Route planning method and device based on road shielding degree

Abstract

The invention relates to the technical field of target characteristics and camouflage protection, in particular to a route planning method and device based on the road shielding degree, and the method comprises the steps: obtaining a shielding region through threshold segmentation on the basis of image preprocessing; after component information is weakened, pixel point space domain enhancement and shielding area information recovery are achieved through a compensation method, and on the basis that the difference between road surface shielding and the surrounding environment is increased, shielding road extraction is achieved through an efficient segmentation algorithm; non-shielded roads obtained through clustering segmentation are combined, and the shielding degree of shielded roads is finally calculated through refining processing. According to the method, the shadow shielding road in the shadow area can be extracted.

Description

Technical Field

[0001] The present application relates to the field of target characteristics and camouflage protection technology, and in particular to a route planning method and device based on road shielding. Background Art

[0002] In road extraction based on high-resolution remote sensing images, road occlusion caused by various factors is an important factor leading to the loss of part of the extracted or disputed roads.

[0003] Traditional shading coefficient correction methods are difficult to eliminate the interference of vegetation and building shading on road extraction.

[0004] In view of this, how to provide a route planning method based on road obscuration to realize the extraction of shadow-obstructed roads in shadow areas has become a technical problem that urgently needs to be solved. Summary of the invention

[0005] The embodiments of the present application provide a route planning method based on road obscuration, a route planning device based on road obscuration, an electronic device and a computer storage medium, which are used to solve the problem of poor performance in current network traffic anomaly detection.

[0006] In a first aspect of an embodiment of the present application, a route planning method based on road obscuration is provided, comprising:

[0007] Acquiring a remote sensing image, and preprocessing the remote sensing image to obtain an initial remote sensing image;

[0008] Performing shadow detection on the initial remote sensing image to obtain a shadowed area and a non-shadowed area, and compensating the shadowed area based on the light intensity and light color of the shadowed area and the non-shadowed area to obtain a target remote sensing image;

[0009] Performing shadow detection on the target remote sensing image to obtain a shadow image and a non-shadow image, suppressing the blue component of the shadow image, performing shadow compensation on the shadow image based on a shadow compensation algorithm, and then segmenting the shadow image into a foreground area and a background area through an interactive image segmentation algorithm, wherein the foreground area is a road area highlighted in the target remote sensing image, and the background area is other areas in the target remote sensing image except the highlighted road area;

[0010] The background area is segmented by an interactive image segmentation algorithm to obtain a shadow-covered road, the shadow-covered road and the foreground area are merged to generate a road main area, and the road main area is processed by a target contour method to obtain a target road area;

[0011] A target search algorithm is used to perform route planning on the target road area.

[0012] In a second aspect of an embodiment of the present application, a route planning device based on road obscuration is provided, comprising:

[0013] A preprocessing module is configured to acquire a remote sensing image and preprocess the remote sensing image to obtain an initial remote sensing image;

[0014] A compensation module is configured to perform shadow shielding detection on the initial remote sensing image to obtain a shadow shielding area and a non-shadow shielding area, and compensate the shielding area based on the light intensity and light color of the shadow shielding area and the non-shadow shielding area to obtain a target remote sensing image;

[0015] A first segmentation module is configured to perform shadow detection on the target remote sensing image to obtain a shadow image and a non-shadow image, suppress a blue component of the shadow image, perform shadow compensation on the shadow image based on a shadow compensation algorithm, and then segment the shadow image into a foreground area and a background area through an interactive image segmentation algorithm, wherein the foreground area is a road area highlighted in the target remote sensing image, and the background area is other areas in the target remote sensing image except the highlighted road area;

[0016] The second segmentation module is configured to segment the background area by an interactive image segmentation algorithm to obtain a shadow-covered road, merge the shadow-covered road and the foreground area to generate a road main body area, and process the road main body area by a target contour method to obtain a target road area;

[0017] The planning module is configured to perform route planning on the target road area using a target search algorithm.

[0018] According to a third aspect of an embodiment of the present application, a computing device is provided, including:

[0019] Memory and processor;

[0020] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the route planning method based on road obstruction are implemented.

[0021] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned route planning method based on road obstruction are implemented.

[0022] The present application provides a route planning method based on road obscuration, comprising: acquiring a remote sensing image, and preprocessing the remote sensing image to obtain an initial remote sensing image; performing shadow obscuration detection on the initial remote sensing image to obtain a shadow obscuration area and a non-shadow obscuration area, and compensating the obscuration area based on the light intensity and light color of the shadow obscuration area and the non-shadow obscuration area to obtain a target remote sensing image; performing shadow detection on the target remote sensing image to obtain a shadow image and a non-shadow image, and suppressing the blue component of the shadow image, and performing shadow compensation on the shadow image based on a shadow compensation algorithm. , by using an interactive image segmentation algorithm, the shadow image is segmented into a foreground area and a background area, wherein the foreground area is the road area highlighted in the target remote sensing image, and the background area is other areas in the target remote sensing image except the highlighted road area; by using an interactive image segmentation algorithm, the background area is segmented to obtain a shadow-obstructed road, the shadow-obstructed road and the foreground area are merged to generate a road main body area, and the road main body area is processed by a target contour method to obtain a target road area; and a target search algorithm is used to perform route planning on the target road area.

[0023] By applying the route planning method based on road obscuration provided in the embodiment of the present application, the obscured area is compensated based on light intensity and light brightness, which can effectively eliminate non-road surface shadows during shadow road extraction, reduce the interference of shadows such as vegetation on shadow road extraction, reduce the fragmentation of patches during shadow road extraction, better preserve the integrity of the main road patches, and reduce the workload of road post-processing.

[0024] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, which can be implemented in accordance with the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0026] Figure 1 A schematic diagram of a process flow of a route planning method based on road obscuration provided in an embodiment of the present application;

[0027] Figure 2 A schematic diagram of a process of road extraction in a route planning method based on road obscuration provided in an embodiment of the present application;

[0028] Figure 3 A schematic diagram of shadow extraction effect in a route planning method based on road shielding provided in an embodiment of the present application;

[0029] Figure 4 A schematic diagram of a search process of an A* algorithm in a route planning method based on road obscuration provided in an embodiment of the present application;

[0030] Figure 5 A schematic diagram of the structure of a route planning device based on road obscuration provided in an embodiment of the present application;

[0031] Figure 6 A structural block diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary 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 limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0033] The embodiment of the present application provides a route planning method based on road obscuration, which specifically includes: based on image preprocessing, using threshold segmentation to obtain obscured areas; using compensation methods to achieve pixel point spatial domain enhancement and recovery of obscured area information after weakening component information, and on the basis of increasing the difference between road surface obscuration and the surrounding environment, using efficient segmentation algorithms to achieve obscured road extraction; merging non-obscured roads obtained by clustering segmentation, and finally achieving calculation of the obscuration degree of obscured roads through refinement processing. The present invention can achieve the extraction of shadowed roads in shadow areas.

[0034] See also Figure 1 , Figure 1 The following is a flow chart of a route planning method based on road obscuration provided in an embodiment of the present application. Figure 1 As shown, the specific steps include the following steps.

[0035] It should be noted that the route planning method based on road obscuration provided in the embodiment of the present application is most suitable for suburban shadow road extraction and path planning, and can also be used for path planning for the extraction of urban shadow roads.

[0036] Step S102: Acquire a remote sensing image, and preprocess the remote sensing image to obtain an initial remote sensing image.

[0037] In an embodiment of the present application, the preprocessing of the remote sensing image to obtain a target remote sensing image includes: linearly stretching the remote sensing image to obtain a first remote sensing image; performing bilateral filtering on the remote sensing image to obtain a second remote sensing image; and obtaining a target remote sensing image based on the first remote sensing image and the second remote sensing image.

[0038] First of all, this application provides a road obscuration analysis modeling method, which first pre-processes the remote sensing image. On the one hand, the original remote sensing image is linearly stretched to improve the image clarity, thereby highlighting the required information, which is conducive to further processing and analysis. The original image is dark as a whole, so a linear stretch based on the grayscale histogram is used. This processing changes the display effect, improves the brightness, and makes the image clearer. The difference between the road area and the surrounding background area is enhanced, but the pixel value does not change. On the other hand, the original remote sensing image is subjected to bilateral filtering.

[0039] Step S104: performing shadow detection on the initial remote sensing image to obtain a shadowed area and a non-shadowed area, and compensating the shadowed area based on the light intensity and light color of the shadowed area and the non-shadowed area to obtain a target remote sensing image.

[0040] In the embodiment of the present application, the compensation of the shadowed area based on the light intensity and light color of the shadowed area and the non-shadowed area to obtain the target remote sensing image includes:

[0041] The blue component of the shadow-shaded area is suppressed, and the shadow-shaded area is compensated based on a first calculation formula to obtain a shadow-shaded image, wherein the first calculation formula includes:

[0042]

[0043] Where k(S) is the light intensity and light color of the shadow area; S(x, y) is the shadow area; a is a fixed constant; p is the exponential parameter in the Minkowski normal form, which can be any integer in [1, ∞]; For image and Gaussian filter convolution, It is a 3*3 template.

[0044] Based on a second calculation formula, the non-shadow-shielded area is compensated to obtain a non-shadow-shielded image, wherein the second calculation formula includes:

[0045]

[0046] Where k(NS) is the light intensity and light color of the non-shadow area; NS(x, y) is the non-shadow area; a is a fixed constant; p is the exponential parameter in the Minkowski normal form, which can be any integer in [1, ∞]; For image and Gaussian filter convolution, It is a 3*3 template.

[0047] A target remote sensing image is obtained based on the shadow-obstructed image and the non-shadow-obstructed image.

[0048] In practical applications, shadow detection is performed on remote sensing aerial images, and the images are divided into two images: the shadow area S(x,y) and the non-shadow area NS(x,y). The blue component of S(x,y) is first suppressed, and then the light intensity and color of the shadow area and the non-shadow area are estimated respectively. The shaded area is compensated according to the calculated light color. For specific implementation, please refer to the first and second calculation formulas above.

[0049] In an embodiment of the present application, the shadow detection is performed on the initial remote sensing image to obtain the shadow area and the non-shadow area, including: using the ISODATA clustering algorithm to perform shadow detection on the initial remote sensing image to obtain the shadow area and the non-shadow area.

[0050] It should be noted that most roads are linear, with uniform texture features and high spectral feature similarity. By using the unsupervised classification method, spectral information can be used to classify images without prior knowledge. Since the ISODATA algorithm has less influence on the selection of the initial center than the K-mean clustering algorithm and has a better clustering effect, the present invention selects the ISODATA clustering algorithm to segment non-shadow roads.

[0051] Step S106: Perform shadow detection on the target remote sensing image to obtain a shadow image and a non-shadow image, suppress the blue component of the shadow image, perform shadow compensation on the shadow image based on a shadow compensation algorithm, and then segment the shadow image into a foreground area and a background area through an interactive image segmentation algorithm, wherein the foreground area is the highlighted road area in the target remote sensing image, and the background area is other areas in the target remote sensing image except the highlighted road area.

[0052] By performing shadow detection on remote sensing images, the remote sensing images are decomposed into two images: shadow images and non-shadow images. The shadow images are firstly subjected to blue component suppression, and then shadow compensation is performed using the proposed shadow compensation algorithm, thereby increasing the difference between the road area and the surrounding objects. The present invention adopts an efficient segmentation algorithm, the Lazy Snapping algorithm, which treats the highlighted road area as the foreground and the rest as the background; the shadow road area is segmented in combination with the algorithm to obtain the road area obscured by the shadow.

[0053] Step S108: Segment the background area through an interactive image segmentation algorithm to obtain a shadow-obstructed road, merge the shadow-obstructed road and the foreground area to generate a road main body area, and process the road main body area through a target contour method to obtain a target road area.

[0054] By merging the shadowed roads and the non-shadowed roads, the main information of the road is basically extracted. However, due to the interference of gaps in the road and small patches around the road, the road needs to be further processed. In the embodiment of the present application, the target road area is obtained by processing the main road area by the target contour method, including: using morphological methods and connected domain analysis to refine the main road area, repairing the concave road edges by contour neighborhood search to obtain the initial main road area, and calculating the degree of shielding; using the contour repair method to process the contour endpoints of the initial main road area to obtain the target road area.

[0055] The embodiment of the present application mainly uses morphological methods and connected domain analysis to refine the extraction results, and calculates the degree of shielding after repairing the sunken road edges through contour neighborhood search. In view of the sunken phenomenon caused by incomplete extraction of road edges, this model uses contour repair method to process the contour endpoints of the road.

[0056] The above embodiment provides a road obscuration analysis characteristic modeling method, with the support of which multispectral remote sensing images are used to extract road networks. Due to obstruction by other objects, the model uses comprehensive index shadow detection, shadow compensation algorithm, and Lazy Snapping segmentation algorithm to reconstruct the complete road and calculate the degree of road obscuration.

[0057] Step S110: using a target search algorithm to perform route planning on the target road area.

[0058] In the embodiment of the present application, the A* algorithm is used to perform route planning on the target road area.

[0059] After the results of road extraction are generated, the design of path planning is selected and used. The embodiment of the present application chooses to use the A* algorithm, which has the advantages of simple calculation, fast convergence speed, good scalability and high reliability, and can meet the timeliness requirements of path planning.

[0060] In another embodiment, the method further includes: using a diagonal function to estimate the cost of route planning.

[0061] The embodiment of the present application selects the diagonal distance as the calculation function for estimating the cost because the estimated cost as a heuristic function is closer to the actual value of the optimal path and has a smaller error.

[0062] The calculation idea is to first move along the diagonal direction from A to B, and then move the remaining distance in the horizontal or vertical direction. Similarly, let the coordinates of the two points in the figure be A(x1,y1) and B(x2,y2), and the unit movement cost in the horizontal or vertical direction be c. Then the unit movement cost in the diagonal direction is The diagonal distance heuristic function h(n) can be expressed as:

[0063] diagonal(n)=min(|x 1 -x 2 |,|y 1 -y 2 |)

[0064] straight(n)=|x 1 -x 2 |+|y 1 -y 2 |

[0065]

[0066] The route planning method based on road shielding provided in the embodiment of the present application and the method based on brightness compensation can effectively remove non-road surface shadows when extracting shadow roads, reduce the interference of shadows such as vegetation on shadow road extraction, reduce the fragmentation of patches when extracting shadow roads, better preserve the integrity of the main patch of the road, and reduce the workload of road post-processing. A road planning method is provided in which the estimated cost of path selection is closer to the actual value of the optimal path.

[0067] See also Figure 2 , Figure 2 A schematic diagram of the process of road extraction in a route planning method based on road obscuration provided in an embodiment of the present application.

[0068] like Figure 2As shown, firstly, a remote sensing image is acquired; then, image preprocessing is performed on the remote sensing image, wherein the preprocessing includes linear stretching and bilateral filtering; secondly, HSI threshold segmentation is performed to obtain the initial shadow area and the initial cluster K value respectively; thirdly, based on the initial shadow area and the initial cluster K, shadow road extraction and non-shadow road extraction are performed, wherein the shadow road extraction includes two steps of brightness compensation and lazy Snapping segmentation, and the non-shadow road extraction includes a K-means segmentation step; thirdly, road post-processing is performed, wherein the road post-processing includes morphological processing and contour repair; finally, the road is obtained.

[0069] See also Figure 3 , Figure 3 A schematic diagram of shadow extraction effect in a route planning method based on road shielding provided in an embodiment of the present application. Figure 3 As shown in the figure, the experiment selected a 1956 pixel × 1941 pixel remote sensing image with blue objects and vegetation. The image scene includes blue objects, vegetation, houses, roads and other objects. The red frame contains blue objects and vegetation. First, the shadow detection result is threshold segmented by the Otsu algorithm to obtain a binary shadow detection image. As shown in the figure, the NBRI index will detect blue objects, but it performs better in vegetation detection; the SI index performs better in detecting blue objects, but it will cause false detection in vegetation detection; this paper combines the two shadow detection indices to successfully remove blue objects and vegetation, and obtain a more accurate shadow detection map.

[0070] See also Figure 4 , Figure 4 A schematic diagram of the flow of A* algorithm search in a route planning method based on road obscuration provided in an embodiment of the present application.

[0071] The A* algorithm needs to establish an OPEN table and a CLOSE table to store unexamined nodes and examined nodes respectively. Suppose the search starting point is S and the target node is T. Figure 4 As shown, the specific steps include:

[0072] Step S401: first add the search starting point S to the OPEN table;

[0073] Step S402: Take S as the current node (at this time, there is only the search starting point S in the OPEN table), add all nodes K adjacent to S to the OPEN table, set the pointer of node K to S, and remove S from the OPEN table and add it to the CLOSE table;

[0074] Step S403: determine whether the OPEN table is empty. If it is empty, the search fails and the search is exited; if it is not empty, calculate the f(n) value of each node in the OPEN table and sort them in ascending order;

[0075] Step S404: remove the first node from the OPEN table and add it to the COLSE table to determine whether it is the target node T. If so, the search is successful and the search is exited. Otherwise, the node is expanded.

[0076] Step S405: Determine whether the newly expanded node K exists in the OPEN table or the CLOSE table;

[0077] Step S406: re-order the OPEN table and return to step S404;

[0078] Step S407: After successfully searching for the target node T, searching in reverse order from the parent node is the shortest path.

[0079] By applying the route planning method based on road obscuration provided in the embodiment of the present application, the obscured area is compensated based on light intensity and light brightness, which can effectively eliminate non-road surface shadows during shadow road extraction, reduce the interference of shadows such as vegetation on shadow road extraction, reduce the fragmentation of patches during shadow road extraction, better preserve the integrity of the main road patches, and reduce the workload of road post-processing.

[0080] Corresponding to the above method embodiment, this specification also provides an embodiment of a route planning device based on road shielding degree, Figure 5 The following is a schematic diagram of the structure of a route planning device based on road obscuration provided in an embodiment of the present application. Figure 5 As shown, the device comprises:

[0081] The preprocessing module 502 is configured to acquire a remote sensing image and preprocess the remote sensing image to obtain an initial remote sensing image;

[0082] The compensation module 504 is configured to perform shadow detection on the initial remote sensing image to obtain a shadow area and a non-shadow area, and compensate the shadow area based on the light intensity and light color of the shadow area and the non-shadow area to obtain a target remote sensing image;

[0083] The first segmentation module 506 is configured to perform shadow detection on the target remote sensing image to obtain a shadow image and a non-shadow image, suppress the blue component of the shadow image, perform shadow compensation on the shadow image based on a shadow compensation algorithm, and then segment the shadow image into a foreground area and a background area through an interactive image segmentation algorithm, wherein the foreground area is a road area highlighted in the target remote sensing image, and the background area is other areas in the target remote sensing image except the highlighted road area;

[0084] The second segmentation module 508 is configured to segment the background area by an interactive image segmentation algorithm to obtain a shadow-covered road, merge the shadow-covered road and the foreground area to generate a road main area, and process the road main area by a target contour method to obtain a target road area;

[0085] The planning module 510 is configured to perform route planning on the target road area using a target search algorithm.

[0086] In an optional embodiment, the preprocessing module 502 is further configured to:

[0087] Linearly stretching the remote sensing image to obtain a first remote sensing image;

[0088] Performing bilateral filtering on the remote sensing image to obtain a second remote sensing image;

[0089] A target remote sensing image is obtained based on the first remote sensing image and the second remote sensing image.

[0090] In an optional embodiment, the compensation module 504 is further configured to:

[0091] The ISODATA clustering algorithm is used to perform shadow detection on the initial remote sensing image to obtain shadow areas and non-shadow areas.

[0092] In an optional embodiment, the compensation module 504 is further configured to:

[0093] The blue component of the shadow-shaded area is suppressed, and the shadow-shaded area is compensated based on a first calculation formula to obtain a shadow-shaded image, wherein the first calculation formula includes:

[0094]

[0095] Where k(S) is the light intensity and light color of the shadow area; S(x, y) is the shadow area; a is a fixed constant; p is the exponential parameter in the Minkowski normal form, which can be any integer in [1, ∞]; For image and Gaussian filter convolution, It is a 3*3 template.

[0096] Based on a second calculation formula, the non-shadow-shielded area is compensated to obtain a non-shadow-shielded image, wherein the second calculation formula includes:

[0097]

[0098] Where k(NS) is the light intensity and light color of the non-shadow area; NS(x, y) is the non-shadow area; a is a fixed constant; p is the exponential parameter in the Minkowski normal form, which can be any integer in [1, ∞]; For image and Gaussian filter convolution, It is a 3*3 template.

[0099] A target remote sensing image is obtained based on the shadow-obstructed image and the non-shadow-obstructed image.

[0100] In an optional embodiment, the second segmentation module 508 is further configured to:

[0101] Using morphological methods and connected domain analysis, the main road area is refined, the sunken road edge is repaired by contour neighborhood search, the initial main road area is obtained, and the degree of shielding is calculated;

[0102] The contour patching method is used to process the contour endpoints of the initial road main area to obtain the target road area.

[0103] In an optional embodiment, the planning module 510 is further configured to:

[0104] The A* algorithm is used to perform route planning on the target road area.

[0105] In an optional embodiment, the device is further configured to:

[0106] The estimation module is configured to estimate the cost of route planning using a diagonal function.

[0107] By using the route planning device based on road obscuration provided in the embodiment of the present application, the obscured area is compensated based on light intensity and light brightness, which can effectively eliminate non-road surface shadows during shadow road extraction, reduce the interference of shadows such as vegetation on shadow road extraction, reduce the fragmentation of patches during shadow road extraction, better preserve the integrity of the main road patches, and reduce the workload of road post-processing.

[0108] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the route planning device based on road shielding, since it is basically similar to the route planning method embodiment based on road shielding, the description is relatively simple, and the relevant parts can be referred to the partial description of the route planning method embodiment based on road shielding.

[0109] Figure 6This is a block diagram of a computing device provided in an embodiment of the present application. The components of the computing device 600 include but are not limited to a memory 610 and a processor 620. The processor 620 is connected to the memory 610 via a bus 630, and a database 650 is used to store data.

[0110] The computing device 600 also includes an access device 640, which enables the computing device 600 to communicate via one or more networks 660. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 640 may include one or more of any type of network interface (e.g., a network interface card (NIC)) of wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, and a near field communication (NFC).

[0111] In one embodiment of the present specification, the above components of the computing device 600 and Figure 6 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 6 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0112] The computing device 600 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 600 may also be a mobile or stationary server.

[0113] The processor 620 is used to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the route planning method based on road obstruction.

[0114] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the computing device embodiment, since it is basically similar to the route planning method embodiment based on road obstruction, the description is relatively simple, and the relevant parts can be referred to the partial description of the route planning method embodiment based on road obstruction.

[0115] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the route planning method based on road obstruction.

[0116] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the computer-readable storage medium embodiment, since it is basically similar to the route planning method embodiment based on road obstruction, the description is relatively simple, and the relevant parts can be referred to the partial description of the route planning method embodiment based on road obstruction.

[0117] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned route planning method based on road obstruction.

[0118] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the computer program embodiment, since it is basically similar to the route planning method embodiment based on road obstruction, the description is relatively simple, and the relevant parts can be referred to the partial description of the route planning method embodiment based on road obstruction.

[0119] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0120] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0121] It should be noted that the above is a description of a specific embodiment of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of the present specification.

[0122] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0123] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A route planning method based on road obscuration, characterized in that: include: Acquiring a remote sensing image, and preprocessing the remote sensing image to obtain an initial remote sensing image; Performing shadow detection on the initial remote sensing image to obtain a shadowed area and a non-shadowed area, and compensating the shadowed area based on the light intensity and light color of the shadowed area and the non-shadowed area to obtain a target remote sensing image; Performing shadow detection on the target remote sensing image to obtain a shadow image and a non-shadow image, suppressing the blue component of the shadow image, performing shadow compensation on the shadow image based on a shadow compensation algorithm, and then segmenting the shadow image into a foreground area and a background area through an interactive image segmentation algorithm, wherein the foreground area is a road area highlighted in the target remote sensing image, and the background area is other areas in the target remote sensing image except the highlighted road area; The background area is segmented by an interactive image segmentation algorithm to obtain a shadow-covered road, the shadow-covered road and the foreground area are merged to generate a road main area, and the road main area is processed by a target contour method to obtain a target road area; A target search algorithm is used to perform route planning on the target road area.

2. The method according to claim 1, characterized in that The preprocessing of the remote sensing image to obtain the target remote sensing image includes: Linearly stretching the remote sensing image to obtain a first remote sensing image; Performing bilateral filtering on the remote sensing image to obtain a second remote sensing image; A target remote sensing image is obtained based on the first remote sensing image and the second remote sensing image.

3. The method according to claim 1, characterized in that The shadow masking detection is performed on the initial remote sensing image to obtain the shadow masking area and the non-shadow masking area, including: The ISODATA clustering algorithm is used to perform shadow detection on the initial remote sensing image to obtain shadow areas and non-shadow areas.

4. The method according to claim 1, characterized in that: The method of compensating the shadowed area based on the light intensity and light color of the shadowed area and the non-shadowed area to obtain a target remote sensing image includes: The blue component of the shadow-shaded area is suppressed, and the shadow-shaded area is compensated based on a first calculation formula to obtain a shadow-shaded image, wherein the first calculation formula includes: Where k(S) is the light intensity and light color of the shadow area; S(x, y) is the shadow area; a is a fixed constant; p is the exponential parameter in the Minkowski normal form, which can be any integer in [1, ∞]; For image and Gaussian filter convolution, It is a 3*3 template. Based on a second calculation formula, the non-shadow-shielded area is compensated to obtain a non-shadow-shielded image, wherein the second calculation formula includes: Where k(NS) is the light intensity and light color of the non-shadow area; NS(x, y) is the non-shadow area; a is a fixed constant; p is the exponential parameter in the Minkowski normal form, which can be any integer in [1, ∞]; For image and Gaussian filter convolution, It is a 3*3 template. A target remote sensing image is obtained based on the shadow-obstructed image and the non-shadow-obstructed image.

5. The method according to claim 1, characterized in that The method of processing the main road area by a target contour method to obtain a target road area includes: Using morphological methods and connected domain analysis, the main road area is refined, the sunken road edge is repaired by contour neighborhood search, the initial main road area is obtained, and the degree of shielding is calculated; The contour patching method is used to process the contour endpoints of the initial road main area to obtain the target road area.

6. The method according to claim 1, characterized in that The method of using a target search algorithm to perform route planning on the target road area includes: The A* algorithm is used to perform route planning on the target road area.

7. The method according to claim 1, characterized in that The method further comprises: Use the diagonal function to estimate the cost of route planning.

8. A route planning device based on road obscuration, characterized in that: include: A preprocessing module is configured to acquire a remote sensing image and preprocess the remote sensing image to obtain an initial remote sensing image; A compensation module is configured to perform shadow shielding detection on the initial remote sensing image to obtain a shadow shielding area and a non-shadow shielding area, and compensate the shielding area based on the light intensity and light color of the shadow shielding area and the non-shadow shielding area to obtain a target remote sensing image; A first segmentation module is configured to perform shadow detection on the target remote sensing image to obtain a shadow image and a non-shadow image, suppress a blue component of the shadow image, perform shadow compensation on the shadow image based on a shadow compensation algorithm, and then segment the shadow image into a foreground area and a background area through an interactive image segmentation algorithm, wherein the foreground area is a road area highlighted in the target remote sensing image, and the background area is other areas in the target remote sensing image except the highlighted road area; The second segmentation module is configured to segment the background area by an interactive image segmentation algorithm to obtain a shadow-covered road, merge the shadow-covered road and the foreground area to generate a road main body area, and process the road main body area by a target contour method to obtain a target road area; The planning module is configured to perform route planning on the target road area using a target search algorithm.

9. A computer device, characterized in that: The computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method according to any one of claims 1 to 7 when executing the program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an implementation program for information transmission, and when the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images