing satellite images to be trained, and inputs the remote sensing satellite images to be identified into the obtained map coding model to determine the three-dimensional tensor map of the remote sensing satellite images to be identified. By adopting the technical means, a relatively accurate graph coding model can be obtained, and further the remote sensing satellite image to be identified can be input into the accurate graph coding model, so that a relatively accurate three-dimensional tensor graph of the remote sensing satellite image to be identified can be obtained.

Fig. 6 is a schematic diagram according to a fourth embodiment of the present disclosure, and as shown in fig. 6, fig. 6 shows a training method of a graph coding model applied to map updating, the method including:

s601, acquiring a plurality of remote sensing satellite images to be trained, wherein the remote sensing satellite images to be trained have standard three-dimensional tensor graphs.

Illustratively, this step may refer to step S501, which is not described herein.

S602, carrying out feature extraction on a remote sensing satellite image to be trained based on a graph coding model to obtain a global feature graph and a local feature graph; the global feature map characterizes global features of the remote sensing satellite images to be trained, and the local feature map characterizes road features of the remote sensing satellite images to be trained.

Illustratively, performing feature extraction on a remote sensing satellite image to be trained based on a graph coding model to obtain a global feature graph and a local feature graph, including:

performing feature extraction on a remote sensing satellite image to be trained based on a graph coding model to obtain a global feature graph;

Illustratively, this step may refer to step S303, which is not described herein.

And S603, carrying out feature fusion on the global feature map and the local feature map based on the map coding model to obtain a fused feature map.

In this embodiment, feature fusion is performed on the global feature map and the local feature map based on the map coding model, so as to obtain a fused feature map, which includes:

S604, generating a three-dimensional tensor graph according to the fused feature graph.

S605, parameter adjustment is carried out on the graph coding model according to the predicted three-dimensional tensor graph and the standard three-dimensional tensor graph; the map coding model obtained when the preset condition is reached is used for determining a three-dimensional tensor map of the remote sensing satellite image in the method of the embodiment.

For example, in response to a labeling operation of a user, obtaining a road key point in a remote sensing satellite image to be trained; generating road coding information of the remote sensing satellite image to be trained according to the road key points in the remote sensing satellite image to be trained and other road key points adjacent to the road key points; the road coding information comprises coding data of each pixel point of the remote sensing satellite image to be trained; and generating a standard three-dimensional tensor graph of the remote sensing satellite image to be trained according to the road coding information of the remote sensing satellite image to be trained.

In this embodiment, a user marks road key points in a remote sensing satellite image to be trained, where the road key points in the remote sensing satellite image to be trained are different road junctions and end points of different roads. For example, fig. 7 is a schematic diagram of a user marking road keypoints in a remote sensing satellite image to be trained, and it can be seen from fig. 7 that the road keypoints are A, B, C, D, E and F, the road keypoint a is connected to the road keypoint B, the road keypoint B is connected to the road keypoint C, and the road keypoint C is connected to the road keypoint D and the road keypoint E simultaneously. The road key point E is connected with the road key point F.

Further, in this embodiment, after determining the road key point in the remote sensing satellite image to be trained, other road key points adjacent to the road key point can be determined. For example, if the road key point in the preliminarily determined remote sensing satellite image to be trained is the road key point C, the other road key points adjacent to the road key point are the road key point B, the road key point D and the road key point E. And generating the encoded data of the road key point C according to the road key point C and other road key points adjacent to the road key point as the road key point B, the road key point D and the road key point E. The remote sensing satellite image after the user labeling operation cannot be directly used for training the image coding model, so that the remote sensing satellite image after the user labeling operation needs to be converted into a data form capable of training the image coding model.

The coded data of each pixel point of the remote sensing satellite image to be trained comprises one or more of the following information:

whether each pixel point in the remote sensing satellite image to be trained is a road key point or not;

the number of other road key points adjacent to the pixel point as the road key point;

and distance information between the pixel point as the road key point and other adjacent road key points of the pixel point as the road key point.

In this embodiment, the encoded data includes information on whether each pixel point in the remote sensing satellite image to be trained is a road key point, or the number of other adjacent road key points to the pixel point as the road key point, or the distance between the pixel point as the road key point and other adjacent road key points to the pixel point as the road key point.

The encoded data further includes: whether each pixel point in the remote sensing satellite image to be trained is a road key point or not and the number of other adjacent road key points of the pixel points serving as the road key points; the number of other road key points adjacent to the pixel point as the road key point and the distance information between the pixel point as the road key point and the other road key points adjacent to the pixel point as the road key point; whether each pixel point in the remote sensing satellite image to be trained is a road key point, the pixel point serving as the road key point and distance information between the two adjacent other road key points of the pixel point serving as the road key point.

The encoded data further includes: whether each pixel point in the remote sensing satellite image to be trained is a road key point, the number of other adjacent road key points of the pixel points serving as the road key points, and the distance information between the pixel points serving as the road key points and other adjacent road key points of the pixel points serving as the road key points.

In this embodiment, whether each pixel point in the remote sensing satellite image to be trained is a road key point may be represented by two coded data bits. For example, the encoded data bit is 10 when the pixel is a road key point, and 01 when the pixel is not a road key point. Two of the encoded data bits of the road keypoint a, the road keypoint B, the road keypoint C, the road keypoint D, the road keypoint E, and the road keypoint F in fig. 7 may be 10.

In this embodiment, the number of coded data bits of other road key points adjacent to the pixel point as the road key point is 12 bits, and the reason for this is that the number of other road key points adjacent to the pixel point of the road key point is generally at most 6. In the present embodiment, the number of coded data bits of 12 bits, which are the number of other road key points adjacent to the pixel point as the road key point, is merely an example, and the coded data bits may be set by themselves, for example, may be 20 bits. As seen from fig. 7, the number of other road key points adjacent to the pixel point of the road key point a is 1, the number of other road key points adjacent to the pixel point of the road key point B is 2, the number of other road key points adjacent to the pixel point of the road key point C is 3, the number of other road key points adjacent to the pixel point of the road key point D is 1, the number of other road key points adjacent to the pixel point of the road key point E is 2, and the number of other road key points adjacent to the pixel point of the road key point F is 1. The number of adjacent other road key points of the pixel points of the road key points is determined, six areas are divided by taking the pixel points of the road key points as the centers, and a specific dividing mode can be seen from a statistical diagram of the number of adjacent other road key points of the pixel points of one road key point shown in fig. 8. It is possible to confirm sequentially in the six areas in fig. 8 that the first two bits of the 12 bits of the encoded data are confirmed as 10 if the road key exists in the first area, that the third four bits of the 12 bits of the encoded data are confirmed as 10 if the road key exists in the second area, and so on.

The distance information between the pixel point serving as the road key point and other adjacent road key points serving as the pixel point of the road key point is specifically determined by dividing a remote sensing satellite image to be trained according to coordinate information, confirming the coordinate information of the pixel point of each road key point and determining the distance information between the pixel point of each road key point and the coordinate information of other adjacent road key points. The coded data bit is 12 bits, wherein every two bits are distance information of adjacent other road key points. The distance information of the coded data bits and the coded data bits of the number of the road key points are in a corresponding relation.

Specifically, fig. 9 shows the encoded data of each pixel of a remote sensing satellite image to be trained and a three-dimensional tensor map. As can be seen from fig. 9, it is assumed that the encoded data of a pixel point is determined from the three-dimensional tensor map, where the pixel point is a pixel point of the road key point C, and the encoded data is composed of three parts, and the first part is an encoded data bit of whether the pixel point in the remote sensing satellite image to be trained is the road key point, and since the pixel point is the pixel point of the road key point C, the encoded data bit of the first part is 10; the second part is the number of other road key points adjacent to the pixel point as the road key point, because the pixel point is the pixel point of the road key point C, the number of other road key points adjacent to the pixel point of the road key point C is 3, as can be seen from fig. 8, if the road key point C has road key points in one area, the third area and the fourth area, the coded data bit of the second part is 100110100101; the third part is distance information between the pixel point serving as the road key point and other adjacent road key points of the pixel point serving as the road key point, and since the pixel point is the pixel point of the road key point C, distance information between the road key point B, the road key point D and the road key point E and the road key point C is calculated.

The advantage of this arrangement is that the road key point information of the remote sensing satellite image to be trained can be accurately represented by an accurate data form.

The present disclosure provides a training method of a graph coding model applied to map updating, comprising: acquiring a plurality of remote sensing satellite images to be trained, wherein the remote sensing satellite images to be trained have standard three-dimensional tensor graphs, and acquiring road key points in the remote sensing satellite images to be trained in response to labeling operation of a user; generating road coding information of the remote sensing satellite image to be trained according to the road key points in the remote sensing satellite image to be trained and other road key points adjacent to the road key points; the road coding information comprises coding data of each pixel point of the remote sensing satellite image to be trained; and generating a standard three-dimensional tensor graph of the remote sensing satellite image to be trained according to the road coding information of the remote sensing satellite image to be trained. By adopting the technical scheme, an accurate graph coding model can be obtained, and then a relatively accurate three-dimensional tensor graph is output, so that the recall rate of the obtained second topological graph is relatively high, the updating speed of the map is ensured, and the operation process is optimized.

Fig. 10 is a schematic diagram according to a fifth embodiment of the present disclosure, and as shown in fig. 10, fig. 10 shows a map updating apparatus based on remote sensing satellite images, and the apparatus 10 includes:

an acquisition unit 1001 is configured to acquire a remote sensing satellite image.

The first determining unit 1002 is configured to perform semantic segmentation processing on the remote sensing satellite image, to obtain a first topological graph, where the first topological graph includes a road at a location corresponding to the remote sensing satellite image; and determining a three-dimensional tensor map according to the remote sensing satellite image, wherein the three-dimensional tensor map represents the coding information of the road at the position corresponding to the remote sensing satellite image.

A second determining unit 1003, configured to perform decoding processing on the three-dimensional tensor map to obtain a second topology map, where the second topology map includes a road at a position corresponding to the remote sensing satellite image;

the third determining unit 1004 is configured to determine a road topology map according to the first topology map and the second topology map, and update the map according to the road topology map.

It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the above-described apparatus may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.

Fig. 11 is a schematic diagram according to a sixth embodiment of the present disclosure, and as shown in fig. 11, fig. 11 shows a map updating apparatus based on a remote sensing satellite image, the apparatus 11 includes:

an acquisition unit 1101, configured to acquire a remote sensing satellite image;

the first determining unit 1102 is configured to perform semantic segmentation processing on the remote sensing satellite image to obtain a first topological graph, where the first topological graph includes a road at a location corresponding to the remote sensing satellite image; and determining a three-dimensional tensor map according to the remote sensing satellite image, wherein the three-dimensional tensor map represents the coding information of the road at the position corresponding to the remote sensing satellite image.

The second determining unit 1103 is configured to perform decoding processing on the three-dimensional tensor map to obtain a second topological graph, where the second topological graph includes a road at a position corresponding to the remote sensing satellite image.

A third determining unit 1104 for determining a road topology map according to the first topology map and the second topology map, and updating the map according to the road topology map.

Illustratively, the first determining unit 1102 includes:

the first determining module 11021 is configured to input a remote sensing satellite image into the graph coding model to obtain a three-dimensional tensor graph; the image coding model is obtained by training based on remote sensing satellite images with standard three-dimensional tensor images.

Illustratively, the first determining module 11021 includes:

an extraction submodule 110211, configured to perform feature extraction on the remote sensing satellite image based on the image coding model, so as to obtain a global feature image and a local feature image; the global feature map characterizes global features of the remote sensing satellite image, and the local feature map characterizes road features of the remote sensing satellite image.

And a fusion submodule 110212, configured to perform feature fusion on the global feature map and the local feature map based on the map coding model, so as to obtain a fused feature map.

A generating submodule 110213 is configured to generate a three-dimensional tensor map according to the fused feature map.

Illustratively, the extraction sub-module 110211 includes:

and carrying out binarization processing on the global feature map to obtain a binarized feature map, wherein the binarized feature map comprises features of the road.

Illustratively, the fusion submodule 110212 includes:

Performing up-sampling treatment on the local feature map to obtain an up-sampled local feature map; the size of the local feature map after upsampling is the same as the size of the global feature map.

Illustratively, the third determining unit 1104 includes:

and a joining module 11041, configured to join the road pixel point in the first topology map to the second topology map to generate the road topology map if it is determined that the road pixel point in the first topology map does not exist in the second topology map.

Illustratively, wherein the apparatus further comprises:

the processing unit 1105 is configured to perform image enhancement processing on the road topology map, and obtain an enhanced road topology map.

The first topological graph is a binary graph, and the second topological graph is a binary graph.

Fig. 12 is a schematic diagram according to a seventh embodiment of the present disclosure, and as shown in fig. 12, fig. 12 shows a training apparatus applied to a map coding model for map updating, where the apparatus 12 includes:

A first obtaining unit 1201, configured to obtain a plurality of remote sensing satellite images to be trained, where the remote sensing satellite images to be trained have a standard three-dimensional tensor map;

a first determining unit 1202, configured to repeat the following steps until a preset condition is reached: inputting the remote sensing satellite image to be trained into a graph coding model to obtain a predicted three-dimensional tensor graph, wherein the predicted three-dimensional tensor graph represents the coding information of the road at the position corresponding to the remote sensing satellite image to be trained; parameter adjustment is carried out on the graph coding model according to the predicted three-dimensional tensor graph and the standard three-dimensional tensor graph;

wherein the map coding model obtained when the preset condition is reached is used for determining the three-dimensional tensor map of the remote sensing satellite image in the device of any one of claims 15-22.

Fig. 13 is a schematic diagram according to an eighth embodiment of the present disclosure, and as shown in fig. 13, fig. 13 shows a training apparatus applied to a map coding model for map updating, where the apparatus 13 includes:

The first obtaining unit 1301 is configured to obtain a plurality of remote sensing satellite images to be trained, where the remote sensing satellite images to be trained have a standard three-dimensional tensor map.

A first determining unit 1302, configured to repeat the following steps until a preset condition is reached: inputting the remote sensing satellite image to be trained into a graph coding model to obtain a predicted three-dimensional tensor graph, wherein the predicted three-dimensional tensor graph represents the coding information of the road at the position corresponding to the remote sensing satellite image to be trained; and carrying out parameter adjustment on the graph coding model according to the predicted three-dimensional tensor graph and the standard three-dimensional tensor graph.

The map coding model obtained when the preset condition is reached is used for determining a three-dimensional tensor map of the remote sensing satellite image in the device in the embodiment.

Illustratively, the first determining unit 1302 includes:

the extraction module 13021 is configured to perform feature extraction on a remote sensing satellite image to be trained based on a graph coding model, so as to obtain a global feature graph and a local feature graph; the global feature map characterizes global features of the remote sensing satellite images to be trained, and the local feature map characterizes road features of the remote sensing satellite images to be trained.

The determining module 13022 is configured to perform feature fusion on the global feature map and the local feature map based on the map coding model, and obtain a fused feature map.

And the generating module 13023 is configured to generate a three-dimensional tensor map according to the fused feature map.

Illustratively, the extraction module 13021 includes:

the extraction submodule 130211 is used for extracting features of the remote sensing satellite image to be trained based on the image coding model to obtain a global feature image.

The processing sub-module 130212 is configured to perform binarization processing on the global feature map to obtain a binarized feature map, where the binarized feature map includes features of the road.

A generation sub-module 130213 for determining a road location area corresponding to a road point in the global feature map based on the road point in the binarized feature map; and generating a local feature map according to the road position area corresponding to the road point.

Illustratively, the determining module 13022 includes:

a processing sub-module 130221, configured to perform upsampling processing on the local feature map to obtain an upsampled local feature map; the size of the local feature map after upsampling is the same as the size of the global feature map.

And the fusion submodule 130222 is used for carrying out feature fusion on the global feature map and the up-sampled local feature map based on the map coding model to obtain a fused feature map.

Illustratively, the method further comprises:

the second obtaining unit 1303 is configured to obtain, in response to an annotation operation of a user, a road key point in a remote sensing satellite image to be trained.

The first generating unit 1304 is configured to generate road coding information of the remote sensing satellite image to be trained according to the road key points in the remote sensing satellite image to be trained and other road key points adjacent to the road key points; the road coding information comprises coding data of each pixel point of the remote sensing satellite image to be trained.

The second generating unit 1305 is configured to generate a standard three-dimensional tensor map of the remote sensing satellite image to be trained according to the road coding information of the remote sensing satellite image to be trained.

Illustratively, the method further comprises: the coded data of each pixel point of the remote sensing satellite image to be trained comprises one or more of the following information: whether each pixel point in the remote sensing satellite image to be trained is a road key point or not; the number of other road key points adjacent to the pixel point as the road key point; and distance information between the pixel point as the road key point and other adjacent road key points of the pixel point as the road key point.

According to embodiments of the present disclosure, the present disclosure also provides a computer device, a readable storage medium and a computer program product.

According to an embodiment of the present disclosure, the present disclosure also provides a computer program product comprising: a computer program stored in a readable storage medium, from which the computer program can be read by at least one processor of a computer device, the at least one processor executing the computer program causing the computer device to perform the solution provided by any one of the embodiments described above.

Fig. 14 is a schematic diagram according to a ninth embodiment of the present disclosure, as shown in fig. 14, a server 1400 in the present disclosure may include: a processor 1401 and a memory 1402.

A memory 1402 for storing a program; memory 1402, which may include volatile memory (English: volatile memory), such as random-access memory (RAM), such as static random-access memory (SRAM), double data rate synchronous dynamic random-access memory (Double Data Rate Synchronous Dynamic Random Access Memory, DDR SDRAM), etc.; the memory may also include a non-volatile memory (English) such as a flash memory (English). Memory 1402 is used to store computer programs (e.g., application programs, functional modules, etc. that implement the methods described above), computer instructions, etc., which may be stored in one or more memory 1402 in partitions. And the above-described computer programs, computer instructions, data, etc. may be invoked by the processor 1401.

The computer programs, computer instructions, etc. described above may be stored in partitions in one or more memories 1402. And the above-described computer programs, computer instructions, etc. may be invoked by the processor 1401.

A processor 1401 is configured to execute a computer program stored in a memory 1402, so as to implement the steps of the remote sensing satellite image based map updating method according to the above embodiment.

Reference may be made in particular to the description of the embodiments of the method described above.

The processor 1401 and the memory 1402 may be separate structures or may be integrated structures integrated together. When the processor 1401 and the memory 1402 are separate structures, the memory 1402 and the processor 1401 may be coupled through the bus 1403.

The server in this embodiment may execute the technical scheme in the above method, and the specific implementation process and the technical principle are the same, which are not described herein again.

According to an embodiment of the present disclosure, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the solution provided by the above-described respective embodiments.

According to an embodiment of the present disclosure, the present disclosure also provides a computer program product comprising: computer program stored in a readable storage medium, from which the computer program can be read by at least one processor of a server, the at least one processor executing the computer program causing the server to perform the solutions provided by the respective embodiments described above.

According to an embodiment of the present disclosure, the present disclosure also provides a computer program product comprising: a computer program stored in a readable storage medium, from which at least one processor of a control device of a vehicle can read, the at least one processor executing the computer program causing the control device of the vehicle to execute the solution provided by the respective embodiments described above.

Fig. 15 is a schematic diagram according to a tenth embodiment of the present disclosure, as shown in fig. 15, a server 1500 in the present disclosure may include: a processor 1501 and a memory 1502.

A memory 1502 for storing a program; the memory 1502 may include a volatile memory (english: volatile memory), such as a random-access memory (RAM), such as a static random-access memory (SRAM), a double data rate synchronous dynamic random-access memory (DDR SDRAM), etc.; the memory may also include a non-volatile memory (English) such as a flash memory (English). The memory 1502 is used to store computer programs (e.g., application programs, functional modules, etc. that implement the methods described above), computer instructions, etc., which may be stored in one or more of the memory 1502 in partitions. And the above-described computer programs, computer instructions, data, etc. may be invoked by the processor 1501.

The computer programs, computer instructions, etc., described above may be stored in one or more of the memories 1502 in partitions. And the above-described computer programs, computer instructions, etc. may be invoked by the processor 1501.

A processor 1501 for executing the computer program stored in the memory 1502 to implement the respective steps in the training method of the map coding model applied to map updating according to the above embodiment.

The processor 1501 and the memory 1502 may be separate structures or may be integrated structures integrated together. When the processor 1501 and the memory 1502 are separate structures, the memory 1502 and the processor 1501 may be coupled by a bus 1503.

FIG. 16 illustrates a schematic block diagram of an example computer device 1600 that can be used to implement embodiments of the present disclosure. Computer devices are intended to represent various forms of digital computers, such as laptops, desktops, personal digital assistants, computer devices, blade computer devices, mainframes, and other appropriate computers. The computer device may also represent various forms of mobile apparatuses, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing apparatuses. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 16, the computer device 1600 includes a computing unit 1601 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 1602 or a computer program loaded from a storage unit 1608 into a Random Access Memory (RAM) 1603. In RAM 1603, various programs and data required for operation of device 1600 may also be stored. The computing unit 1601, ROM 1602, and RAM 1603 are connected to each other by a bus 1604. An input/output (I/O) interface 1605 is also connected to the bus 1604.

Various components in computer device 1600 are connected to I/O interface 1605, including: an input unit 1606 such as a keyboard, a mouse, and the like; an output unit 1607 such as various types of displays, speakers, and the like; a storage unit 1608, such as a magnetic disk, an optical disk, or the like; and a communication unit 1609, such as a network card, modem, wireless communication transceiver, or the like. The communication unit 1609 allows the computer device 1600 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks.

The computing unit 1601 may be a variety of general purpose and/or special purpose processing components with processing and computing capabilities. Some examples of computing unit 1601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1601 performs the respective methods and processes described above, for example, a processing method for generating positioning information of a high-precision map. For example, in some embodiments, the model training of the method for image processing may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 1608. In some embodiments, some or all of the computer programs may be loaded and/or installed onto computer device 1600 via ROM 1602 and/or communication unit 1609. When the computer program is loaded into RAM 1603 and executed by computing unit 1601, one or more steps of the remote sensing satellite image based map updating method described above may be performed. Alternatively, in other embodiments, the computing unit 1601 may be configured to perform model training of methods for image processing by any other suitable means (e.g. by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or computer device.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data computer device), or that includes a middleware component (e.g., an application computer device), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.

The computer system may include a client and a computer device. The client and computer devices are typically remote from each other and typically interact through a communications network. The relationship of client and computer devices arises by virtue of computer programs running on the respective computers and having a client-computer device relationship to each other. The computer equipment can be cloud computer equipment, also called cloud computer equipment or cloud host, is a host product in a cloud computing service system, and solves the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service ("Virtual Private Server" or simply "VPS"). The computer device may also be a distributed system computer device or a computer device that incorporates a blockchain.

Fig. 17 illustrates a schematic block diagram of an example computer device 1700 that can be used to implement embodiments of the present disclosure. Computer devices are intended to represent various forms of digital computers, such as laptops, desktops, personal digital assistants, computer devices, blade computer devices, mainframes, and other appropriate computers. The computer device may also represent various forms of mobile apparatuses, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing apparatuses. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 17, the computer device 1700 includes a computing unit 1701 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 1702 or a computer program loaded from a storage unit 1708 into a Random Access Memory (RAM) 1703. In the RAM 1703, various programs and data required for the operation of the device 1700 may also be stored. The computing unit 1701, the ROM 1702, and the RAM 1703 are connected to each other via a bus 1704. An input/output (I/O) interface 1705 is also connected to the bus 1704.

Various components in computer device 1700 are connected to I/O interface 1705, including: an input unit 1706 such as a keyboard, a mouse, etc.; an output unit 1707 such as various types of displays, speakers, and the like; a storage unit 1708 such as a magnetic disk, an optical disk, or the like; and a communication unit 1709 such as a network card, modem, wireless communication transceiver, or the like. The communication unit 1709 allows the computer device 1700 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunications networks.

The computing unit 1701 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 1701 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The calculation unit 1701 performs the respective methods and processes described above, for example, a processing method for generating positioning information of a high-precision map. For example, in some embodiments, the model training of the method for image processing may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 1708. In some embodiments, part or all of the computer program may be loaded and/or installed onto the computer device 1700 via the ROM 1702 and/or the communication unit 1709. When the computer program is loaded into the RAM 1703 and executed by the computing unit 1701, one or more steps of the training method described above applied to the map-updated, map-encoding model may be performed. Alternatively, in other embodiments, the computing unit 1701 may be configured to perform model training of methods for image processing in any other suitable way (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.

The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. A map updating method based on remote sensing satellite images comprises the following steps:

acquiring a remote sensing satellite image;

determining a road topological graph according to the first topological graph and the second topological graph, and updating a map according to the road topological graph;

wherein, according to the remote sensing satellite image, determining a three-dimensional tensor map comprises:

inputting the remote sensing satellite image into a graph coding model, and extracting features of the remote sensing satellite image based on the graph coding model to obtain a global feature graph and a local feature graph; the global feature map represents global features of the remote sensing satellite image, and the local feature map represents road features of the remote sensing satellite image;

performing feature fusion on the global feature map and the local feature map based on the map coding model to obtain a fused feature map;

generating a three-dimensional tensor graph according to the fused feature graph; the image coding model is obtained by training based on remote sensing satellite images with standard three-dimensional tensor images.

2. The method of claim 1, wherein performing feature extraction on the remote sensing satellite image based on the graph coding model to obtain a global feature graph and a local feature graph, comprises:

Performing feature extraction on the remote sensing satellite image based on the image coding model to obtain the global feature image;

performing binarization processing on the global feature map to obtain a binarized feature map, wherein the binarized feature map comprises features of roads;

determining a road position area corresponding to the road point in the global feature map based on the road point in the binarized feature map; and generating the local feature map according to the road position area corresponding to the road point.

3. The method according to claim 1 or 2, wherein feature fusion is performed on the global feature map and the local feature map based on the map coding model, so as to obtain a fused feature map, including:

performing up-sampling treatment on the local feature map to obtain an up-sampled local feature map; the size of the local feature map after up-sampling is the same as the size of the global feature map;

and carrying out feature fusion on the global feature map and the up-sampled local feature map based on the map coding model to obtain the fused feature map.

4. The method of claim 1 or 2, wherein determining a road topology from the first topology and the second topology comprises:

And if the road pixel points in the first topological graph are determined to be not in the second topological graph, adding the road pixel points in the first topological graph into the second topological graph to generate the road topological graph.

5. The method according to claim 1 or 2, wherein after determining a road topology from the first topology and the second topology, further comprising:

and carrying out image enhancement processing on the road topological graph to obtain an enhanced road topological graph.

6. The method of claim 1 or 2, wherein the first topology graph is a binary graph and the second topology graph is a binary graph.

7. A training method of a graph coding model applied to map updating, comprising:

Wherein the graph coding model obtained when the preset condition is reached is used for determining the three-dimensional tensor graph of the remote sensing satellite image in the method of any one of claims 1-6.

8. The method of claim 7, wherein inputting the remote sensing satellite image to be trained into a graph coding model results in a predicted three-dimensional tensor graph, comprising:

performing feature extraction on the remote sensing satellite image to be trained based on the image coding model to obtain a global feature image and a local feature image; the global feature map represents global features of the remote sensing satellite image to be trained, and the local feature map represents road features of the remote sensing satellite image to be trained;

and generating the three-dimensional tensor graph according to the fused feature graph.

9. The method of claim 8, wherein performing feature extraction on the remote sensing satellite image to be trained based on the graph coding model to obtain a global feature graph and a local feature graph, comprises:

performing feature extraction on the remote sensing satellite image to be trained based on the image coding model to obtain the global feature image;

10. The method according to claim 8 or 9, wherein feature fusion is performed on the global feature map and the local feature map based on the map coding model, so as to obtain a fused feature map, including:

11. The method of claim 10, further comprising:

responding to the labeling operation of a user, and acquiring road key points in the remote sensing satellite image to be trained;

generating road coding information of the remote sensing satellite image to be trained according to the road key points in the remote sensing satellite image to be trained and other road key points adjacent to the road key points; the road coding information comprises coding data of each pixel point of the remote sensing satellite image to be trained;

And generating a standard three-dimensional tensor graph of the remote sensing satellite image to be trained according to the road coding information of the remote sensing satellite image to be trained.

12. The method of claim 11, wherein the encoded data for each pixel of the remote sensing satellite image to be trained includes one or more of the following information:

13. A map updating device based on remote sensing satellite images, comprising:

the acquisition unit is used for acquiring remote sensing satellite images;

a third determining unit, configured to determine a road topology map according to the first topology map and the second topology map, and update a map according to the road topology map; wherein the first determining unit includes:

the first determining module is used for inputting the remote sensing satellite image into a graph coding model to obtain a three-dimensional tensor graph; the image coding model is obtained by training based on a remote sensing satellite image with a standard three-dimensional tensor image;

wherein the first determining module includes:

the extraction sub-module is used for extracting the characteristics of the remote sensing satellite image based on the image coding model to obtain a global characteristic image and a local characteristic image; the global feature map represents global features of the remote sensing satellite image, and the local feature map represents road features of the remote sensing satellite image;

the fusion sub-module is used for carrying out feature fusion on the global feature map and the local feature map based on the map coding model to obtain a fused feature map;

And the generation sub-module is used for generating the three-dimensional tensor graph according to the fused feature graph.

14. The apparatus of claim 13, wherein the extraction sub-module comprises:

15. The apparatus of claim 13 or 14, wherein the fusion sub-module comprises:

16. The apparatus according to claim 13 or 14, wherein the third determining unit comprises:

and the adding module is used for adding the road pixel points in the first topological graph into the second topological graph to generate the road topological graph if the road pixel points in the first topological graph are determined to be not in the second topological graph.

17. The apparatus according to claim 13 or 14, wherein the apparatus further comprises:

and the processing unit is used for carrying out image enhancement processing on the road topological graph to obtain an enhanced road topological graph.

18. The apparatus of claim 13 or 14, wherein the first topology graph is a binary graph and the second topology graph is a binary graph.

19. A training device for a graph coding model applied to map updating, comprising:

Wherein the graph coding model obtained when the preset condition is reached is used for determining a three-dimensional tensor graph of the remote sensing satellite image in the device according to any one of claims 13-18.

20. The apparatus of claim 19, wherein the first determining unit comprises:

the extraction module is used for extracting the characteristics of the remote sensing satellite image to be trained based on the image coding model to obtain a global characteristic image and a local characteristic image; the global feature map represents global features of the remote sensing satellite image to be trained, and the local feature map represents road features of the remote sensing satellite image to be trained;

the determining module is used for carrying out feature fusion on the global feature map and the local feature map based on the map coding model to obtain a fused feature map;

and the generating module is used for generating the three-dimensional tensor graph according to the fused feature graph.

21. The apparatus of claim 20, wherein the extraction module comprises:

the extraction sub-module is used for extracting the characteristics of the remote sensing satellite image to be trained based on the image coding model to obtain the global characteristic image;

the processing sub-module is used for carrying out binarization processing on the global feature map to obtain a binarized feature map, wherein the binarized feature map comprises features of roads;

A generation sub-module, configured to determine, in the global feature map, a road location area corresponding to a road point based on the road point in the binarized feature map; and generating the local feature map according to the road position area corresponding to the road point.

22. The apparatus of claim 20 or 21, wherein the determining module comprises:

the processing sub-module is used for carrying out up-sampling processing on the local feature map to obtain an up-sampled local feature map; the size of the local feature map after up-sampling is the same as the size of the global feature map;

and the fusion sub-module is used for carrying out feature fusion on the global feature map and the up-sampled local feature map based on the map coding model to obtain the fused feature map.

23. The apparatus of claim 22, further comprising:

the second acquisition unit is used for responding to the labeling operation of the user and acquiring the road key points in the remote sensing satellite image to be trained;

the first generation unit is used for generating road coding information of the remote sensing satellite image to be trained according to the road key points in the remote sensing satellite image to be trained and other road key points adjacent to the road key points; the road coding information comprises coding data of each pixel point of the remote sensing satellite image to be trained;

And the second generation unit is used for generating a standard three-dimensional tensor graph of the remote sensing satellite image to be trained according to the road coding information of the remote sensing satellite image to be trained.

24. The apparatus of claim 23, wherein the encoded data for each pixel of the remote sensing satellite image to be trained comprises one or more of the following information:

25. A computer device, comprising:

at least one processor; and

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

26. A computer device, comprising:

at least one processor; and

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 7-12.

27. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-6.

28. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 7-12.