A method, system, device and medium for quickly indexing oblique photographic images

Abstract

The present application discloses a method, system, computer device, and medium for quickly indexing oblique photographic images. The method constructs an initial image dataset by combining the names of collected oblique photographic images with internal and external orientation elements. Based on the initial image dataset, for a specific intended modeling area, the projection coverage of the oblique photographic images within the height range of the intended modeling area is obtained according to the internal and external orientation elements of the image. The projection coverage ratio between the projection coverage range and the intended modeling area is used as the correlation between the oblique photographic images and the intended modeling area. The oblique photographic images associated with the intended modeling area are selected based on the magnitude of the correlation. The selected oblique photographic images are encoded using an encoding method combining the initial image dataset and the correlation to generate an image dataset of the intended modeling area. The method can quickly extract oblique photographic images associated with the intended modeling area without performing an overall spatial solution on the images, thereby improving the efficiency of three-dimensional modeling.

Description

Technical Field

[0001] The present application relates to the field of photo indexing technology, and in particular to a method, system, computer equipment and medium for quickly indexing oblique photography photos. Background Art

[0002] Drone oblique photography, such as Figure 1 As shown in the figure, a multi-head camera with multiple sensors is installed on a UAV, and one orthophoto camera and four oblique cameras are used to shoot objects in the survey area, which greatly improves the urban surveying effect.

[0003] With the continuous advancement and widespread adoption of drone oblique photography technology, real-world 3D technology is experiencing rapid development, and the trend toward detailed modeling of large urban scenes is becoming increasingly prominent. This process has resulted in a vast amount of oblique photography image data being accumulated across various industries. The challenge of implementing detailed 3D modeling is to efficiently utilize this existing image data and rapidly extract image data for the areas to be modeled within the survey area, thereby quickly locating the corresponding images when producing finely textured 3D models.

[0004] The current common process for drone oblique photography involves first defining the survey area, then conducting drone oblique photography, and finally, using the acquired oblique images and the corresponding onboard Position and Orientation System (POS) data, performing block adjustment, multi-view matching, point cloud meshing, and multi-view texture mapping to produce an oblique 3D model. This process often neglects the management and indexing of oblique photography data, resulting in the oblique images being unable to be further extracted and utilized. Summary of the Invention

[0005] The present application provides a method, system, computer equipment and medium for quickly indexing oblique photographic images to solve the technical problem that a large number of oblique photographic images cannot be managed and indexed in the existing three-dimensional modeling process, and can realize the rapid extraction and efficient use of oblique photographic images.

[0006] To solve the above technical problems, in a first aspect, the present application provides a method for fast indexing of oblique photographic images, the method comprising:

[0007] Obtaining oblique photography images and POS data corresponding to the oblique photography images to construct an initial image data set;

[0008] Calculating the geographic space coordinates of the image corner points of the oblique photography pictures at different heights according to the POS data corresponding to the oblique photography pictures;

[0009] Obtaining the scope of the proposed modeling area, and determining the correlation between all the oblique photographs and the proposed modeling area based on the scope of the proposed modeling area and the geographic spatial coordinates of the image corner points of all the oblique photographs at different heights, and generating an image dataset of the proposed modeling area based on the correlation based on the initial image dataset.

[0010] Preferably, the constructing of the initial image dataset includes:

[0011] Determining whether the oblique photography image contains position data and posture data, and if so, constructing an oblique photography image pose data set based on the position data and posture data;

[0012] If not, setting the posture data of the oblique photography film containing only the position data to zero, and constructing the oblique photography film posture data set according to the position data and the zeroed posture data;

[0013] Constructing an oblique photography internal orientation element dataset according to the batches of the oblique photography images;

[0014] The oblique photography image pose dataset and the oblique photography image internal orientation element dataset are combined and encoded to construct an initial image dataset.

[0015] Preferably, the step of calculating the geographic spatial coordinates of the image corners of the oblique photograph at different heights based on the POS data corresponding to the oblique photograph includes:

[0016] Solving the inverse perspective transformation matrix according to the POS data corresponding to the oblique photographic image;

[0017] Constructing the collinear equations of the principal point and the corner points of the oblique photographic image according to the inverse perspective transformation matrix;

[0018] The geographic space coordinates of the image corner points of all the oblique photographic images at different heights are determined according to the collinear equations of the image principal points and the image corner points of all the oblique photographic images.

[0019] Preferably, solving the inverse perspective transformation matrix according to the POS data corresponding to the oblique photographic image includes:

[0020] Converting the oblique photographic image from a pixel coordinate system to an image coordinate system to obtain a first translation vector;

[0021] Based on the first translation vector, the oblique photographic image is converted from the image coordinate system to a camera coordinate system to obtain a first rotation matrix and a second translation vector;

[0022] Based on the first rotation matrix and the second translation vector, the oblique photographic image is converted from a camera coordinate system to a world coordinate system to obtain a rotation matrix and a translation vector for obtaining an inverse perspective transformation matrix.

[0023] Preferably, obtaining the range of the area to be modeled includes:

[0024] Obtaining the height of the proposed modeling area and the coordinates of consecutive points on the ground plane corresponding to the proposed modeling area;

[0025] The range of the proposed modeling area is represented according to the height of the proposed modeling area and the coordinates of consecutive points on the ground plane corresponding to the proposed modeling area.

[0026] Preferably, the determining of the correlation between all the oblique photographs and the proposed modeling area includes:

[0027] Determining the geographic space coordinates of the image corner points of the oblique photography pictures at the height of the proposed modeling area according to the geographic space coordinates of the image corner points of the oblique photography pictures at different heights;

[0028] Determining the projection coverage of all the oblique photographs according to the geospatial coordinates of the height of the area to be modeled;

[0029] The projection coverage ratio is calculated based on the projection coverage range and the ground plane corresponding to the area to be modeled, and the projection coverage ratio is used as the correlation degree between the oblique photography film and the area to be modeled.

[0030] Preferably, generating the image dataset of the simulated modeling area according to the correlation degree includes:

[0031] Selecting oblique photographs associated with the area to be modeled according to the degree of association;

[0032] Constructing a correlation degree data set of the oblique photography pictures according to the correlation degrees of the selected oblique photography pictures having correlation;

[0033] The selected initial image dataset and the correlation degree dataset of the associated oblique photographs are combined and encoded to generate an image dataset of the proposed modeling area.

[0034] In a second aspect, the present application further provides a system for rapid indexing of oblique photographic images, the system comprising: a data acquisition unit, a calculation unit, and a unit for associating images of a proposed modeling area;

[0035] Data acquisition unit: used to acquire oblique photography images and POS data corresponding to the oblique photography images, and construct an initial image data set;

[0036] A calculation unit is used to calculate the geographic space coordinates of the image corner points of the oblique photography pictures at different heights according to the POS data corresponding to the oblique photography pictures;

[0037] The image association unit for the proposed modeling area is used to obtain the scope of the proposed modeling area, and based on the scope of the proposed modeling area and the geographic spatial coordinates of the image corner points of all the oblique photographs at different heights, determine the correlation between all the oblique photographs and the proposed modeling area, and generate the proposed modeling area image dataset based on the correlation based on the initial image dataset.

[0038] In a third aspect, the present application also provides a computer device, which includes a memory, a processor and a transceiver, which are connected via a bus; the memory is used to store a set of computer program instructions and data, and transmit the stored data to the processor, and the processor executes the program instructions stored in the memory to execute the method described above.

[0039] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed, the above-described method is implemented.

[0040] The present application provides a method, system, computer equipment and storage medium for fast indexing of oblique photographic images. The method performs standardized management on the oblique photographic images collected during the flight, constructs an initial image data set together with the oblique photographic image names and internal and external orientation elements, and on the basis of the initial image data set, obtains the projection coverage of the oblique photographic images within the height range of the intended modeling area according to the internal and external orientation elements of the image for a specific intended modeling area, determines the correlation between the oblique photographic images and the intended modeling area according to the projection coverage and the projection coverage ratio between the projected coverage and the intended modeling area, selects the oblique photographic images associated with the intended modeling area according to the magnitude of the correlation, and encodes the selected oblique photographic images using a coding method combining the initial image data set and the correlation to generate an image data set of the intended modeling area. The method for fast indexing of oblique photographic images provided by the present application can quickly extract oblique photographic images associated with the intended modeling area without performing overall spatial solution on the images, and can quickly read the corresponding images for areas that require individual modeling, thereby improving the efficiency of three-dimensional modeling. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a schematic diagram of drone oblique photography provided by a preferred embodiment of the present application;

[0042] Figure 2 This is a flow chart of a method for quickly indexing oblique photographic images provided by a preferred embodiment of the present application;

[0043] Figure 3 This is a schematic diagram of a method for constructing an initial image dataset provided by a preferred embodiment of the present application;

[0044] Figure 4 This is a schematic diagram of a method for calculating the geographic spatial coordinates of image corners at different heights of an oblique photograph provided by a preferred embodiment of the present application;

[0045] Figure 5 This is a schematic diagram of a method for solving an inverse perspective transformation matrix provided by a preferred embodiment of the present application;

[0046] Figure 6 This is a schematic diagram of a method for obtaining the range of a proposed modeling area provided by a preferred embodiment of the present application;

[0047] Figure 7 This is a schematic diagram of a method for determining the degree of association between all oblique photographs and the area to be modeled, provided by a preferred embodiment of the present application;

[0048] Figure 8 This is a schematic diagram of the relationship between the ground plane actually corresponding to the image corner point and the projected coverage calculated based on a given height H, provided in a preferred embodiment of the present application;

[0049] Figure 9 This is a schematic diagram of the overlapping relationship between the projection coverage of the oblique photography film and the intended modeling area provided by a preferred embodiment of the present application;

[0050] Figure 10 This is a schematic diagram of a method for generating an image dataset of a simulated modeling area provided by a preferred embodiment of the present application;

[0051] Figure 11 This is a schematic diagram of a fast indexing system for oblique photography provided by a preferred embodiment of the present application;

[0052] Figure 12 This is a schematic diagram of a computer device provided by a preferred embodiment of the present application. DETAILED DESCRIPTION

[0053] The following describes the embodiments of the present application in detail with reference to the accompanying drawings. The embodiments are provided for illustrative purposes only and are not to be construed as limiting the present application. The accompanying drawings are provided for reference and illustration purposes only and do not constitute a limitation on the scope of protection of the present application. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments in this application without creative effort are also within the scope of protection of this application.

[0054] In order to solve the technical problem that a large number of oblique photographic images cannot be managed and indexed in the existing three-dimensional modeling process, an embodiment of the present application provides a method for quickly indexing oblique photographic images.

[0055] See also Figure 2 , in an embodiment of the present application, the method comprises the following steps;

[0056] S1. Obtain oblique photography images and POS data corresponding to the oblique photography images to construct an initial image data set.

[0057] S2. Calculate the geographic space coordinates of the corner points of the oblique photography pictures at different heights according to the POS data corresponding to the oblique photography pictures.

[0058] S3. Obtain the scope of the proposed modeling area, and determine the correlation between all the oblique photographs and the proposed modeling area based on the scope of the proposed modeling area and the geographic spatial coordinates of the image corner points of all the oblique photographs at different heights. Based on the initial image dataset, generate an image dataset of the proposed modeling area according to the correlation.

[0059] In this application, based on the technical problem to be solved, the geographic spatial coordinates of the image corner points of the oblique photographic images at different heights are obtained by calculating the oblique photographic images, and the correlation between the oblique photographic images and the area to be modeled is judged, and the data set of the oblique photographic images is updated according to the correlation, so as to improve the efficiency and accuracy of the extraction of oblique photographic images in the three-dimensional modeling process such as regional network adjustment, multi-view matching, point cloud networking and multi-view texture mapping.

[0060] In a preferred embodiment of the present application, firstly, an oblique photographic image and the onboard POS data corresponding to the oblique photographic image are acquired.

[0061] During drone flight operations, the captured images often carry accompanying POS data, making image processing more convenient. POS data primarily includes GPS and IMU data, which are the exterior orientation elements used in oblique photogrammetry: latitude, longitude, elevation, heading, pitch, and roll.

[0062] GPS data is generally expressed in X, Y, and Z, representing the geographic location of the aircraft at the moment of exposure during flight.

[0063] IMU data mainly includes heading angle, pitch angle and roll angle.

[0064] In the preferred embodiment of this application, Figure 3 As shown, the construction of the initial image dataset includes the following steps:

[0065] S101: Determine whether the oblique photography image contains position data and posture data. If so, construct an oblique photography image position and posture data set based on the position data and posture data.

[0066] S102: If not, the posture data is reset to zero, and an oblique photography posture data set is constructed according to the position data and the zeroed posture data.

[0067] S103: Constructing an oblique photography internal orientation element dataset according to the batches of the oblique photography images.

[0068] S104: Combining and encoding the oblique photography image pose dataset and the oblique photography image internal orientation element dataset to construct an initial image dataset.

[0069] In accordance with the technical requirements of drone tilt measurement, aerial photography of the proposed modeling area is carried out to generate tilt photographic images. At the same time, the POS data of each image is extracted based on the GPS and IMU sensors carried by the drone.

[0070] Information encoding is performed on each oblique photograph. First, the oblique photograph is judged to determine whether the POS data contains image data of position and posture. If so, it indicates that the information of the oblique photograph is complete. The position data and posture data are used to construct the oblique photograph pose dataset, such as: (i=1, 2, 3, 4... are all picture numbers), X, Y, Z represent the latitude, longitude and altitude of the aircraft at the exposure point during flight respectively; ω,κ represent the heading angle, pitch angle and roll angle of the aircraft at the exposure point in flight, respectively.

[0071] If not, it indicates that the information of the oblique photography is incomplete. In the embodiment of the present application, for oblique photography images with incomplete information, only the oblique photography images containing position data are selected, and the posture data of the oblique photography images containing only position data are set to zero. The oblique photography image pose data set 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 picture numbers).

[0072] Table 1 shows an example of an oblique photography pose dataset.

[0073]

[0074] In the preferred embodiment of the present application, the internal orientation elements of the oblique photography images are further used as coding elements of the oblique image images. At present, the oblique lenses carried by drones for oblique photography are generally calibrated, and their internal orientation elements are known quantities. For different batches of oblique images, an oblique photography image internal orientation element dataset W can be established by batch. j ={p j ,x j ,y j ,f j}, where p represents the batch of oblique photography images, x and y represent the coordinates of the principal point in the camera coordinate system, f represents the principal distance of the image, and j = 1, 2, 3, 4, ..., represents the flight batch number.

[0075] Table 2 shows an example of an internal orientation dataset of oblique photography images.

[0076]

[0077]

[0078] For the i-th picture in the j-th batch, encode it as To construct an initial image dataset that corresponds one-to-one to the oblique photography images.

[0079] In an embodiment of the present application, the oblique photography image pose dataset and the oblique photography image internal orientation element dataset are combined and encoded to construct an initial image dataset, so as to characterize the oblique photography images with more comprehensive information, thereby facilitating more comprehensive retrieval and extraction of the oblique photography images.

[0080] In a preferred embodiment of the present application, the geographical spatial positions of the four corner points of the oblique photographic film at different heights are calculated based on the POS data corresponding to the oblique photographic film. Figure 4 As shown, the calculation of the geographic space coordinates of the image corner points of the oblique photographic images at different heights based on the POS data corresponding to the oblique photographic images includes:

[0081] S201: Solve the inverse perspective transformation matrix according to the POS data corresponding to the oblique photographic image.

[0082] S202: Constructing collinear equations of the principal point and the corner points of the oblique photographic image according to the inverse perspective transformation matrix.

[0083] S203 , determining the geographic space coordinates of the image corner points of all the oblique photographic images at different heights according to the collinear equations of the image principal points and the image corner points of all the oblique photographic images.

[0084] Based on the method of solving the geospatial coordinates of images, it is necessary to solve the perspective transformation matrix of the oblique photographic images, determine the collinear equations of the image corners of each oblique photographic image, and then determine the geospatial coordinates of the image corners of the oblique photographic images at different heights, so as to realize the conversion of the oblique photographic images from pixel coordinates to geospatial coordinates.

[0085] 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.

[0086] World coordinate system: Expressed as Ow-XwYwZw, the world coordinate system can be used to mark the position of objects and the position of the camera. The world coordinate system generally shows the positional relationship between the camera and the object, reflecting the coordinates in the real world.

[0087] The camera coordinate system is represented by Oc-XcYcZc. Its origin is the camera's optical center, or the center of the camera's pinhole. The z-axis coincides with the optical axis and points forward. The positive directions of the Xc and Yc axes are parallel to the object coordinate system. The camera coordinate system defines the position of an object relative to the camera, with the origin being the center of the camera's pinhole.

[0088] Image coordinate system: denoted by O-xy, pixel positions are expressed in physical units, with the origin being the intersection of the camera's optical axis and the image plane. The x-axis and y-axis are parallel to the Xc-axis and Yc-axis, respectively, and represent the actual position of real objects on the camera's sensor.

[0089] Pixel coordinate system: An image is stored in a computer as pixels arranged in rows and columns. Therefore, the pixel coordinate system records the row and column numbers of each pixel. The origin of the coordinate system is in the upper left corner, and the unit is pixels. For example, the coordinates (u, v) of a pixel point represent column u and row v in the image array, respectively.

[0090] The pixel coordinate system and the image coordinate system are defined on a plane and can be transformed between them via translation. The transformation from the image coordinate system to the camera coordinate system is a perspective projection, from 2D to 3D. The transformation from the camera coordinate system to the world coordinate system is a rigid body transformation, meaning the object does not deform and only requires the transformation of a rotation matrix and a translation vector.

[0091] In the embodiments of this application, Figure 5 As shown, solving the inverse perspective transformation matrix based on the POS data corresponding to the oblique photographic image includes:

[0092] S2011: Convert the oblique photographic image from a pixel coordinate system to an image coordinate system to obtain a first translation vector.

[0093] S2012: 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.

[0094] 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 to obtain the rotation matrix and the translation vector for obtaining the inverse perspective transformation matrix.

[0095] Among them, after the above transformation, the conversion relationship between the world coordinate system and the pixel coordinate system is:

[0096]

[0097] Among them, R represents the rotation matrix of the inverse perspective transformation matrix, T represents the translation vector of the inverse perspective transformation matrix, u0 and v0 represent the coordinates of the principal point in the pixel coordinate system, dx and dy represent the length of a pixel, and f represents the principal distance of the film.

[0098] The rotation matrix of the inverse perspective transformation matrix is ​​expressed as:

[0099]

[0100] The translation vector of the inverse perspective transformation matrix is ​​expressed as:

[0101]

[0102] Wherein, ΔX, ΔY, and ΔZ represent the translation distances of the principal point in the X-axis, Y-axis, and Z-axis directions from the pixel coordinate system to the world coordinate system.

[0103] According to the inverse perspective transformation matrix, the collinear equation of the principal point and the four corner points of the oblique photographic film is constructed.

[0104]

[0105] According to the collinear equation, the geographic space coordinates of the image corners of the oblique photography film at different heights are calculated as follows:

[0106]

[0107]

[0108] Among them, a i 、b i 、c i (i=1,2,3) indicates the external 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 image principal point as the origin, X, Y, Z are the coordinates of the ground point corresponding to 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 dataset.

[0109] In an embodiment of the present application, based on the inverse transformation matrix, the collinearity equations of the image corner points of the oblique photographic film are inversely deduced according to the internal and external orientation elements of the oblique photographic film, and then the projection plane coordinates corresponding to the image corner points at different heights are solved, thereby determining the projection coverage range of the oblique photographic film at a given height.

[0110] In the embodiment of the present application, the range of the proposed modeling area is obtained, and the range includes the height of the proposed modeling area and the area formed by the ground plane corresponding to the proposed modeling area, including: Figure 6 As shown, the process of obtaining the range of the proposed modeling area includes the following steps:

[0111] S301: Acquire the height of the proposed modeling area and the coordinates of consecutive points on the ground plane corresponding to the proposed modeling area.

[0112] S302 : Characterize the range of the proposed modeling area according to the height of the proposed modeling area and the coordinates of consecutive points on the ground plane corresponding to the proposed modeling area.

[0113] The proposed modeling area 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 proposed modeling area, represented by H.

[0114] The plane close to the ground in the area to be modeled should be represented by a set of continuous points, characterized as follows:

[0115]

[0116] Among them, m represents the number of points that make up the modeling pre-fetch, X m 、Y m Indicates the position of a point in the plane close to the ground in the area to be modeled in the world coordinate system.

[0117] Furthermore, in the embodiments of the present application, Figure 7 As shown, the determination of the correlation between all the oblique photographs and the proposed modeling area includes the following steps:

[0118] S303 : Determine the geographic space coordinates of the image corner points of the oblique photography images at the height of the proposed modeling area according to the geographic space coordinates of the image corner points of the oblique photography images at different heights.

[0119] S304: Determine the projection coverage of all the oblique photographs according to the geographic space coordinates at the height of the area to be modeled.

[0120] S305 : Calculate a projection coverage rate based on the projection coverage range and the ground plane corresponding to the proposed modeling area, and use the projection coverage rate as a correlation degree between the oblique photography image and the proposed modeling area.

[0121] According to the height H determined by the area to be modeled, the height is substituted into the geographic space coordinate equation of the image corner points of the oblique photograph at different heights to obtain the coordinates of the ground plane points corresponding to the four image corner points of the oblique photograph. Then, the projection coverage of the oblique photograph on the ground plane is determined according to the coordinates of the ground plane points corresponding to the four image corner points. Figure 8 As shown, the actual ground plane points corresponding to the image corner points (a, b, c, d) are A', B', C', D', which do not completely coincide with the projection points A, B, C, D calculated based on the given height H.

[0122] In a preferred embodiment of the present application, the correlation between the oblique photographic image and the area to be modeled is determined by comparing the size of the overlapping range between the projection coverage and the ground plane corresponding to the area to be modeled. A larger overlapping range indicates a larger correlation, and a smaller overlapping range indicates a smaller correlation.

[0123] like Figure 9 As shown in FIG, the overlapping range between the projection coverage of the oblique photograph and the area to be modeled is divided into non-overlap, partial overlap and full coverage. In order to express the correlation more specifically, the projection coverage ratio is used as the correlation between the oblique photograph and the area to be modeled.

[0124] The calculation formula for projection coverage is:

[0125]

[0126] Among them, S0 represents the area of ​​overlap between the projection coverage of the oblique photographic film and the area to be modeled, S ABCD It represents the area covered by the projection of the oblique photographic film at height H.

[0127] Furthermore, in the embodiments of the present application, Figure 10 As shown, generating the image dataset of the simulated modeling area according to the correlation degree includes the following steps:

[0128] S306: Selecting oblique photographic images associated with the proposed modeling area according to the degree of association.

[0129] S307: Constructing a correlation degree data set of the oblique photography pictures according to the correlation degrees of the selected oblique photography pictures with correlation.

[0130] S308: Combining and encoding the selected initial image dataset and the correlation degree dataset of the associated oblique photographs to generate an image dataset of the proposed modeling area.

[0131] In the embodiment of the present application, oblique photographs associated with the area to be modeled are selected, and the initial image dataset and the degree of association of the selected oblique photographs are combined and encoded as the code of each oblique photograph, which is specifically expressed as follows:

[0132]

[0133] Where i represents the image number and j represents the flight batch number.

[0134] In a preferred embodiment of the present application, oblique photography pictures are sorted according to the degree of association to facilitate the retrieval and extraction of oblique photography pictures, thereby improving the efficiency of picture retrieval and extraction.

[0135] In summary, the oblique photographic images collected during the flight are managed in a standardized manner, and the names of the oblique photographic images are combined with the internal and external orientation elements to construct an initial image dataset. On the basis of the initial image dataset, for a specific intended modeling area, the projection coverage of the oblique photographic images within the height range of the intended modeling area is obtained according to the internal and external orientation elements of the image. The correlation between the oblique photographic images and the intended modeling area is determined according to the projection coverage ratio between the projection coverage and the intended modeling area. The oblique photographic images associated with the intended modeling area are selected according to the magnitude of the correlation. The selected oblique photographic images are encoded using an encoding method combining the initial image dataset and the correlation to generate an image dataset of the intended modeling area. The oblique photographic image rapid indexing method provided in the present application can quickly extract oblique photographic images associated with the intended modeling area without performing overall spatial solution on the images. For areas that require individual modeling, the corresponding images can be quickly read, thereby improving the speed of three-dimensional modeling.

[0136] Accordingly, if Figure 11 As shown, based on a method for rapid indexing of oblique photographic images, an embodiment of the present invention further provides a system for rapid indexing of oblique photographic images, the system comprising: a data acquisition unit 1, a calculation unit 2 and a simulated modeling area image association unit 3;

[0137] Data acquisition unit 1 is used to acquire oblique photography images and POS data corresponding to the oblique photography images to construct an initial image data set.

[0138] Calculation unit 2: used for calculating the geographic space coordinates of the image corner points of the oblique photography pictures at different heights according to the POS data corresponding to the oblique photography pictures.

[0139] The image association unit 3 of the proposed modeling area is used to obtain the scope of the proposed modeling area, and judge the correlation between all the oblique photographs and the proposed modeling area according to the scope of the proposed modeling area and the geographic spatial coordinates of the image corner points of all the oblique photographs at different heights, and generate the proposed modeling area image dataset based on the initial image dataset and the correlation.

[0140] For the specific definition of a system for rapid indexing of oblique photographic images, please refer to the above-mentioned definition of a method for rapid indexing of oblique photographic images, which will not be repeated here. A person 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. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0141] like Figure 12 As shown, an embodiment of the present invention provides a computer device, including a memory, a processor and a transceiver, which are connected via a bus; the memory is used to store a set of computer program instructions and data, and transmit the stored data to the processor, and the processor executes the program instructions stored in the memory to perform the steps of the above-mentioned oblique photography film rapid indexing method.

[0142] 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 device, or a combination thereof. By way of example and not limitation, the programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0143] Additionally, the memory may be a physically separate unit or integrated with the processor.

[0144] It can be understood by those skilled in the art that Figure 12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have the same component arrangement.

[0145] In one embodiment, a computer-readable storage medium is provided, wherein the storage medium is used to store one or more computer programs, wherein the one or more computer programs include program codes, and when the computer programs are run on a computer, the program codes are used to execute the above-mentioned steps of rapid indexing of oblique photography images.

[0146] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented 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 process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line, or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., an SSD).

[0147] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0148] The present embodiment provides a method, system, computer equipment and storage medium for quickly indexing oblique photographs, which addresses the technical problem that a large number of oblique photographs cannot be managed and indexed in the existing three-dimensional modeling process. The oblique photographs collected during the flight are managed in a standardized manner, and the names of the oblique photographs are constructed together with the internal and external orientation elements to construct an initial image data set. On the basis of the initial image data set, for a specific intended modeling area, the projection coverage range of the oblique photographs within the height range of the intended modeling area is obtained according to the internal and external orientation elements of the image. The correlation between the oblique photographs and the intended modeling area is determined according to the projection coverage ratio between the projection coverage range and the intended modeling area. The oblique photographs associated with the intended modeling area are selected according to the magnitude of the correlation. The selected oblique photographs are encoded using an encoding method combining the initial image data set and the correlation to generate an image data set of the intended modeling area. The method for quickly indexing oblique photographs provided in the present application does not require an overall spatial solution of the photographs, and can quickly extract oblique photographs associated with the intended modeling area. For areas that require individual modeling, the corresponding photographs can be quickly read, thereby improving the speed of three-dimensional modeling.

[0149] The above-described embodiments merely represent several preferred implementations of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent. It should be noted that a person skilled in the art could make several improvements and substitutions without departing from the technical principles of the present invention, and these improvements and substitutions should also be considered within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be based on the scope of protection of the claims.

Claims

1. A method for rapid indexing of oblique photographic images, characterized in that: The method comprises: Obtaining oblique photography images and POS data corresponding to the oblique photography images to construct an initial image data set; Calculating the geographic space coordinates of the image corner points of the oblique photography pictures at different heights according to the POS data corresponding to the oblique photography pictures; Obtaining a range of the proposed modeling area, and determining, based on the range of the proposed modeling area and the geographic spatial coordinates of the image corners of all the oblique photographs at different heights, a correlation between all the oblique photographs and the proposed modeling area, and generating an image dataset of the proposed modeling area based on the correlation, based on the initial image dataset; The obtaining of the range of the proposed modeling area includes: Obtaining the height of the proposed modeling area and the coordinates of consecutive points on the ground plane corresponding to the proposed modeling area; Characterizing the range of the proposed modeling area according to the height of the proposed modeling area and the coordinates of consecutive points on the ground plane corresponding to the proposed modeling area; The determining of the correlation between all the oblique photographs and the proposed modeling area includes: Determining the geographic space coordinates of the image corner points of the oblique photography pictures at the height of the proposed modeling area according to the geographic space coordinates of the image corner points of the oblique photography pictures at different heights; Determining the projection coverage of all the oblique photographs according to the geospatial coordinates of the height of the area to be modeled; Calculating a projection coverage ratio based on the projection coverage range and a ground plane corresponding to the area to be modeled, and using the projection coverage ratio as a correlation between the oblique photography image and the area to be modeled; Generating a pseudo-modeling area image dataset according to the correlation degree includes: Selecting oblique photographs associated with the area to be modeled according to the degree of association; Constructing a correlation degree data set of the oblique photography pictures according to the correlation degrees of the selected oblique photography pictures having correlation; The selected initial image dataset and the correlation degree dataset of the associated oblique photographs are combined and encoded to generate an image dataset of the proposed modeling area.

2. The method for quickly indexing oblique photographic images according to claim 1, wherein: The constructing of the initial image dataset includes: Determining whether the oblique photography image contains position data and posture data, and if so, constructing an oblique photography image pose data set based on the position data and posture data; If not, setting the posture data of the oblique photography film containing only the position data to zero, and constructing the oblique photography film posture data set according to the position data and the zeroed posture data; Constructing an oblique photography internal orientation element dataset according to the batches of the oblique photography images; The oblique photography image pose dataset and the oblique photography image internal orientation element dataset are combined and encoded to construct an initial image dataset.

3. The method for quickly indexing oblique photographic images according to claim 1, wherein: The step of calculating the geographic spatial coordinates of the image corner points of the oblique photographic images at different heights based on the POS data corresponding to the oblique photographic images comprises: Solving the inverse perspective transformation matrix according to the POS data corresponding to the oblique photographic image; Constructing the collinear equations of the principal point and the corner points of the oblique photographic image according to the inverse perspective transformation matrix; The geographic space coordinates of the image corner points of all the oblique photographic images at different heights are determined according to the collinear equations of the image principal points and the image corner points of all the oblique photographic images.

4. The method for rapid indexing of oblique photographic images according to claim 3, wherein: Solving the inverse perspective transformation matrix according to the POS data corresponding to the oblique photographic image includes: Converting the oblique photographic image from a pixel coordinate system to an image coordinate system to obtain a first translation vector; Based on the first translation vector, the oblique photographic image is converted from the image coordinate system to a camera coordinate system to 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 a camera coordinate system to a world coordinate system to obtain a rotation matrix and a translation vector for obtaining an inverse perspective transformation matrix.

5. A fast indexing system for oblique photography, characterized in that: The system comprises: a data acquisition unit, a calculation unit and a proposed modeling area image association unit; Data acquisition unit: used to acquire oblique photography images and POS data corresponding to the oblique photography images, and construct an initial image data set; A calculation unit is used to calculate the geographic space coordinates of the image corner points of the oblique photography pictures at different heights according to the POS data corresponding to the oblique photography pictures; The proposed modeling area image association unit is used to obtain the scope of the proposed modeling area, and determine the correlation between all the oblique photographs and the proposed modeling area based on the scope of the proposed modeling area and the geographic spatial coordinates of the image corner points of all the oblique photographs at different heights, and generate the proposed modeling area image dataset based on the correlation based on the initial image dataset; The obtaining of the range of the proposed modeling area includes: Obtaining the height of the proposed modeling area and the coordinates of consecutive points on the ground plane corresponding to the proposed modeling area; Characterizing the range of the proposed modeling area according to the height of the proposed modeling area and the coordinates of consecutive points on the ground plane corresponding to the proposed modeling area; The determining of the correlation between all the oblique photographs and the proposed modeling area includes: Determining the geographic space coordinates of the image corner points of the oblique photography pictures at the height of the proposed modeling area according to the geographic space coordinates of the image corner points of the oblique photography pictures at different heights; Determining the projection coverage of all the oblique photographs according to the geospatial coordinates of the height of the area to be modeled; Calculating a projection coverage ratio based on the projection coverage range and a ground plane corresponding to the area to be modeled, and using the projection coverage ratio as a correlation between the oblique photography image and the area to be modeled; Generating a pseudo-modeling area image dataset according to the correlation degree includes: Selecting oblique photographs associated with the area to be modeled according to the degree of association; Constructing a correlation degree data set of the oblique photography pictures according to the correlation degrees of the selected oblique photography pictures having correlation; The selected initial image dataset and the correlation degree dataset of the associated oblique photographs are combined and encoded to generate an image dataset of the proposed modeling area.

6. A computer device, characterized in that: The computer device includes a memory, a processor and a transceiver, which are connected via a bus; the memory is used to store a set of computer program instructions and data, and transmit the stored data to the processor, and the processor executes the program instructions stored in the memory to perform the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 4 is implemented.

Images