Unmanned aerial vehicle image processing system and method
First Claim
1. An unmanned aerial vehicle image processing system, comprising:
- a digital camera mounted on an unmanned aerial vehicle;
an autopilot controller installed in the unmanned aerial vehicle and pre-loaded with a fly file generated from a base image drawn thereon a target polygon, wherein the autopilot controller is configured to program a flight path as a series of mission lags to cover the target polygon on the base image in a lawnmower pattern for controlling the unmanned aerial vehicle to perform a flight mission by traveling along the flight path in which the autopilot controller records plural Global Positioning System/Inertial Navigation System (GPS/INS) data and triggers the digital camera plural times to take plural photos which are further calibrated based on calibration parameters of lens distortion of the digital camera to calculate the amount of distortion for each pixel of plural photos, so as to generate plural calibrated photos corresponding to the plural GPS/INS data, respectively; and
a computer device for receiving the plural calibrated photos and the plural GPS/INS data, processing the plural calibrated photos to generate plural projected photos by using the corresponding plural GPS/INS data, respectively, and stitching the plural projected photos to a mosaic image by a photo-stitching process,wherein the calibration parameters of lens distortion include principal point deviation, decentric lens distortion and radial lens distortion, and the amount of distortion for each pixel (x,y) of one photo is calculated based on the following equation;
1 Assignment
0 Petitions
Accused Products
Abstract
An unmanned aerial vehicle image processing system includes a digital camera mounted on an unmanned aerial vehicle, an autopilot controller installed in the unmanned aerial vehicle and pre-loaded with a base image, and a computer device. The autopilot controller programs a flight path as a series of mission lags to cover a target polygon on the base image in a lawnmower pattern for controlling the unmanned aerial vehicle to perform a flight mission in which the autopilot controller records plural GPS/INS data and triggers the digital camera to take plural photos which are further calibrated to generate plural calibrated photos corresponding to the plural GPS/INS data, respectively. The computer device processes the plural calibrated photos to generate plural projected photos by using the corresponding plural GPS/INS data, respectively, and stitches the plural projected photos to a mosaic image by a photo-stitching process.
-
Citations
11 Claims
-
1. An unmanned aerial vehicle image processing system, comprising:
-
a digital camera mounted on an unmanned aerial vehicle; an autopilot controller installed in the unmanned aerial vehicle and pre-loaded with a fly file generated from a base image drawn thereon a target polygon, wherein the autopilot controller is configured to program a flight path as a series of mission lags to cover the target polygon on the base image in a lawnmower pattern for controlling the unmanned aerial vehicle to perform a flight mission by traveling along the flight path in which the autopilot controller records plural Global Positioning System/Inertial Navigation System (GPS/INS) data and triggers the digital camera plural times to take plural photos which are further calibrated based on calibration parameters of lens distortion of the digital camera to calculate the amount of distortion for each pixel of plural photos, so as to generate plural calibrated photos corresponding to the plural GPS/INS data, respectively; and a computer device for receiving the plural calibrated photos and the plural GPS/INS data, processing the plural calibrated photos to generate plural projected photos by using the corresponding plural GPS/INS data, respectively, and stitching the plural projected photos to a mosaic image by a photo-stitching process, wherein the calibration parameters of lens distortion include principal point deviation, decentric lens distortion and radial lens distortion, and the amount of distortion for each pixel (x,y) of one photo is calculated based on the following equation; - View Dependent Claims (2, 3, 4, 5)
-
-
6. An image processing method for use in an unmanned aerial vehicle image processing system including a digital camera mounted on an unmanned aerial vehicle, an autopilot controller installed in the unmanned aerial vehicle, and a computer device, the method comprising the steps of:
-
(A) configuring the autopilot controller, which is pre-loaded with a fly file generated from a base image drawn thereon a target polygon, to program a flight path as a series of mission lags to cover the target polygon on the base image in a lawnmower pattern for controlling the unmanned aerial vehicle to perform a flight mission by traveling along the flight path in which the autopilot controller records plural Global Positioning System/Inertial Navigation System (GPS/INS) data and triggers the digital camera plural times to take plural photos which are further calibrated based on calibration parameters of lens distortion of the digital camera to calculate the amount of distortion for each pixel of plural photos, so as to generate plural calibrated photos corresponding to the plural GPS/INS data, respectively; (B) downloading the plural calibrated photos and the plural GPS/INS data into the computer device for processing the plural calibrated photos to generate plural projected photos by using the corresponding plural GPS/INS data, respectively; and (C) stitching the plural projected photos to a mosaic image by a photo-stitching process, wherein the calibration parameters of lens distortion include principal point deviation, decentric lens distortion and radial lens distortion, and the amount of distortion for each pixel (x,y) of one photo is calculated based on the following equation - View Dependent Claims (7, 8, 9, 10, 11)
-
Specification