CN117235299A - Quick indexing method, system, equipment and medium for oblique photographic pictures - Google Patents

Abstract

This application discloses a method, system, computer equipment and media for rapid indexing of oblique photography photos. The method constructs an initial image data set by combining the names of the collected oblique photography photos with internal and external orientation elements. In the initial image data set, Basically, for a specific simulated modeling area, the projection coverage of the oblique photographic image within the height range of the simulated modeling area is obtained according to the internal and external azimuth elements of the image, and the projection coverage and the projection coverage ratio between the simulated modeling area are As the correlation between the oblique photographic image and the proposed modeling area, the oblique photographic photograph associated with the proposed modeling area is selected according to the degree of correlation, and the selected image is encoded using a combination of the initial image data set and the correlation degree. Oblique photography images are encoded to generate a simulated area image data set. The method described above can quickly extract oblique photography photos associated with the proposed modeling area without performing overall spatial calculation of the photos, thereby improving the efficiency of three-dimensional modeling.

Description

A fast indexing method, system, equipment and medium for oblique photography images

Technical field

The present application relates to the technical field of photo indexing, and in particular to a method, system, computer equipment and media for rapid indexing of oblique photography photos.

Background technique

UAV oblique photography, as shown in Figure 1, refers to installing a multi-head camera with multiple sensors on the UAV, using 1 orthophoto camera and 4 oblique cameras to photograph the ground objects in the survey area, so that The urban measurement effect has been greatly improved.

With the continuous upgrading and popularization of drone oblique photography technology, real-life 3D technology has also ushered in rapid development, and refined modeling of large urban scenes has formed a trend. In this process, various industries have accumulated a large amount of oblique photography data. How to efficiently utilize the existing image data and quickly extract the image data of the proposed modeling area in the survey area, so as to quickly produce three-dimensional models with fine textures? Finding the corresponding photos is an urgent problem that needs to be solved in the process of three-dimensional precision modeling.

The current common UAV oblique photography process is to first delineate the survey area, then carry out UAV oblique photography, and finally carry out regional network based on the collected oblique photography photos and corresponding airborne POS (Position and Orientation System) data. Adjustment, multi-view matching, point cloud meshing and multi-view texture mapping are used to finally produce an oblique 3D model. In this process, the management and indexing of oblique photography photo data were not considered, resulting in the resulting oblique photography photos being unable to be further extracted and utilized.

Contents of the invention

This application provides a method, system, computer equipment and media for fast indexing of oblique photographic images, to solve the technical problem of being unable to manage and index a large number of oblique photographic images in the existing three-dimensional modeling process, and to realize oblique photographic images. Rapid extraction and efficient utilization of slices.

In order to solve the above technical problems, in the first aspect, this application provides a quick indexing method for oblique photography photos, which method includes:

Obtain oblique photography photos and POS data corresponding to the oblique photography photos, and construct an initial image data set;

According to the POS data corresponding to the oblique photographic image, calculate the geographical spatial coordinates of the image corner points of the oblique photographic image at different heights;

Obtain the range of the simulated modeling area, and determine the relationship between all the oblique photography images and the The correlation degree of the simulated modeling area is based on the initial image data set, and the simulated modeling area image data set is generated according to the correlation degree.

Preferably, the construction of the initial image data set includes:

Determine whether the oblique photography photo contains position data and attitude data, and if so, construct an oblique photography photo pose data set based on the position data and attitude data;

If not, then set the posture data of the oblique photographic photos containing only position data to zero, and construct an oblique photographic photograph pose data set based on the position data and the zeroed posture data;

Construct a data set of orientation elements in the oblique photography photos according to the batch of oblique photography photos;

The oblique photographic photo pose data set and the oblique photographic photo internal orientation element data set are combined and coded to construct an initial image data set.

Preferably, calculating the geographical spatial coordinates of the image corner points of the oblique photography photos at different heights based on the POS data corresponding to the oblique photography photos includes:

Solve the inverse perspective transformation matrix according to the POS data corresponding to the oblique photography image;

Construct the collinear equation of the principal image point and the image corner point of the oblique photographic image according to the inverse perspective transformation matrix;

According to the collinear equations of the image principal points and image corner points of all the oblique photography photos, the geographical spatial coordinates of the image corner points at different heights of all the oblique photography photos are determined.

Preferably, solving the inverse perspective transformation matrix based on the POS data corresponding to the oblique photograph includes:

Convert the oblique photography photograph from the pixel coordinate system to the image coordinate system, and obtain the first translation vector;

Based on the first translation vector, convert the oblique photographic image from the image coordinate system to a camera coordinate system, and obtain a first rotation matrix and a second translation vector;

Based on the first rotation matrix and the second translation vector, the oblique photographic image is converted from the camera coordinate system to the world coordinate system to obtain the rotation matrix and translation vector for obtaining the inverse perspective transformation matrix.

Preferably, obtaining the range of the simulated modeling area includes:

Obtain the height of the simulated modeling area and the continuous point coordinates of the ground plane corresponding to the simulated modeling area;

The range of the pseudo-modelling area is characterized according to the height of the pseudo-modelling area and the continuous point coordinates of the ground plane corresponding to the pseudo-modelling area.

Preferably, the determination of the correlation between all oblique photography images and the simulated modeling area includes:

Determine the geospatial coordinates of the image corner point of the oblique photographic image at the height of the simulated modeling area based on the geographical spatial coordinates of the image corner point of the oblique photographic image at different heights;

Determine the projection coverage of all said oblique photographic images based on geospatial coordinates at the height of said simulated modeling area;

According to the projection coverage range and the ground plane corresponding to the pseudo-modelling area, the projection coverage rate is calculated, and the projection coverage rate is used as the correlation degree between the oblique photographic image and the pseudo-modelling area.

Preferably, generating a simulated modeling area image data set based on the degree of correlation includes:

Select oblique photography images that are related to the simulated modeling area according to the degree of correlation;

Construct a correlation data set of the oblique photography photos according to the correlation degree of the selected oblique photography photos that are related;

The selected initial image data set and the correlation data set of the associated oblique photography photos are combined and coded to generate a simulated regional image data set.

In a second aspect, this application also provides a rapid indexing system for oblique photography images, which system includes: a data acquisition unit, a calculation unit, and a simulated modeling area image association unit;

Data acquisition unit: used to acquire oblique photography photos and POS data corresponding to the oblique photography photos, and construct an initial image data set;

Calculation unit: configured to calculate the geographical spatial coordinates of the image corner points of the oblique photography photos at different heights based on the POS data corresponding to the oblique photography photos;

Simulated modeling area image correlation unit: used to obtain the range of the simulated modeling area, and determine based on the range of the simulated modeling area and the geographical spatial coordinates of the image corner points of all the oblique photography photos at different heights. The degree of correlation between all oblique photography photos and the simulated modeling area is based on the initial image data set, and a simulated modeling area image data set is generated according to the correlation degree.

In a third aspect, this application also provides a computer device. The computer device includes a memory, a processor and a transceiver, which are connected through a bus; the memory is used to store a set of computer program instructions and data, and to store the stored data. Transmitted to the processor, the processor executes the program instructions stored in the memory to perform the above-mentioned method.

In a fourth aspect, the present application also provides a computer-readable storage medium. A computer program is stored in the computer-readable storage medium. When the computer program is run, the above-mentioned method is implemented.

This application provides a quick indexing method, system, computer equipment and storage medium for oblique photography photos. The method described carries out standardized management on oblique photography photos collected during the flight, and constructs an initial image data set by combining the names of the oblique photography photos with the internal and external orientation elements. For the modeling area, the projection coverage of the oblique photographic image within the height range of the simulated modeling area is obtained based on the internal and external azimuth elements of the image. Based on the projection coverage ratio between the projection coverage and the simulated modeling area, the relationship between the oblique photographic image and the simulated modeling area is determined. According to the degree of correlation between the simulated modeling areas, select the oblique photographic images associated with the simulated modeling area according to the degree of correlation, and use the encoding method of the combination of the initial image data set and the correlation degree to encode the selected oblique photographic images. , to generate a simulated modeling area image data set. The fast indexing method for oblique photography photos provided by this application can quickly extract the oblique photography photos associated with the simulated modeling area without the need to solve the overall space of the photos. For areas that require single modeling, it can Quickly read the corresponding photos to improve the efficiency of 3D modeling.

Description of drawings

Figure 1 is a schematic diagram of UAV oblique photography provided by a preferred embodiment of the present application;

Figure 2 is a flow chart of a method for fast indexing of oblique photography images provided by a preferred embodiment of the present application;

Figure 3 is a schematic diagram of a method for constructing an initial image data set provided by a preferred embodiment of the present application;

Figure 4 is a schematic diagram of a method for calculating the geospatial coordinates of image angle points at different heights of oblique photography images provided by a preferred embodiment of the present application;

Figure 5 is a schematic diagram of a method for solving the inverse perspective transformation matrix provided by a preferred embodiment of the present application;

Figure 6 is a schematic diagram of a method for obtaining the range of a simulated modeling area provided by a preferred embodiment of the present application;

Figure 7 is a schematic diagram of a method for determining the correlation between all oblique photography images and the simulated modeling area provided by a preferred embodiment of the present application;

Figure 8 is a schematic diagram of the relationship between the ground plane actually corresponding to the image corner point and the projection coverage calculated according to the given height H provided by a preferred embodiment of the present application;

Figure 9 is a schematic diagram of the overlapping relationship between the projection coverage and the simulated modeling area of the oblique photography image provided by a preferred embodiment of the present application;

Figure 10 is a schematic diagram of a method for generating a simulated modeling area image data set provided by a preferred embodiment of the present application;

Figure 11 is a schematic diagram of a rapid indexing system for oblique photography provided by a preferred embodiment of the present application;

Figure 12 is a schematic diagram of a computer device provided by a preferred embodiment of the present application.

Detailed ways

The embodiments of the present application are specifically explained below with reference to the accompanying drawings. The examples are given for illustrative purposes only and cannot be understood as limiting the present application. The accompanying drawings are only for reference and illustration and do not constitute a limitation on the patent protection scope of the present application. limit. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

In order to solve the technical problem of being unable to manage and index a large number of oblique photography photos in the existing three-dimensional modeling process, embodiments of the present application provide a quick indexing method for oblique photography photos.

Please refer to Figure 2. In the embodiment of the present application, the method includes the following steps;

S1. Obtain oblique photography photos and POS data corresponding to the oblique photography photos, and construct an initial image data set.

S2. Calculate the geographical spatial coordinates of the image corner points of the oblique photography photo at different heights based on the POS data corresponding to the oblique photography photo.

S3. Obtain the range of the simulated modeling area, and based on the range of the simulated modeling area and the geographical spatial coordinates of the image angle points of all the oblique photography images at different heights, determine the relationship between all the oblique photography images and The correlation degree of the pseudo-modelling area is based on the initial image data set, and an image data set of the pseudo-modelling area is generated according to the correlation degree.

In this application, based on the technical problem to be solved, by calculating the oblique photographic images, the geographical spatial coordinates of the image angle points of the oblique photographic images at different heights are obtained, and by judging the distance between the oblique photographic images and the simulated modeling area Correlation, the oblique photographic images are updated according to the correlation degree to improve the accuracy of the oblique photographic images in the three-dimensional modeling process such as area network adjustment, multi-view matching, point cloud network construction and multi-view texture mapping. Extraction efficiency and accuracy.

In the preferred embodiment of the present application, the oblique photography image is first obtained, and the airborne POS data corresponding to the oblique photography image is taken.

When the drone is flying, the drone images acquired usually carry supporting POS data, so that the images can be processed more conveniently. POS data mainly includes GPS data and IMU data, that is, the external orientation elements in oblique photogrammetry: latitude, longitude, elevation, heading angle, pitch angle and roll angle.

GPS data is generally represented by X, Y, and Z, which represents the geographical location of the aircraft at the time of exposure during flight.

IMU data mainly includes heading angle, pitch angle and roll angle.

In a preferred embodiment of the present application, as shown in Figure 3, constructing an initial image data set includes the following steps:

S101. Determine whether the oblique photography photo contains position data and attitude data. If so, construct an oblique photography photo pose data set based on the position data and attitude data.

S102. If not, set the posture data to zero, and construct an oblique photography photo pose data set based on the position data and the zeroed posture data.

S103. Construct a data set of orientation elements in the oblique photography photos according to the batch of oblique photography photos.

S104. Combine and encode the oblique photographic image pose data set and the oblique photographic image internal orientation element data set to construct an initial image data set.

According to the technical requirements of UAV tilt measurement, aerial photography of the simulated model area is carried out to generate oblique photography photos. At the same time, the POS data of each photo is extracted based on the GPS and IMU sensors mounted on the UAV.

Information encoding is performed on each oblique photographic image. First, the oblique photographic photograph is judged to determine whether the POS data contains image data of position and attitude. If so, it indicates that the information of the oblique photographic photograph is complete, and the position is used. Data and posture data are used to construct an oblique photography pose data set, such as: (i=1, 2, 3, 4... are all photo numbers), X, Y, Z respectively represent the latitude, longitude and altitude of the aircraft at the exposure point during flight;/> ω and κ respectively represent the heading angle, pitch angle and roll angle of the aircraft at the exposure point in flight.

If not, it indicates that the information of the oblique photographic images is incomplete. In the embodiment of the present application, for the oblique photographic images with incomplete information, only the oblique photographic images containing position data are selected, and the oblique photographic images containing only position data are selected. The posture data of the oblique photography photos is set to zero, and a posture data set of the oblique photography photos is constructed based on the position data and the zeroed posture data. For example, V _i = {name _i , X, Y, Z, 0, 0, 0} (i = 1, 2, 3, 4... are all photo numbers).

Table 1 is an example of the oblique photography pose data set.

In the preferred embodiment of the present application, further, the inner orientation element of the oblique image is also used as the encoding element of the oblique image. At present, the tilt lenses used in oblique photography of UAVs have generally been calibrated, and the internal orientation elements are known quantities. For different batches of oblique photos, a data set W of the internal orientation elements of oblique photography photos can be established according to batches. _j = {p _j ,x _j ,y _j ,f _j }, where p represents the batch of oblique photography photos, x and y represent the coordinates of the principal point of the image in the camera coordinate system, f represents the principal distance of the photo, j=1, 2, 3, 4…, represents the flight batch number.

Table 2 is an example of the orientation data set in oblique photography images.

For the i-th photo of the j-th batch, encode it as To construct an initial image data set that corresponds one-to-one with oblique photography photos.

In the embodiment of the present application, the oblique photographic image pose data set and the oblique photographic image internal orientation element data set are combined and coded to construct an initial image data set, which represents the oblique photographic image with more comprehensive information and facilitates the oblique photography. Photos for more comprehensive retrieval and extraction.

In a preferred embodiment of the present application, the geographical spatial positions of the four image corner points of the oblique photography image at different heights are calculated based on the POS data corresponding to the oblique photography image. As shown in Figure 4, calculating the geographical spatial coordinates of the image corner points of the oblique photography photos at different heights based on the POS data corresponding to the oblique photography photos includes:

S201. Solve the inverse perspective transformation matrix according to the POS data corresponding to the oblique photographic image.

S202. Construct a collinear equation of the principal image point and the image corner point of the oblique photographic image according to the inverse perspective transformation matrix.

S203. Determine the geographical spatial coordinates of the image corner points at different heights of all the oblique photography photos based on the collinear equations of the image principal points and image corner points of all the oblique photography photos.

Based on the photo geospatial coordinate solution method, it is necessary to solve the perspective transformation matrix of the oblique photography image, determine the collinear equation of the image corner point of each oblique photography image, and then determine the geographical location of the image corner point of the oblique photography image at different heights. Spatial coordinates realize the conversion of oblique photography images from pixel coordinates to geographical spatial coordinates.

Solving the inverse perspective transformation matrix involves the transformation of four coordinate systems: world coordinate system, camera coordinate system, image coordinate system and pixel coordinate system.

World coordinate system: represented by Ow-XwYwZw. In the world coordinate system, the location of the object and the location of the camera can be marked. The world coordinate system generally shows the positional relationship between the camera and the object, and reflects the coordinates in the real world.

Camera coordinate system: represented by Oc-XcYcZc, with the camera optical center, that is, the center of the camera hole as the origin, the z-axis coincides with the optical axis and points in front of the camera, and the positive directions of the Xc-axis and Yc-axis are parallel to the object coordinate system. The position of the object relative to the camera can be defined in the camera coordinate system, where the origin of the coordinate system is the center of the camera hole.

Image coordinate system: represented by O-xy, using physical units to represent the position of the pixel, and the origin of the coordinates is the intersection position of the camera optical axis and the image plane. The x-axis and y-axis are respectively parallel to the Xc-axis and Yc-axis, indicating the actual position of the real object on the camera sensor.

Pixel coordinate system: An image exists in the computer in the form of pixels arranged in rows and columns. Therefore, in the pixel coordinate system, the row number and column number of each pixel are recorded. The origin of the coordinates is in the upper left corner, in pixels. For example, the coordinates (u, v) of a pixel point represent the u column and v row in the image array respectively.

Among them, the pixel coordinate system and the image coordinate system are defined on the plane, and they can be converted through translation. The conversion of the image coordinate system to the camera coordinate system belongs to the perspective projection relationship, from 2D to 3D. The transformation from the camera coordinate system to the world coordinate system is a rigid body transformation, that is, the object will not deform and only needs to be transformed through a rotation matrix and a translation vector.

In the embodiment of the present application, as shown in Figure 5, solving the inverse perspective transformation matrix based on the POS data corresponding to the oblique photography includes:

S2011. Convert the oblique photographic image from the pixel coordinate system to the image coordinate system, and obtain the first translation vector.

S2012. Based on the first translation vector, convert the oblique photography photograph from the image coordinate system to a camera coordinate system, and obtain a first rotation matrix and a second translation vector.

S2013. Based on the first rotation matrix and the second translation vector, convert the oblique photographic image from the camera coordinate system to the world coordinate system, and obtain the rotation matrix and translation vector for obtaining the inverse perspective transformation matrix.

Among them, after the above transformation, the conversion relationship between the world coordinate system and the pixel coordinate system is:

Among them, R represents the rotation matrix of the inverse perspective transformation matrix, T represents the translation vector of the inverse perspective transformation matrix, u ₀ and v ₀ represent the coordinates of the main point of the image in the pixel coordinate system, dx and dy represent the length of a pixel, and f represents the image Film main distance.

The rotation matrix of the inverse perspective transformation matrix is expressed as:

The translation vector of the inverse perspective transformation matrix is expressed as:

Among them, ΔX, ΔY, and ΔZ represent the translation distance of the main image point from the pixel coordinate system to the world coordinate system in the X-axis direction, the Y-axis direction, and the Z-axis direction.

Construct the collinear equation of the main image point and four image corner points of the oblique photographic image based on the inverse perspective transformation matrix,

According to the collinear equation, the geographical spatial coordinates of the image corner points of the oblique photographic images at different heights are calculated as follows:

Among them, a _i , b _i , c _i (i=1,2,3) represent the outer orientation elements An element of the 3×3 orthogonal rotation matrix R generated by ω and κ. x, y represent the coordinates of the image corner point with the principal point of the image as the origin, X, Y, Z are the coordinates of the corresponding ground point of the image corner point, f is the principal distance of the image, X _S , Y _S , Z _S ,/> ω and κ represent the oblique photography pose data set.

In the embodiment of the present application, based on the inverse transformation matrix, the collinear equation of the image corner point of the oblique photographic image is deduced according to the internal and external orientation elements of the oblique photographic image, and then the projection plane coordinates corresponding to the image corner point at different heights are solved. This determines the projection coverage of an oblique photographic image at a given height.

In this embodiment of the present application, the range of the proposed modeling area is obtained. The range includes the height of the proposed modeling area and the area formed by the ground plane corresponding to the simulated modeling area, including, as shown in Figure 6, the Obtaining the scope of the proposed modeling area includes the following steps:

S301. Obtain the height of the simulated modeling area and the continuous point coordinates of the ground plane corresponding to the simulated modeling area.

S302. Characterize the range of the pseudo-modelling area according to the height of the pseudo-modelling area and the continuous point coordinates of the ground plane corresponding to the pseudo-modelling area.

The area to be modeled should be a three-dimensional range consisting of a plane close to the ground and a corresponding height. The height should be the average height of the area to be modeled, represented by H.

The plane close to the ground in the proposed modeling area should be represented by a set of continuous points, characterized as:

Among them, m represents the number of points that make up the prefetched simulation model, and X _m and Y _m represent the positions of the points in the plane close to the ground in the simulated modeling area in the world coordinate system.

Further, in the embodiment of the present application, as shown in Figure 7, determining the correlation between all the oblique photography images and the simulated modeling area includes the following steps:

S303. Determine the geospatial coordinates of the image corner point of the oblique photographic image at the height of the simulated modeling area based on the geospatial coordinates of the image corner point of the oblique photographic image at different heights.

S304. Determine the projection coverage of all oblique photography images based on the geospatial coordinates of the height of the proposed modeling area.

S305: Calculate the projection coverage rate according to the projection coverage range and the ground plane corresponding to the simulated modeling area, and use the projection coverage rate as the correlation between the oblique photographic image and the simulated modeling area.

According to the height H determined in the proposed modeling area, the height is substituted into the geographical space coordinate equation of the image corner points of the oblique photography image at different heights, and the coordinates of the ground plane points corresponding to the four image corner points of the oblique photography image are obtained, and then according to the four The ground plane point coordinates corresponding to each image corner point determine the projection coverage of the oblique photographic image on the ground plane. As shown in Figure 8, the actual ground plane points corresponding to the image corner points (a, b, c, d) are A', B', C', D', which are calculated based on the given height H to obtain the projection points A, B, C, and D do not completely overlap.

In the preferred embodiment of the present application, the correlation degree between the oblique photographic image and the simulated modeling area is determined by comparing the overlap range between the projection coverage and the ground plane corresponding to the simulated modeling area. A large overlap range indicates A large degree of correlation and a small overlap range indicate a small degree of correlation.

As shown in Figure 9, the overlap range of the projection coverage of the oblique photographic image and the simulated modeling area is divided into non-overlapping, partial overlap and complete coverage. In order to express the correlation more specifically, the projection coverage is regarded as the relationship between the oblique photographic image and the simulated modeling area. The correlation degree of the proposed modeling area.

The calculation formula for projection coverage is:

Among them, S ₀ represents the area of the overlap range between the projection coverage of the oblique photographic image and the simulated modeling area, and S _ABCD represents the area of the projection coverage of the oblique photographic image at height H.

Further, in this embodiment of the present application, as shown in Figure 10, generating a simulated modeling area image data set based on the correlation includes the following steps:

S306: Select oblique photography images that are related to the simulated modeling area according to the degree of correlation.

S307: Construct a correlation data set of the oblique photography photos according to the correlation degree of the selected oblique photography photos that are related.

S308: Combine and code the selected initial image data set and the correlation data set of the associated oblique photography photos to generate a simulated modeling area image data set.

In the embodiment of the present application, the oblique photography images associated with the simulated modeling area are selected, and the initial image data set and correlation degree of the selected oblique photography images are combined and coded as each oblique photography image. The encoding of the slice is specifically expressed as follows:

Among them, i represents the photo number, and j represents the flight batch number.

In the preferred embodiment of the present application, the oblique photographic images are sorted according to the degree of correlation, so as to facilitate the retrieval and extraction of oblique photographic images and improve the efficiency of image retrieval and extraction.

To sum up, the oblique photography photos collected during the flight are standardized and managed, and the names of the oblique photography photos and the internal and external orientation elements are combined to construct an initial image data set. Based on the initial image data set, specific of the simulated modeling area. According to the internal and external orientation elements of the image, the projection coverage of the oblique photographic image within the height range of the simulated modeling area is obtained. According to the projection coverage rate between the projection coverage and the simulated modeling area, the tilt is determined. According to the degree of correlation between the photographic image and the proposed modeling area, select the oblique photographic photograph associated with the proposed modeling area according to the degree of correlation, and use the encoding method of the combination of the initial image data set and the correlation degree to encode the selected oblique photography The images are encoded to generate a simulated area image data set. The fast indexing method for oblique photography photos provided by this application can quickly extract the oblique photography photos associated with the simulated modeling area without the need to solve the overall space of the photos. For areas that require single modeling, it can Quickly read the corresponding photos to increase the speed of 3D modeling.

Correspondingly, as shown in Figure 11, based on a quick indexing method for oblique photography photos, embodiments of the present invention also provide a quick indexing system for oblique photography photos. The system includes: a data acquisition unit 1, a computing unit 2 and Simulated modeling area image correlation unit 3;

Data acquisition unit 1: used to acquire oblique photography photos and POS data corresponding to the oblique photography photos, and construct an initial image data set.

Calculation unit 2: configured to calculate the geographical spatial coordinates of the image corner points of the oblique photography photos at different heights based on the POS data corresponding to the oblique photography photos.

Simulated modeling area image association unit 3: used to obtain the range of the pseudo modeling area, and based on the range of the pseudo modeling area and the geographical spatial coordinates of the image corner points of all the oblique photography photos at different heights, Determine the correlation between all oblique photography photos and the simulated modeling area, and generate a simulated modeling area image data set based on the correlation based on the initial image data set.

For specific limitations on a quick indexing system for oblique photography photos, please refer to the above-mentioned limitations on a quick indexing method for oblique photography photos, which will not be described again here. Those of ordinary skill in the art will appreciate that the various modules and steps described in conjunction with the embodiments disclosed in this application can be implemented in hardware, software, or a combination of both. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each specific application, but such implementations should not be considered beyond the scope of this application.

As shown in Figure 12, a computer device provided by an embodiment of the present invention includes a memory, a processor and a transceiver, which are connected through a bus; the memory is used to store a set of computer program instructions and data, and store the stored data Transmitted to the processor, the processor executes the program instructions stored in the memory to perform the steps of the above-mentioned fast indexing method for oblique photography photos.

Wherein, the memory may include volatile memory or non-volatile memory, or may include both volatile and non-volatile memory; the processor may be a central processing unit, a microprocessor, an application-specific integrated circuit, a programmable Logic devices or combinations thereof. By way of illustration but not limitation, the above-mentioned programmable logic device may be a complex programmable logic device, a field programmable logic gate array, a general array logic or any combination thereof.

In addition, memory can be a physically separate unit or integrated with the processor.

Those of ordinary skill in the art can understand that the structure shown in Figure 12 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Specific computer equipment It is possible to include more or fewer components than shown in the figures, or to combine certain components, or to have the same arrangement of components.

In one embodiment, a computer-readable storage medium is provided for storing one or more computer programs, the one or more computer programs including program code, and when the computer program is run on a computer When running, the program code is used to perform the above-mentioned steps of rapid indexing of oblique photography images.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are generated in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable device. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, e.g., the computer instructions may be transferred from a website, computer, server, or data center Transmit to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line or wireless (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be a computer Any available media that can be accessed or a data storage device such as a server or data center integrated with one or more available media. The available media can be magnetic media, (for example, floppy disks, hard disks, tapes), optical media (for example, , DVD), or semiconductor media (such as SSD), etc.

Those skilled in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. The computer program During execution, the process may include the processes of the embodiments of each of the above methods.

This embodiment provides a method, system, computer equipment and storage medium for fast indexing of oblique photography photos, aiming at the technical problem of being unable to manage and index a large number of oblique photography photos in the existing three-dimensional modeling process. Standardize the management of oblique photography photos collected during the flight. The names of the oblique photography photos and the internal and external orientation elements are used to construct an initial image data set. Based on the initial image data set, specific simulation models are built. Model area, according to the internal and external orientation elements of the image, obtain the projection coverage of the oblique photographic image within the height range of the simulated modeling area, and determine the relationship between the oblique photographic image and the simulated modeling area based on the projection coverage ratio between the projection coverage range and the simulated modeling area. According to the degree of correlation between the modeling areas, select the oblique photography photos associated with the proposed modeling area according to the degree of correlation, and use the coding method of the combination of the initial image data set and the correlation degree to encode the selected oblique photography photos. To generate a simulated modeling area image data set. The fast indexing method for oblique photography photos provided by this application can quickly extract the oblique photography photos associated with the simulated modeling area without the need to solve the overall space of the photos. For areas that require single modeling, it can Quickly read the corresponding photos to increase the speed of 3D modeling.

The above-described embodiments only express several preferred embodiments of the present application. The descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that, for those of ordinary skill in the art, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be regarded as the protection scope of the present application. Therefore, the protection scope of the patent of this application shall be subject to the protection scope of the claims.

Claims (10)

1. A quick indexing method for oblique photography photos, characterized in that the method includes: Obtain oblique photography photos and POS data corresponding to the oblique photography photos, and construct an initial image data set; According to the POS data corresponding to the oblique photographic image, calculate the geographical spatial coordinates of the image corner points of the oblique photographic image at different heights; Obtain the range of the simulated modeling area, and determine the relationship between all the oblique photography images and the The correlation degree of the simulated modeling area is based on the initial image data set, and the simulated modeling area image data set is generated according to the correlation degree. 2. The method for fast indexing of oblique photography photos as claimed in claim 1, wherein said constructing an initial image data set includes: Determine whether the oblique photography photo contains position data and attitude data, and if so, construct an oblique photography photo pose data set based on the position data and attitude data; If not, then set the posture data of the oblique photographic photos containing only position data to zero, and construct an oblique photographic photograph pose data set based on the position data and the zeroed posture data; Construct a data set of orientation elements in the oblique photography photos according to the batch of oblique photography photos; The oblique photographic photo pose data set and the oblique photographic photo internal orientation element data set are combined and coded to construct an initial image data set. 3. The method for fast indexing of oblique photography photos as claimed in claim 1, characterized in that, according to the POS data corresponding to the oblique photography photos, the image angle points of the oblique photography photos are calculated at different heights. The geospatial coordinates include: Solve the inverse perspective transformation matrix according to the POS data corresponding to the oblique photography image; Construct the collinear equation of the principal image point and the image corner point of the oblique photographic image according to the inverse perspective transformation matrix; According to the collinear equations of the image principal points and image corner points of all the oblique photography photos, the geographical spatial coordinates of the image corner points at different heights of all the oblique photography photos are determined. 4. The method for fast indexing of oblique photography photos as claimed in claim 3, wherein the step of solving the inverse perspective transformation matrix according to the POS data corresponding to the oblique photography photos includes: Convert the oblique photography photograph from the pixel coordinate system to the image coordinate system, and obtain the first translation vector; Based on the first translation vector, convert the oblique photographic image from the image coordinate system to a camera coordinate system, and obtain a first rotation matrix and a second translation vector; Based on the first rotation matrix and the second translation vector, the oblique photographic image is converted from the camera coordinate system to the world coordinate system to obtain the rotation matrix and translation vector for obtaining the inverse perspective transformation matrix. 5. The method for fast indexing of oblique photography photos as claimed in claim 2, wherein said obtaining the range of the simulated modeling area includes: Obtain the height of the simulated modeling area and the continuous point coordinates of the ground plane corresponding to the simulated modeling area; The range of the pseudo-modelling area is characterized according to the height of the pseudo-modelling area and the continuous point coordinates of the ground plane corresponding to the pseudo-modelling area. 6. The method for fast indexing of oblique photography photos as claimed in claim 5, wherein determining the correlation between all oblique photography photos and the simulated modeling area includes: Determine the geospatial coordinates of the image corner point of the oblique photographic image at the height of the simulated modeling area based on the geographical spatial coordinates of the image corner point of the oblique photographic image at different heights; Determine the projection coverage of all said oblique photographic images based on geospatial coordinates at the height of said simulated modeling area; According to the projection coverage range and the ground plane corresponding to the pseudo-modelling area, the projection coverage rate is calculated, and the projection coverage rate is used as the correlation degree between the oblique photographic image and the pseudo-modelling area. 7. The method for fast indexing of oblique photography photos as claimed in claim 6, wherein generating a simulated area image data set according to the degree of correlation includes: Select oblique photography images that are related to the simulated modeling area according to the degree of correlation; Construct a correlation data set of the oblique photography photos according to the correlation degree of the selected oblique photography photos that are related; The selected initial image data set and the correlation data set of the associated oblique photography photos are combined and coded to generate a simulated regional image data set. 8. A rapid indexing system for oblique photography photos, characterized in that the system includes: a data acquisition unit, a calculation unit and a simulated modeling area image association unit; Data acquisition unit: used to acquire oblique photography photos and POS data corresponding to the oblique photography photos, and construct an initial image data set; Calculation unit: configured to calculate the geographical spatial coordinates of the image corner points of the oblique photography photos at different heights based on the POS data corresponding to the oblique photography photos; Simulated modeling area image correlation unit: used to obtain the range of the simulated modeling area, and determine based on the range of the simulated modeling area and the geographical spatial coordinates of the image corner points of all the oblique photography photos at different heights. The degree of correlation between all oblique photography photos and the simulated modeling area is based on the initial image data set, and a simulated modeling area image data set is generated according to the correlation degree. 9. A computer device, characterized in that: the computer device includes a memory, a processor and a transceiver, which are connected through a bus; the memory is used to store a set of computer program instructions and data, and transmit the stored data to A processor executes program instructions stored in the memory to perform the method according to any one of claims 1 to 7. 10. A computer-readable storage medium, characterized in that: a computer program is stored in the computer-readable storage medium, and when the computer program is run, the method according to any one of claims 1 to 7 is implemented. .