초록 ▼

A method, a computer program product, and a system are disclosed for stitching aerial data using information from at least one previous image. The method includes capturing a plurality of images of the landscape; obtaining, image metadata for each of the captured images; generating, for each of the

A method, a computer program product, and a system are disclosed for stitching aerial data using information from at least one previous image. The method includes capturing a plurality of images of the landscape; obtaining, image metadata for each of the captured images; generating, for each of the captured images, a set of transformed images based on the image metadata, comprises: setting a variable for each of the parameters; preparing a plurality of sets of transformed image metadata by applying the variables to the parameters; and preparing the set of transformed images from the captured image based on the plurality of sets of transformed image metadata, respectively; identifying, for each set of transformed images, one of the transformed images by calculating quality of fit to the top level image for each of the transformed images; and assembling a new aerial image based on the plurality of the identified transformed images.

대표청구항 ▼

1. A method of stitching aerial data using information from at least one previous image, the method comprising: providing a top level image of a landscape from the at least one previous image;capturing, by a camera installed on an aerial vehicle, a plurality of images of the landscape;obtaining, fro

1. A method of stitching aerial data using information from at least one previous image, the method comprising: providing a top level image of a landscape from the at least one previous image;capturing, by a camera installed on an aerial vehicle, a plurality of images of the landscape;obtaining, from sensors installed on the aerial vehicle, image metadata for each of the captured images, the image metadata including parameters relating to an altitude of the aerial vehicle, a latitude of the aerial vehicle, a longitude of the aerial vehicle, a pitch angle of the aerial vehicle, a roll angle of the aerial vehicle, and a yaw angle of the aerial vehicle; andgenerating, for each of the captured images, a set of 64 transformed images based on the image metadata, comprises: setting a variable for each of the parameters, the variable being a plus variable and a minus variable for each of the parameters;preparing a plurality of sets of transformed image metadata by applying the variables to the parameters; andpreparing the set of 64 transformed images from the captured image based on the plurality of sets of transformed image metadata, respectively;identifying, for each set of 64 transformed images, one of the transformed images by calculating quality of fit to the top level image for each of the transformed images; andassembling a new aerial image based on the plurality of the identified transformed images. 2. The method of claim 1, the identifying step comprising: selecting the transformed image with the quality of fit meeting a fit threshold, wherein if the quality of fit threshold is not met, resetting the variable for each of the parameters. 3. The method of claim 1, the identifying step comprising: using existing landmarks to fit the plurality of captured images to the top level image. 4. The method of claim 1, the identifying step comprising: detecting relative size differences in crop row distances or distance between plants or other objects with known separation or dimensions using aerial pitch and roll. 5. The method of claim 4, the identifying step comprising: removing images of irrigation or farm equipment that covers crop to be imaged using pixel replication or pixels from previously captured image in a same geographic location of an agricultural field. 6. The method of claim 5, the identifying step comprising: detecting irrigation or farm equipment covering crops during aerial imaging using known patterns or colors. 7. The method of claim 1, wherein the camera is a multispectral imaging camera, the aerial vehicle is an unmanned aerial vehicle, and flying the unmanned aerial vehicle at a height of 100±5 meters above ground level (AGL). 8. A computer program product comprising a non-transitory computer readable medium having a computer readable code embodied therein for stitching aerial data using information from at least one previous image, the computer readable program code configured to execute a process, which includes the steps of: providing a top level image of a landscape from the at least one previous image;capturing, by a camera installed on an aerial vehicle, a plurality of images of the landscape;obtaining, from sensors installed on the aerial vehicle, image metadata for each of the captured images, the image metadata including parameters relating to an altitude of the aerial vehicle, a latitude of the aerial vehicle, a longitude of the aerial vehicle, a pitch angle of the aerial vehicle, a roll angle of the aerial vehicle, and a yaw angle of the aerial vehicle;generating, for each of the captured images, a set of 64 transformed images based on the image metadata, comprises: setting a variable for each of the parameters, the variable being a plus variable and a minus variable for each of the parameters;preparing a plurality of sets of transformed image metadata by applying the variables to the parameters; andpreparing the set of 64 transformed images from the captured image based on the plurality of sets of transformed image metadata, respectively;identifying, for each set of 64 transformed images, one of the transformed images by calculating quality of fit to the top level image for each of the transformed images; andassembling a new aerial image based on the plurality of the identified transformed images. 9. The computer program product of claim 8, the identifying step comprising: selecting the transformed image with the quality of fit meeting a fit threshold, wherein if the quality of fit threshold is not met, resetting the variable for each of the parameters. 10. The computer program product of claim 8, the identifying step comprising: using existing landmarks to fit the plurality of captured images to the top level image. 11. The computer program product of claim 8, the identifying step comprising: detecting relative size differences in crop row distances or distance between plants or other objects with known separation or dimensions using aerial pitch and roll. 12. The computer program product of claim 8, the identifying step comprising: removing images of irrigation or farm equipment that covers crop to be imaged using pixel replication or pixels from previously captured image in a same geographic location of an agricultural field. 13. The computer program product of claim 8, the identifying step comprising: detecting irrigation or farm equipment covering crops during aerial imaging using known patterns or colors. 14. A system for stitching aerial data using information from at least one previous image, the system comprising: an aerial vehicle configured to: capture, a plurality of images of an area at a plurality of intervals with a multispectral imaging camera; andobtain, from sensors installed on the aerial vehicle, image metadata for each of the captured images, the image metadata including parameters relating to an altitude of the aerial vehicle, a latitude of the aerial vehicle, a longitude of the aerial vehicle, a pitch angle of the aerial vehicle, a roll angle of the aerial vehicle, and a yaw angle of the aerial vehicle; anda computer configured to: provide a top level image of a landscape from the at least one previous image;generate, for each of the captured images, a set of 64 transformed images based on the image metadata, comprises: setting a variable for each of the parameters, the variable being a plus variable and a minus variable for each of the parameters;preparing a plurality of sets of transformed image metadata by applying the variables to the parameters; andpreparing the set of 64 transformed images from the captured image based on the plurality of sets of transformed image metadata; andidentify, for each set of 64 transformed images, one of the transformed images by calculating quality of fit to the top level image for each of the transformed images; andassemble a new aerial image based on the plurality of the identified transformed images. 15. The system of claim 14, wherein the parameters are captured using one or more of the following: a GPS sensor;a pressure altimeter;pitch and roll sensors; anda magnetometer. 16. The system of claim 15, wherein the computer in the identifying step is configured to: select the transformed image with the quality of fit meeting a fit threshold, wherein if the quality of fit threshold is not met, reset the variable for each of the parameters. 17. The system of claim 15, wherein the computer in the identifying step is configured to: use existing landmarks to fit the plurality of captured images to the top level image. 18. The system of claim 15, wherein the computer in the identifying step is configured to: detect relative size differences in crop row distances or distance between plants or other objects with known separation or dimensions using aerial pitch and roll. 19. The system of claim 18, wherein the computer in the identifying step is configured to: remove images of irrigation or farm equipment that covers crop to be imaged using pixel replication or pixels from previously captured image in a same geographic location of an agricultural field. 20. The system of claim 19, wherein the computer in the identifying step is configured to: detect irrigation or farm equipment covering crops during aerial imaging using known patterns or colors.