Methods for generating aerial photographing path for unmanned aerial vehicle, computer devices, and storage mediums

1. A method for generating an aerial photographing path for a UAV, the method comprising:

acquiring an inputted aerial photographing landmark;

obtaining a UAV aerial photographing safe space according to the aerial photographing landmark;

constructing a viewing angle quality scalar field of the aerial photographing landmark; and

generating an aerial photographing path set in the UAV aerial photographing safe space according to the viewing angle quality scalar field;

wherein the generating the aerial photographing path set in the UAV aerial photographing safe space according to the viewing angle quality scalar field comprises:

dividing the viewing angle quality scalar field into a plurality of spaces based on a cylindrical coordinate system; and

acquiring a key viewing angle of each respective space in the plurality of spaces, and performing curve fitting in the UAV aerial photographing safe space on the basis of the key viewing angle to generate the aerial photographing path set, wherein the key viewing angle is a viewing angle corresponding to a maximum value of viewing angle quality in the respective space.

2. The method according to claim 1 , wherein the respective space comprises a plurality of sub-spaces, the acquiring the key viewing angle of each respective space in the plurality of spaces comprises:

acquiring a viewing angle quality corresponding to each sub-space in the respective space, and regarding a viewing angle corresponding to a maximum viewing angle quality as a candidate viewing angle of the respective space; and

removing a viewing angle in the candidate viewing angle whose corresponding distance is less than a preset value, and obtaining a key viewing angle of the respective space.

3. The method according to claim 1 , wherein the generating the aerial photographing path set in the UAV aerial photographing safe space according to the viewing angle quality scalar field further comprises:

classifying aerial photographing paths in the aerial photographing path set according to a divided space, and obtaining an aerial photographing path subset in the UAV aerial photographing safe space;

acquiring a local path cost of each aerial photographing path in the aerial photographing path subset, and obtaining a candidate aerial photographing path corresponding to the aerial photographing path subset based on a local path cost minimum principle; and

generating a cost-based aerial photographing path set according to the candidate aerial photographing path corresponding to the aerial photographing path set.

4. The method according to claim 3 , wherein the acquiring the local path cost of each aerial photographing path in the aerial photographing path subset comprises:

acquiring an average viewing angle quality of the aerial photographing path, an angle between the aerial photographing path and an aerial photographing landmark dominant axis, and a change rate of the viewing angle of the aerial photographing path; and

obtaining the local path cost corresponding to the aerial photographing path according to the average viewing angle quality of the aerial photographing path, the angle between the aerial photographing path and the aerial photographing landmark dominant axis, and the change rate of the viewing angle of the aerial photographing path.

5. The method according to claim 1 , wherein the constructing the viewing angle quality scalar field of the aerial photographing landmark comprises:

acquiring a rendering image of the aerial photographing landmark;

constructing a weight map corresponding to an image pixel of the aerial photographing landmark; and

obtaining the viewing angle quality scalar field of the aerial photographing landmark according to the rendering image and the weight map.

6. The method according to claim 5 , wherein the acquiring the rendering image of the aerial photographing landmark comprises:

calculating a top surface salience and a side surface salience of the aerial photographing landmark respectively; and

obtaining the rendering image of the aerial photographing landmark according to the top surface salience and the side surface salience.

7. The method according to claim 1 , wherein the obtaining the UAV aerial photographing safe space according to the aerial photographing landmark comprises:

acquiring an image corresponding to the aerial photographing landmark and two-dimensional silhouettes of the aerial photographing landmark, the image comprising a plurality of image pixels;

calculating a distance between each pixel in the image and the two-dimensional silhouettes; and

acquiring a safe pixel in the image pixels, the safe pixel corresponding to a preset safe distance from the two-dimensional silhouettes, obtaining an equidistant line comprising the safe pixel and spaced from the two-dimensional silhouettes by the preset safe distance, and using the equidistant line as the two-dimensional silhouettes of an aerial photographing prohibited space; and obtaining a UAV aerial photographing safe space by using the equidistant line as the two-dimensional silhouettes of the aerial photographing prohibited space.

8. The method according to claim 1 , wherein when the inputted aerial photographing landmark is a plurality of aerial photographing landmarks, the generating the aerial photographing path set in the UAV aerial photographing safe space according to the viewing angle quality scalar field further comprises:

acquiring a path cost corresponding to a migration path; and

generating a UAV global aerial photographing path according to the aerial photographing path set and the path cost corresponding to the migration path.

9. The method according to claim 8 , wherein the acquiring the path cost corresponding to the migration path comprises:

acquiring the migration path;

acquiring an average viewing angle quality of the migration path, a change rate of the migration path viewing angle, and a steering angle of the migration path; and

obtaining the path cost corresponding to the migration path according to the average viewing angle quality of the migration path, the change rate of the migration path viewing angle, and the steering angle of the migration path.

10. The method according to claim 8 , wherein the generating the UAV global photographing path according to the aerial photographing path set and the path cost corresponding to the migration path comprises:

calculating a local path cost of each photographing path in the aerial photographing path set; and

constructing and solving a generalized travel salesman problem according to the path cost corresponding to the migration path and the local path cost, and obtaining the UAV global aerial photographing path.

11. A computer device, comprising a memory and a processor, the memory storing computer-readable instructions, the computer device configured so that, when the computer-readable instructions are executed by the processor, the computer-readable instructions cause the processor to perform the steps of:

acquiring an inputted aerial photographing landmark;

obtaining a UAV aerial photographing safe space according to the aerial photographing landmark;

constructing a viewing angle quality scalar field of the aerial photographing landmark; and

generating an aerial photographing path set in the UAV aerial photographing safe space according to the viewing angle quality scalar field;

wherein the device is configured so that, when the computer-readable instructions are executed by the processor, the computer-readable instructions further cause the processor to perform the steps of:

dividing the viewing angle quality scalar field into a plurality of spaces based on a cylindrical coordinate system; and

acquiring a key viewing angle of each respective space in the plurality of spaces, and performing curve fitting in the UAV aerial photographing safe space on the basis of the key viewing angle to generate the aerial photographing path set, wherein the key viewing angle is a viewing angle corresponding to a maximum value of viewing angle quality in the respective space.

12. The computer device according to claim 11 , wherein the device is configured so that, when the computer-readable instructions are executed by the processor, the computer-readable instructions further cause the processor to perform the steps of:

acquiring a viewing angle quality corresponding to each sub-space in the respective space, and regarding a viewing angle corresponding to a maximum viewing angle quality as a candidate viewing angle of the respective space; and

removing a viewing angle in the candidate viewing angle whose corresponding distance is less than a preset value, and obtaining a key viewing angle of the respective space.

13. The computer device according to claim 11 , wherein the device is configured so that, when the computer-readable instructions are executed by the processor, the computer-readable instructions further cause the processor to perform the steps of:

classifying aerial photographing paths in the aerial photographing path set according to a divided space, and obtaining an aerial photographing path subset in the UAV aerial photographing safe space;

acquiring a local path cost of each aerial photographing path in the aerial photographing path subset, and obtaining a candidate aerial photographing path corresponding to the aerial photographing path subset based on a local path cost minimum principle; and

generating a cost-based aerial photographing path set according to the candidate aerial photographing path corresponding to the aerial photographing path set.

14. One or more non-volatile storage mediums storing computer-readable instructions, the instructions configured so that, when executed by one or more processors, the computer-readable instructions cause the one or more processors to perform the steps of:

acquiring an inputted aerial photographing landmark;

obtaining a UAV aerial photographing safe space according to the aerial photographing landmark;

constructing a viewing angle quality scalar field of the aerial photographing landmark; and

generating an aerial photographing path set in the UAV aerial photographing safe space according to the viewing angle quality scalar field;

wherein the computer-readable instructions are configured so that, when the computer-readable instructions are executed by one or more processors, the computer-readable instructions cause the one or more processors to perform the steps of:

dividing the viewing angle quality scalar field into a plurality of spaces based on a cylindrical coordinate system; and

acquiring a key viewing angle of each respective space in the plurality of spaces, and performing curve fitting in the UAV aerial photographing safe space on the basis of the key viewing angle to generate the aerial photographing path set, wherein the key viewing angle is a viewing angle corresponding to a maximum value of viewing angle quality in the respective space.

15. The storage medium according to claim 14 , wherein the computer-readable instructions are configured so that, when the computer-readable instructions are executed by the one or more processors, the computer-readable instructions cause the one or more processors to perform the steps of:

acquiring a viewing angle quality corresponding to each sub-space in the respective space, and regarding a viewing angle corresponding to a maximum viewing angle quality as a candidate viewing angle of the respective space; and

removing a viewing angle in the candidate viewing angle whose corresponding distance is less than a preset value, and obtaining a key viewing angle of the respective space.

16. The storage medium according to claim 14 , wherein the computer-readable instructions are configured so that, when the computer-readable instructions are executed by the one or more processors, the computer-readable instructions cause the one or more processors to perform the steps of:

classifying aerial photographing paths in the aerial photographing path set according to a divided space, and obtaining an aerial photographing path subset in the UAV aerial photographing safe space;

acquiring a local path cost of each aerial photographing path in the aerial photographing path subset, and obtaining a candidate aerial photographing path corresponding to the aerial photographing path subset based on a local path cost minimum principle; and

generating a cost-based aerial photographing path set according to the candidate aerial photographing path corresponding to the aerial photographing path set.

17. The storage medium according to claim 16 , wherein the computer-readable instructions are configured so that, when the computer-readable instructions are executed by the one or more processors, the computer-readable instructions cause the one or more processors to perform the steps of:

acquiring an average viewing angle quality of the aerial photographing path, an angle between the aerial photographing path and an aerial photographing landmark dominant axis, and a change rate of the viewing angle of the aerial photographing path; and

obtaining the local path cost corresponding to the aerial photographing path according to the average viewing angle quality of the aerial photographing path, the angle between the aerial photographing path and the aerial photographing landmark dominant axis, and the change rate of the viewing angle of the aerial photographing path.