A method for identifying and fusing urban orthophotos

Abstract

The application discloses a kind of urban orthographic image map identification fusion methods, including the following steps, first, initial identification, form starting seed, second, multiple overlap area fusion, form fusion seed, third, inflation fusion processing, form secondary fusion seed, fourth, form target seed. The embodiment of the application can identify the complete target object.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and specifically to a method for recognizing and fusing urban orthophoto images. Background Technology

[0002] An orthophoto of a city is usually stored using a set of images, with each image corresponding to a part of the city. During the recognition process, each area needs to be identified, and the pixels of the target area will be marked. Current recognition methods often cannot identify the complete target object when identifying target objects such as buildings, but can only identify a part of the target object. This problem is very prominent.

[0003] Chinese invention patent application CN201910606187.2 discloses a method and system for mosaicking urban orthophoto images. First, an initial mosaicking network is generated based on a Voronoi diagram to determine the contribution range of each image to the mosaicking result. Then, the vertices of the mosaicking network are adjusted based on DSM data to avoid stitching gaps and ensure nodes avoid obstacle areas with projection differences, such as buildings and trees. After the initial mosaicking network is constructed and adjusted, the direction of each mosaicking line is optimized. First, the DSM data within the search range is processed to construct a search cost image. Then, an improved JPS algorithm is used to search for and evaluate key skip nodes, improving search efficiency and extracting an optimal mosaicking line that avoids obstacle areas. The images are then mosaicked according to the optimized mosaicking line to form a final high-quality seamless mosaicked image.

[0004] While the above-mentioned scheme has the advantages of improving search efficiency and forming high-quality seamless mosaics, it cannot identify and fuse urban orthophoto maps during the implementation process. Summary of the Invention

[0005] The main objective of this invention is to provide a method for recognizing and fusing urban orthophoto images in order to solve the problems in the background art.

[0006] To achieve the above objectives, the present invention provides a method for identifying and fusing urban orthophoto images, comprising the following steps: first, initial identification to form a starting seed; second, fusion of multiple overlapping regions to form a fusion seed; third, dilation fusion processing to form a secondary fusion seed; and fourth, formation of a target seed.

[0007] Optionally, the starting seed is obtained by normalizing the set of adjacent pixels with the same label.

[0008] Optionally, the pixel belongs to a single image.

[0009] Optionally, the fusion seed is obtained by fusing the overlapping parts of multiple starting seeds into a whole.

[0010] Optionally, the multiple starting seeds are from different images.

[0011] Optionally, during the expansion process of the fusion seed, new intersections will be generated between many starting seeds, and the starting seeds with intersections will be fused again to obtain the secondary fusion seed.

[0012] Optionally, the secondary fusion seed is subjected to corrosion treatment to obtain the target seed.

[0013] In this embodiment of the invention, a method is adopted to identify pixels, process them, and then identify them again. Through the steps of identifying an initial seed, a fusion seed, a secondary fusion seed, and forming a target seed, the goal of identifying a complete target object is achieved. This realizes the technical effect of creating a complete image from the orthophoto of a city and storing it. It also solves the technical problem that existing technologies cannot identify complete target objects, only partial ones, requiring users to manually stitch together each target object. This method can solve the problem of incomplete identification of urban orthophotos and the problem of fusing multiple overlapping image regions, and has a certain degree of scalability. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] In this application, the terms "upper," "lower," "left," "right," "front," "rear," "top," "bottom," "inner," "outer," "middle," "vertical," "horizontal," "lateral," and "longitudinal" indicate orientation or positional relationships. These terms are primarily used to better describe this application and its embodiments and are not intended to limit the indicated devices, elements, or components to having a specific orientation or to be constructed and operated in a specific orientation.

[0017] Furthermore, in addition to indicating location or positional relationship, some of the aforementioned terms may also have other meanings. For example, the term "above" may also be used in some cases to indicate a certain dependency or connection relationship. Those skilled in the art can understand the specific meaning of these terms in this application based on the specific circumstances.

[0018] In addition, the term "multiple" should mean two or more.

[0019] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the embodiments.

[0020] Example 1

[0021] A method for identifying and fusing urban orthophotos includes the following steps: first, initial identification to form a starting seed; second, fusing multiple overlapping regions to form a fusion seed; third, dilatational fusion processing to form a secondary fusion seed; and fourth, forming a target seed.

[0022] By identifying pixels, processing them, and then identifying them again, the method achieves the goal of identifying complete target objects through steps such as identifying initial seeds, merging seeds, secondary merging seeds, and forming target seeds. This enables the technical effect of creating a complete image from the orthophoto of a city and storing it. It also solves the technical problem that existing technologies cannot identify complete target objects but can only identify a part of them, which requires users to manually stitch the target objects one by one.

[0023] The starting seed is obtained by unifying the set of adjacent pixels with the same label.

[0024] A pixel belongs to a single image.

[0025] A fusion seed is obtained by merging the overlapping parts of multiple starting seeds into a single whole.

[0026] Multiple starting seeds come from different images.

[0027] During the expansion of the fusion seed, many initial seeds will have new intersections. The initial seeds with intersections will be fused again to obtain the secondary fusion seed.

[0028] For the target recognition region of a single image, a set of adjacent pixels with the same label is grouped into a "starting seed". A single image will generate many "starting seeds". In multiple single images, overlapping regions are fused, and the overlapping parts of the "starting seeds" are merged into a whole to form a "fusion seed". All "fusion seeds" are dilated. The dilation of the seeds causes many seeds to have new intersections. The overlapping seeds are merged again to form a "secondary fusion seed". The secondary fusion seed is processed to finally obtain the "target seed" to be recognized.

[0029] Example 2

[0030] A method for identifying and fusing urban orthophotos includes the following steps: first, initial identification to form a starting seed; second, fusing multiple overlapping regions to form a fusion seed; third, dilatational fusion processing to form a secondary fusion seed; and fourth, forming a target seed.

[0031] By identifying pixels, processing them, and then identifying them again, the method achieves the goal of identifying complete target objects through steps such as identifying initial seeds, merging seeds, secondary merging seeds, and forming target seeds. This enables the technical effect of creating a complete image from the orthophoto of a city and storing it. It also solves the technical problem that existing technologies cannot identify complete target objects but can only identify a part of them, which requires users to manually stitch the target objects one by one.

[0032] The starting seed is obtained by unifying the set of adjacent pixels with the same label.

[0033] A pixel belongs to a single image.

[0034] A fusion seed is obtained by merging the overlapping parts of multiple starting seeds into a single whole.

[0035] Multiple starting seeds come from different images.

[0036] During the expansion of the fusion seed, many initial seeds will have new intersections. The initial seeds with intersections will be fused again to obtain the secondary fusion seed.

[0037] The target seed is obtained by corroding the secondary fusion seed.

[0038] For the target recognition region of a single image, a set of adjacent pixels with the same label is grouped into a "starting seed". A single image will generate many "starting seeds". In multiple single images, overlapping regions are fused, and the overlapping parts of the "starting seeds" are merged into a whole to form a "fusion seed". All "fusion seeds" are dilated. The dilation of the seeds causes many seeds to have new intersections. The overlapping seeds are merged again to form a "secondary fusion seed". The secondary fusion seed is then eroded to finally obtain the "target seed" to be recognized.

[0039] While embodiments of the invention have been described, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A method for recognizing and fusing urban orthophoto maps, characterized in that, It includes the following steps, The first step is initial identification to form a starting seed. The starting seed is obtained by unifying the set of adjacent pixels with the same label. The pixels belong to a single image. The second step is to merge multiple overlapping regions to form a fusion seed. The fusion seed is obtained by merging the overlapping parts of multiple starting seeds into a whole. The multiple starting seeds come from different images. The third step is expansion and fusion processing to form a secondary fusion seed. The secondary fusion seed is obtained by creating new intersections between many initial seeds during the expansion process of the fusion seed, and then fusing the intersecting initial seeds again. The fourth step is to form a target seed, which is obtained by etching the secondary fusion seed.