.jpg)
A METHOD FOR DETERMINING A HEIGHT OF AN OBJECT FROM A SINGLE IMAGE RECORDED BY AN IMAGING DEVICE COMPRISED BY AN AERIAL VEHICLE
WO2023285598
The invention relates to a method for determining a height of an object above an imaginary or a real horizontal plane from a single image recorded by an imaging device comprised by an aerial vehicle, wherein the imaging device is configured to record an image in an image space from an object space, the method comprising the steps of: - Flying with the aerial vehicle above the horizontal plane, Recording a single image with the imaging device, wherein the object is comprised by the image, - Acquiring imaging device parameters, wherein the imaging device parameters comprise information on an orientation of the imaging device in relation to a world coordinate system and a focal length as well as an information comprising the pixel pitch of the imaging device, - Determining an information on the elevation of the imaging device above at least one point of contact at which the object is in contact with the horizontal plane in the object space, - Relating the coordinates in the object space with the coordinates in the image space using the recorded image by means of the projection model, the imaging device parameters and the information on the elevation of the aerial vehicle. - Determining the height of the object or object's subparts above the horizontal plane in the object space by means of vertical section planes.
Novel method to estimate accurately the position and metrics (length, width, and height) of any target feature appearing in an aerial image. The method is also capable of retrieving the coordinates of the air vehicle when the image is acquired. Descriptive information, such as position and dimensions, can greatly support the reconnaissance and classification of target features. The method can operate in a GPS-denied environment and support navigation by providing the coordinates of air vehicles. The main features of the method are: - Visual-inertial based. No need for GPS or other GNSS information; - Extremely accurate (up to centimetric accuracy); - Moving targets can be considered (people, vehicles, vessels, animals, etc.); - Very fast since only two reference points are needed for camera resectioning; - Fully described mathematically (no black box). It has been extensively tested in real environments for validation and accuracy analysis. The results of the tests have been published in an international scientific journal (IEEE Sensors).