Oblique image screening method and device, terminal and medium

Abstract

The application provides a tilt image screening method, device, terminal and computer storage medium, which are used for obtaining a tilt image matched with a target object in space. The tilt image screening method comprises the following steps: obtaining target object image data; detecting whether the collection angle corresponding to each target object image data meets a preset angle condition; when the collection angle meets the angle condition, the target object image data is taken as a first image; detecting whether the distance between the mark point of each first image and the mark point of the target object is less than a distance threshold value; if yes, the first image is taken as the spatial matching image of the target object. The application not only reduces the processing time and labor cost, but also improves the accuracy of the target object screening result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of oblique photography, and in particular to an oblique image screening method and device, a terminal and a computer storage medium. BACKGROUND

[0002] Oblique photogrammetry is to carry multiple sensors with different viewing angles on the same flight platform, and to collect images of target objects from vertical and oblique directions at the same time during flight. This not only improves data collection efficiency and effectively reduces data collection costs, but also overcomes the shortcomings of traditional photogrammetry technology which only obtains images from vertical angles. Through analysis of multi-view oblique images, more intuitive and real target object information can be obtained, and therefore, oblique photogrammetry is widely used in fields such as real estate integration, topographic mapping, and real scene three-dimensional modeling.

[0003] In order to ensure the image collection quality of target objects, in the process of unmanned aerial vehicle oblique photogrammetry, the collection overlap degree of the heading is usually set to about 75%, and the lateral overlap degree is usually set to about 70%, resulting in that the number of collected images is more than 5 times the number of images collected by traditional photogrammetry. At present, the best oblique image that matches the space of the target object is screened from a large number of oblique images mainly through image matching and manual screening, but more time and labor costs are often required in the processing process, which is difficult to meet the real-time demand, and thus affects subsequent image processing and analysis.

[0004] Therefore, how to quickly, efficiently and accurately screen out image data with high spatial registration degree from the collected oblique image data has become a technical problem to be solved in the field. SUMMARY

[0005] In view of the above-mentioned shortcomings of the prior art, the purpose of the present application is to provide an oblique image screening method, device, terminal and computer storage medium, which can solve the problems of low efficiency, high labor cost and easy screening errors of the existing target object space matching image screening method.

[0006] To achieve the above-mentioned purpose and other related purposes, the present application provides an oblique image screening method in the first aspect, which is used for obtaining an oblique image that matches the space of a target object. The oblique image screening method comprises: obtaining target object image data, which is each collected image data containing a target object; detecting whether the collection angle corresponding to each target object image data satisfies a preset angle condition; when the collection angle satisfies the angle condition, regarding the target object image data as a first image; detecting whether the distance between the identification point of each first image and the target object identification point is less than a distance threshold value, and if so, regarding the first image as the spatial matching image of the target object.

[0007] In an embodiment of the present application, the acquiring the target object image data comprises: acquiring a coverage range corresponding to each of the collected image data; performing spatial analysis on each of the coverage range and pre-constructed ground object distribution data to obtain ground object information in each of the coverage range; and setting the collected image data containing target object information in the ground object information as the target object image data.

[0008] In an embodiment of the present application, the detecting whether the distance between the identification point of each of the first image and the target object identification point satisfies the distance threshold value comprises: acquiring the distance between the center point of each of the first image and the center point of the target object based on the center point coordinates of each of the first image and the center point coordinates of the target object; and respectively detecting whether the distance between each of the first image and the target object is less than a preset distance threshold value.

[0009] In an embodiment of the present application, before the detecting whether the distance between the identification point of each of the first image and the target object identification point satisfies the distance threshold value, the method further comprises: acquiring spatial information of each of the collected image data based on the collection parameters corresponding to each of the collected image and existing elevation information.

[0010] In an embodiment of the present application, the acquiring spatial information of each of the collected image data based on the collection parameters corresponding to each of the collected image and existing elevation information comprises: calculating the spatial coordinates of each corner point in the collected image data by using image interior orientation elements, exterior orientation elements and existing DEM data; and acquiring the coverage range of each of the collected image data and the spatial coordinates corresponding to each pixel point in each of the collected image based on the spatial coordinates of each corner point.

[0011] In an embodiment of the present application, the calculating the spatial coordinates of each corner point in the collected image data by using image interior orientation elements, exterior orientation elements and DEM data comprises: acquiring an initial elevation value of the collected image data based on the existing DEM information; acquiring an initial spatial coordinate corresponding to the collected image based on the initial elevation value, the image interior orientation elements and the exterior orientation elements; acquiring a new elevation value based on the initial spatial coordinate and the existing DEM information; and acquiring a new spatial coordinate in the collected image data based on the new elevation value, the image interior orientation elements and the exterior orientation elements, so as to update the new elevation value based on the new spatial coordinate; and repeating the step until exiting.

[0012] In an embodiment of the present application, the tilt image screening method further comprises: acquiring the distance threshold value corresponding to each of the first image based on the spatial features of the minimum circumscribed circle of each of the first image.

[0013] In one embodiment of the present invention, the distance threshold corresponding to the first image is determined based on the spatial characteristics of the minimum circumscribed circle of each first image, including: obtaining the boundary polygons corresponding to each first image and constructing the minimum circumscribed circle of each boundary polygon; based on the spatial distance corresponding to the radius length of each minimum circumscribed circle, determining the corresponding distance threshold.

[0014] In one embodiment of the present invention, the distance threshold size corresponding to the first image is determined based on the spatial characteristics of the minimum circumscribed circle of each first image, including: obtaining the boundary polygon of the first image, and obtaining the major axis in the boundary polygon; constructing the inscribed triangle of the boundary polygon based on the vertex farthest from the major axis among the vertices of the boundary polygon and the major axis; constructing the circumscribed circle of the inscribed triangle; obtaining the maximum distance between each vertex of the boundary polygon and the center of the circumscribed circle; detecting whether the maximum distance is less than the radius of the circumscribed circle, if so, using the circumscribed circle as the minimum circumscribed circle of the boundary polygon; if not, updating the inscribed triangle based on the vertex corresponding to the maximum distance, so as to construct a new circumscribed circle based on the updated new inscribed triangle, and repeating this step.

[0015] The second aspect of the present invention provides an oblique image screening device for obtaining an oblique image that matches the space of a target object; the oblique image screening device includes: a target image data acquisition unit for obtaining each acquired image data containing the target object; an angle detection unit for detecting whether the acquisition angle corresponding to each target image data satisfies a preset angle condition; when the acquisition angle satisfies the angle condition, the target image data is used as the first image; a distance detection unit for detecting whether the distance between the identification point of each first image and the target identification point is less than a distance threshold, and if so, the first image is used as the spatial matching image of the target object.

[0016] In one embodiment of the present invention, the oblique image screening device further includes: a spatial information unit configured to obtain spatial information of each of the collected image data based on collection parameters and existing elevation information corresponding to each of the collected images.

[0017] In one embodiment of the present invention, the oblique image screening device further includes: a distance threshold acquisition unit, configured to acquire the distance threshold corresponding to the first image based on the spatial characteristics of the minimum circumscribed circle of each first image.

[0018] In a third aspect, the present invention provides a terminal comprising: a processor and a memory, wherein the memory is communicatively connected to the processor; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes any of the above-described oblique image screening methods.

[0019] In a fourth aspect, the present invention provides a computer storage medium storing a computer program, wherein the computer program, when executed by a processor, implements any of the above-described oblique image screening methods.

[0020] As described above, the oblique image screening method, device, terminal and computer storage medium provided by the present invention can quickly obtain oblique image data that matches the target object space by performing angle constraints on the target object image data at the acquisition angle, and performing distance constraints on the angle of the distance between the image and the target object for the oblique image data that meets the angle conditions. This not only reduces processing time and labor costs, but also improves the accuracy of the screening results, effectively improving the processing efficiency and screening quality of oblique image screening, thereby realizing the linked display of the target object and the oblique image. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 Shown is a schematic diagram of the tilt photography process in one embodiment of the present invention;

[0022] Figure 2 It is a schematic diagram showing the execution of oblique image acquisition of ground objects in a single oblique direction in the present invention;

[0023] Figure 3 Shown is a schematic flow chart of an embodiment of the oblique image screening method of the present invention;

[0024] Figure 4 Shown is a schematic flow chart of another embodiment of the oblique image screening method of the present invention;

[0025] Figure 5 Shown is a schematic diagram of a flow chart of calculating the spatial coordinates of four corner points in each captured image in one embodiment of the present invention.

[0026] Figure 6 Shown is a schematic flow chart of another embodiment of the oblique image screening method of the present invention;

[0027] Figure 7 Shown is a schematic diagram of the minimum circumscribed circle of the first image in one embodiment of the present invention;

[0028] Figure 8 A flow chart showing a method for obtaining a boundary polygon corresponding to a first image and a minimum circumscribed circle of the boundary polygon in one embodiment of the present invention is shown.

[0029] Figure 9 Fig. 1 shows a schematic diagram of a structure of the oblique image screening device according to an embodiment of the present application;

[0030] Figure 10 Fig. 2 shows a schematic diagram of a structure of the oblique image screening device according to another embodiment of the present application;

[0031] Figure 11 Fig. 3 shows a schematic diagram of a structure of the terminal according to an embodiment of the present application

[0032] Element number explanation

[0033] 600 oblique image screening device

[0034] 601 target object image data acquisition unit

[0035] 602 angle detection unit

[0036] 603 distance detection unit

[0037] 604 spatial information unit

[0038] 605 distance threshold value acquisition unit

[0039] 5 terminal

[0040] 51 memory

[0041] 52 processor DETAILED DESCRIPTION

[0042] The present application will be described in greater detail by way of specific embodiments, from which its advantages and effects will be apparent to those skilled in the art. The present application can be implemented or applied in other different embodiments, and the details in the present specification can be modified or changed based on different views and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0043] It should be noted that the drawings provided in the following embodiments only schematically illustrate the basic concept of the present application, and the drawings.

[0044] To solve the technical problems in the prior art, the present application provides an oblique image screening method in a first aspect, which is used for screening and acquiring oblique image data matched with a target object space from each collected image data.

[0045] The collected image data is each image data collected in an oblique photography process.

[0046] Referring to Figure 1 and Figure 2 , a schematic diagram of the oblique photography process in an embodiment is shown; as shown in Figure 1 , the oblique photography process is a process of simultaneously performing image acquisition in five directions, i.e., front view, rear view, left view, right view and downward view, by using a sensor during flight, so as to obtain image data in the five directions. In a single oblique direction, as shown in Figure 2 , the sensor is used to perform oblique image acquisition of a ground object based on a certain overhead angle, so as to obtain oblique image data of the ground object.

[0047] Referring to Figure 3 , a flowchart of the oblique image screening method provided by the present application in an embodiment is shown; as shown in Figure 3 , the method comprises:

[0048] S200, target object image data is obtained from each collected image data;

[0049] The target image data is oblique image data containing a target object in the image.

[0050] Specifically, the coverage range corresponding to each collected image data is obtained; the coverage range is the ground surface space range collected by a single collected image data.

[0051] The coverage range and pre-constructed ground object distribution data are subjected to spatial analysis, so as to obtain corresponding ground object information in each coverage range, i.e., a mapping relationship between each collected image data and the ground object information is constructed; the ground object distribution data is data used to represent the spatial distribution information of each ground object element.

[0052] Based on the mapping relationship, the collected image data containing target object information in the ground object information is set as target object image data.

[0053] Optionally, the ground object distribution data comprises a ground object element database, which at least comprises the spatial position of each ground object element and the element name.

[0054] In a specific embodiment, each ground object element in the ground object element database is stored according to a preset data structure model; for example, the data structure model is as follows:

[0055] Sequence Field Name Field Alias Field Type Length 1 GUID Element ID TEXT 50 2 FCODE Classification Code TEXT 15 3 X Center Point X Coordinate DOUBLE — 4 Y Center Point Y Coordinate DOUBLE —

[0056] In another specific embodiment, the target object image data is obtained from each collected image data, which comprises:

[0057] The image data of each target object is obtained by image interpretation of the collected images to obtain ground object information contained in the images, and by detecting whether the target object information is contained in the ground object information.

[0058] S400, detecting whether the collection angle corresponding to each target object image data satisfies a preset angle condition; when the collection angle satisfies the angle condition, the target object image data is taken as a first image.

[0059] In this embodiment, the collection angle includes the overhead angle during image collection, and the angle condition includes a preset angle range.

[0060] Specifically, based on the preset angle range, the overhead angle of each target object image data is detected, that is, whether the overhead angle corresponding to each target object image data is located in the preset angle range is detected; when it is detected that the overhead angle of the image is located in the preset angle range, the image is determined as a first image; otherwise, the step is exited.

[0061] Further, when step S200 is executed, the oblique image screening method further includes:

[0062] When it is detected that the collection angle corresponding to each target object image data does not satisfy the angle condition, the angle condition is adjusted to expand the corresponding preset angle range.

[0063] Optionally, when it is detected that the collection angle does not satisfy the angle condition, the preset angle range is adjusted according to an angle increment until a preset angle range threshold is reached; for example, the angle range is [45°, 50°], the angle increment is 5°, and the angle range threshold is [70°, 75°]; when it is detected that the collection angle does not satisfy the angle condition, the angle range is adjusted to [50°, 55°]; the step is continuously executed, when it is detected that the collection angle still does not satisfy the angle condition, the angle range is adjusted to [55°, 60°], and so on until the [70°, 75°] is reached and the step is exited.

[0064] S600, detecting whether the distance between the identification point of each first image and the corresponding target object identification point satisfies a preset distance threshold, and if so, taking the first image as a spatial matching image of the target object.

[0065] The identification point includes a center point.

[0066] Specifically, for each first image, based on the coordinates of the center point of the first image and the coordinates of the center point of the target, the distance between the center point of the first image and the center point of the target is obtained as follows:

[0067]

[0068] Among them, (X a , Y a ) is the coordinate of the center point of the target object, (Y a , Y b ) are the coordinates of the center point of the image.

[0069] Based on a preset distance threshold, the distance between each first image and the target object is detected respectively; when it is detected that the distance is less than the distance threshold, the first image is determined to be a spatially matching image of the target object; if not, the first image is determined to be a non-spatially matching image.

[0070] In order to improve the accuracy and efficiency of screening oblique images that match the spatial structure of the target object, the present invention also provides another method for screening oblique images.

[0071] See also Figure 4 , which is a flow chart of the tilted image screening method provided by the present invention in another embodiment; Figure 4 As shown, the tilt image screening method is Figure 3 The method shown is basically the same, except that, before executing S600, the tilted image screening method further includes:

[0072] S100, obtaining spatial information of each of the collected image data;

[0073] Based on the acquisition parameters corresponding to each acquired image and the existing elevation information, the spatial coordinates of each acquired image are obtained; wherein the photographic parameters corresponding to the acquired parameter image at the time of acquisition include image internal orientation elements and image external orientation elements;

[0074] The existing elevation information includes existing digital elevation model (DEM) data; optionally, 5-meter DEM data is used, that is, the grid spacing of the DEM data is 5 meters.

[0075] Specifically, the spatial coordinates of the four corner points in each collected image data are calculated using the image interior orientation elements, exterior orientation elements and DEM; based on the spatial coordinates of the four corner points, the coverage range of each collected image and the spatial coordinates corresponding to each pixel point in each collected image are obtained.

[0076] In a specific embodiment, the spatial coordinates of the four corner points in each collected image are calculated using the image internal orientation elements, external orientation elements and DEM, such asFigure 5 as shown, comprising:

[0077] S101, based on the existing DEM information corresponding to the collected image data, obtaining an initial elevation value of the collected image;

[0078] S102, based on the initial elevation value, the image interior orientation elements and exterior orientation elements, obtaining an initial spatial coordinate corresponding to the collected image;

[0079] for:

[0080]

[0081] wherein (x, y) is the image plane coordinate of the image point, (x0, y0, f) is the image interior orientation element (X a ,Y a ,Z a ) is the object space coordinate of the object point, (X s ,Y s ,Z s ) is the object space coordinate of the camera station, (a1, a2, a3, b1, b2, b3, c1, c2, c3) is the 9 direction cosine composed of the image exterior orientation angle element.

[0082] S103, based on the initial spatial coordinate and the existing DEM information, obtaining a new elevation value;

[0083] Specifically, the initial spatial coordinate is interpolated in the DEM to obtain a new elevation value Z1, which is calculated by the following formula:

[0084]

[0085] wherein (a 00 ,a 10 ,a 01 ,a 11 ) is the parameter to be solved, (X, Y) is the object plane coordinate of the to-be-determined point.

[0086] S104, based on the new elevation value, the image interior orientation elements and the exterior orientation elements, obtaining a new spatial coordinate corresponding to the collected image, updating the elevation value based on the new spatial coordinate, and repeating the step until exiting.

[0087] Specifically, the new elevation value Z1, the image interior orientation elements and the exterior orientation elements are substituted into formula 1 to calculate the new ground coordinates (X2, Y2); the new spatial coordinates (X2, Y2) are interpolated in the DEM to obtain the elevation value Z2, and based on the elevation value Z2, the image interior orientation elements and the exterior orientation elements, the new ground coordinates (X3, Y3) are obtained; the step is repeatedly executed until the total number of executions reaches the execution number threshold to exit, so that the spatial coordinates of the collected images can be obtained, thereby improving the accuracy of the spatial coordinates corresponding to the collected images.

[0088] It should be noted that in other embodiments, the step S100 is executed before any order of the step S600, and the execution order between the step S200 and the step S400 is not limited; that is, the step S100 can be executed after the step S200 or after the step S400.

[0089] In order to further improve the screening accuracy of the target space matching inclined image, the application further provides another inclined image screening method.

[0090] Please refer to Figure 6 , which shows the flowchart of the inclined image screening method provided by the application in another embodiment; as Figure 6 shown, the inclined image screening method is basically the same as Figure 3 the method, and the difference is that the inclined image screening method further comprises:

[0091] S500, determining the distance threshold size based on the spatial features of the minimum circumscribed circle of each first image.

[0092] The distance threshold size corresponds to the first image; the minimum circumscribed circle of the first image is the minimum circumscribed circle located outside the boundary of the first image; in a specific embodiment, the minimum circumscribed circle of the first image is as Figure 7 shown; wherein the oblique quadrilateral is the first image, and the circle outside the oblique quadrilateral is the minimum circumscribed circle of the first image.

[0093] Specifically, the boundary polygon corresponding to each first image is obtained, and the minimum circumscribed circle of each boundary polygon is constructed; based on the spatial distance corresponding to the radius length of each minimum circumscribed circle, the corresponding distance threshold is determined.

[0094] Optionally, the radius size of the minimum circumscribed circle is set as the distance threshold size.

[0095] Optionally, the step of obtaining the boundary polygon corresponding to the first image and constructing the minimum circumscribed circle of the boundary polygon comprises the following sub-steps when executed, as Figure 8 shown.

[0096] S501, obtaining a boundary polygon of the first image, and obtaining a long axis in the boundary polygon;

[0097] Specifically, connecting each boundary of the first image to obtain a polygon, and taking the polygon as the boundary polygon of the first image.

[0098] Extracting a line between two vertices farthest apart in the boundary polygon as the long axis of the boundary polygon.

[0099] S502, taking a vertex farthest from the long axis among all vertices of the boundary polygon as a selected vertex, and constructing an incircle triangle of the boundary polygon based on the selected vertex and the long axis.

[0100] Specifically, calculating the distance between each vertex and the long axis, selecting a vertex with the largest distance as the selected vertex according to the distance, and constructing a triangle based on the selected vertex and two end points of the long axis, and taking the triangle as the incircle triangle of the boundary polygon.

[0101] S503, constructing an excircle of the incircle triangle, obtaining a center distance between each vertex of the boundary polygon and the center of the excircle, and obtaining a maximum value in the center distances, and detecting whether the maximum value is less than the length of the radius of the excircle, if yes, taking the excircle as the minimum excircle of the boundary polygon, if no, taking a vertex corresponding to the maximum value as an updated vertex, updating the incircle triangle based on the updated vertex, constructing a new excircle based on the updated incircle triangle, and repeating the step.

[0102] Specifically, obtaining the distance between the updated vertex and each vertex of the incircle triangle, obtaining a maximum value in the distances, and replacing a vertex of the triangle corresponding to the maximum value with the updated vertex to construct a new incircle triangle, and continuing to execute step S503 based on the new incircle triangle until exiting to obtain the minimum excircle of the boundary polygon.

[0103] To solve the technical problems in the prior art, the application further provides an inclined image screening device for screening and obtaining inclined image data matched with a target object in space from image data.

[0104] It should be noted that the inclined image screening device is used to execute each step in the inclined image screening method described above, and only parts related to the embodiments of the application are shown for the convenience of description, and specific technical details not disclosed are referred to the embodiments of the inclined image screening method described in the application.

[0105] Referring toFigure 9 , is a schematic structural diagram of the oblique image screening device provided by the present invention in this embodiment; Figure 9 As shown, the tilted image screening device 600 includes: a target image data acquisition unit 601 , an angle detection unit 602 and a distance detection unit 603 .

[0106] The target image data 601 acquisition unit is used to acquire the collected image data containing the target object from each of the collected image data;

[0107] The angle detection unit 602 is used to detect whether the acquisition angle corresponding to each target image data satisfies a preset angle condition; when the acquisition angle satisfies the angle condition, the target image data is used as the first image;

[0108] Optionally, the angle detection unit further includes an angle condition adjustment module, configured to adjust the preset angle range according to an angle increment until a preset angle range threshold is reached when it is detected that the acquisition angle does not meet the angle condition;

[0109] Exemplarily, the angle range is [45°, 50°], the angle increment is 5°; the angle range threshold is [70°, 75°]; when it is detected that the acquisition angle does not meet the angle condition, the angle range is adjusted to [50°, 55°]; continue to execute this step, and when it is detected that the acquisition angle still does not meet the angle condition, the angle range is adjusted to [55°, 60°], and so on, until it reaches [70°, 75°] and then exits this step.

[0110] The distance detection unit 603 is used to detect whether the distance between the identification point of each first image and the identification point of the target object is less than a distance threshold. If so, the first image is used as the spatial matching image of the target object.

[0111] In another embodiment, the oblique image screening device is as follows Figure 10 As shown, the system further includes: a spatial information unit 604 and a distance threshold acquisition unit 605.

[0112] The spatial information unit 604 is used to obtain spatial information of each collected image data based on the collection parameters and existing elevation information corresponding to each collected image.

[0113] The distance threshold acquisition unit 605 is configured to acquire the distance threshold corresponding to the first image based on the spatial features of the minimum circumscribed circle of each first image.

[0114] To solve the technical problems in the prior art, the embodiment of the present application further provides a terminal, please refer to 10, which shows the structure schematic diagram of the terminal of the present application; as shown in the figure, the terminal 5 includes a memory 51 and a processor 52 connected with each other; the memory 51 is used for storing a computer program, and the processor 52 is used for executing the computer program stored in the memory, so that the terminal can implement the steps in the inclined image screening method when executed. Figure 11 As shown in the figure, the terminal 5 includes a memory 51 and a processor 52 connected with each other; the memory 51 is used for storing a computer program, and the processor 52 is used for executing the computer program stored in the memory, so that the terminal can implement the steps in the inclined image screening method when executed.

[0115] Optionally, the number of the memory can be one or more, and the number of the processor can be one or more, Figure 10 In the embodiment, one is taken as an example.

[0116] Optionally, the processor in the terminal loads one or more instructions corresponding to the application program process into the memory according to the steps in the inclined image screening method, and runs the application program stored in the memory by the processor, so as to realize the functions in the inclined image screening method, which will not be described here.

[0117] It should be noted that the memory includes but is not limited to random access memory (RAM), and can also include non-volatile memory, such as at least one disk memory. Similarly, the processor can also be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0118] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the program is called by the processor to implement the inclined image screening method.

[0119] The computer readable program instructions can also be loaded onto a computer, other programmable instruction execution device, or other device to cause a series of operations to be performed on the computer, other programmable instruction execution device, or other device to produce a computer implemented process, such that the instructions which execute on the computer or other programmable instruction execution device implement the functions / acts specified in the flowcharts and / or block diagram block or blocks.

[0120] The computer readable program instructions can also be loaded onto a computer, other programmable instruction execution device, or other device to cause a series of operations to be performed on the computer, other programmable instruction execution device, or other device to produce a computer implemented process, such that the instructions which execute on the computer or other programmable instruction execution device implement the functions / acts specified in the flowcharts and / or block diagram block or blocks.

[0121] To sum up, the tilt image screening method, device, terminal and computer storage medium provided by the present application, by acquiring target image data containing target objects, and performing angle constraint on each target object image data based on angle conditions, to obtain first image satisfying the angle conditions, and based on distance threshold, the distance between the first image and the target object is constrained, to screen out the tilt image matched with the target object in space, not only reduces the processing time and labor cost, but also improves the accuracy of the screening result. In addition, by accurately positioning the image data in space, and judging the distance between the accurate image data center point and the image circumscribed circle center and the length relationship of the image circumscribed circle radius according to the spatial information of the image outer circumscribed circle, the number of candidate images can be further reduced while improving the image screening efficiency, thereby greatly reducing the calculation complexity, further improving the accuracy of image screening, and improving the screening quality and effect.

[0122] The above embodiments only illustrate the principles and effects of the present application, and are not intended to limit the present application. Any person skilled in the art can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by those skilled in the art without departing from the spirit and technical idea of the present application should be covered by the claims of the present application.

Claims

1. A tilt image screening method, characterized by, The application relates to a method for screening a tilt image matched with a target object in space, and the method comprises the following steps: acquiring target object image data, that is, acquiring each acquisition image data containing a target object; detecting whether the acquisition angle corresponding to each target object image data meets a preset angle condition; when the acquisition angle meets the angle condition, the target object image data is regarded as a first image, wherein the acquisition angle includes a top view angle during image acquisition, and the angle condition includes a preset angle range, and the top view angle of each target object image data is detected based on the preset angle range; when it is detected that the acquisition angle does not meet the angle condition, the preset angle range is adjusted according to an angle increment until a preset angle range threshold is reached; detecting whether the distance between the identification point of each first image and the target object identification point is less than a distance threshold; if yes, the first image is regarded as a spatial matching image of the target object.

2. The oblique image screening method according to claim 1, wherein, The method for acquiring target object image data comprises the following steps: acquiring the coverage range corresponding to each acquisition image data; performing spatial analysis on each coverage range and pre-constructed ground object distribution data to obtain corresponding ground object information in each coverage range; setting the acquisition image data containing target object information in the ground object information as target object image data.

3. The method of claim 1, wherein the step of screening the oblique image is performed by using a neural network. The method for detecting whether the distance between the identification point of each first image and the target object identification point meets a distance threshold comprises the following steps: based on the center point coordinates of each first image and the center point coordinates of the target object, the distance between the center point of each first image and the center point of the target object is acquired; and the distance between each first image and the target object is detected respectively to determine whether the distance is less than a preset distance threshold.

4. The method of claim 1, wherein the step of screening the oblique image is performed by using a neural network. Before the step of detecting whether the distance between the identification point of each first image and the target object identification point is less than a distance threshold, the method further comprises the following steps: based on the acquisition parameters corresponding to each acquisition image and existing elevation information, the spatial information of each acquisition image data is acquired.

5. The method of claim 4, wherein the step of determining the tilt angle of the image is performed by using a tilt angle determination algorithm. The method for acquiring the spatial information of each acquisition image data based on the acquisition parameters corresponding to each acquisition image and existing elevation information comprises the following steps: using image interior orientation elements, exterior orientation elements and existing DEM data to calculate the spatial coordinates of each corner point in the acquisition image data; based on the spatial coordinates of each corner point, the coverage range of each acquisition image data and the spatial coordinates corresponding to each pixel point in each acquisition image are acquired.

6. The oblique image screening method according to claim 5, wherein, The method for calculating the spatial coordinates of each corner point in the acquisition image data using image interior orientation elements, exterior orientation elements and DEM data comprises the following steps: based on the existing DEM information, the initial elevation value of the acquisition image data is acquired; based on the initial elevation value, the image interior orientation elements and the exterior orientation elements, the initial spatial coordinates corresponding to the acquisition image are acquired; based on the initial spatial coordinates and the existing DEM information, a new elevation value is acquired; and based on the new elevation value, the image interior orientation elements and the exterior orientation elements, new spatial coordinates in the acquisition image data are acquired; based on the new spatial coordinates, the new elevation value is updated; the step is repeated until the step is exited.

7. The method of claim 1, wherein the step of screening the oblique image is performed by using a neural network. The method further comprises the following steps: The distance threshold size corresponding to each first image is determined based on a spatial feature of a minimum circumscribed circle of each first image.

8. The method of claim 7, wherein the step of determining the tilt angle of the image is performed by using a tilt angle determination algorithm. The distance threshold size corresponding to each first image is determined based on a spatial feature of a minimum circumscribed circle of each first image. A boundary polygon corresponding to each first image is obtained, and a minimum circumscribed circle of each boundary polygon is constructed; a corresponding distance threshold is determined based on a spatial distance corresponding to a radius length of each minimum circumscribed circle.

9. The oblique image screening method according to claim 8, wherein, The distance threshold size corresponding to each first image is determined based on a spatial feature of a minimum circumscribed circle of each first image. A boundary polygon of the first image is obtained, and a long axis in the boundary polygon is obtained; An incircle triangle of the boundary polygon is constructed based on a vertex farthest from the long axis among all vertices of the boundary polygon and the long axis; A circumscribed circle of the incircle triangle is constructed; a maximum distance between each vertex of the boundary polygon and a center of the circumscribed circle is obtained; whether the maximum distance is less than a radius length of the circumscribed circle is detected; if yes, the circumscribed circle is taken as the minimum circumscribed circle of the boundary polygon; if no, the incircle triangle is updated based on a vertex corresponding to the maximum distance, a new circumscribed circle is constructed based on the updated incircle triangle, and the step is repeatedly executed.

10. A tilt image screening apparatus, characterized by comprising: The oblique image screening device comprises: a target object image data acquisition unit configured to acquire each acquisition image data containing a target object; an angle detection unit configured to detect whether a collection angle corresponding to each target object image data satisfies a preset angle condition; when the collection angle satisfies the angle condition, the target object image data is taken as a first image, wherein the collection angle includes a viewing angle when the image is collected, and the angle condition includes a preset angle range, and the viewing angle of each target object image data is detected based on the preset angle range; when it is detected that the collection angle does not satisfy the angle condition, the preset angle range is adjusted by an angle increment until a preset angle range threshold is reached; a distance detection unit configured to detect whether a distance between a mark point of each first image and a target object mark point is less than a distance threshold; if yes, the first image is taken as a spatial matching image of the target object.

11. The inclined image screening apparatus according to claim 10, wherein Further comprising: a spatial information unit configured to obtain spatial information of each acquisition image data based on a collection parameter corresponding to each acquisition image and existing elevation information.

12. The inclined image screening apparatus according to claim 10, wherein Further comprising: a distance threshold acquisition unit configured to obtain the distance threshold size corresponding to each first image based on a spatial feature of a minimum circumscribed circle of each first image.

13. A terminal, characterized in that: comprising: a processor and a memory, the memory being in communication connection with the processor; the memory is configured to store a computer program, and the processor is configured to execute the computer program stored in the memory, so that the terminal executes the oblique image screening method according to any one of claims 1 to 9.

14. A computer storage medium storing a computer program, the computer program comprising instructions, which, when executed by a computer, cause the computer to perform the method according to any one of claims 1 to 13. The computer program is executed by the processor to realize the oblique image screening method according to any one of claims 1 to 9.

Images