Method and device for UAV path determination for 3D model reconstruction

Abstract

The invention discloses a unmanned aerial vehicle (UAV) path determination method and apparatus for reconstructing a three-dimensional model, the method comprising the steps of: constructing a three-dimensional point model forming an outline of a captured building; determining a photographing points of a flight path of the UAV around the building so that a camera on the UAV can capture a corresponding point set covering the three-dimensional point model at each photographing point and the overlap ratio of the point sets captured by the camera at adjacent photographing points is greater than an overlap ratio threshold; instructing the UAV to fly along the flight path and instructing the camera to photograph the building at corresponding photographing points. The method can calculate minimum photographing point sets satisfying a three-dimensional reconstruction requirement just by acquiring the height and the two-dimensional orthograph of a three-dimensional reconstructed target, so as to provide guidance for a three-dimensional reconstruction data acquisition process, to ensure that the acquired images meet the three-dimensional reconstruction requirement, to avoid the collection of redundant image information, and to improve the efficiency of the three-dimensional reconstruction process.

Description

【Technical field】 [0001] The invention relates to a UAV path determination method and device for three-dimensional model reconstruction. 【Background technique】 [0002] Spatial information is an important basic data, and its collection and application run through the entire process of emergency management. Existing spatial information is mostly expressed in the form of two-dimensional maps, and many valuable terrain and feature details such as texture, height, and shape information are difficult to present. In the process of emergency management, the 3D real scene map can provide more intuitive and detailed spatial information, and provide better support for emergency decision-making. [0003] In order to obtain a high-precision 3D model of the building, it is necessary to fly around the building layer by layer to completely obtain the surface texture information of the building. The existing texture image acquisition process relies on manual control, and the UAV flight tr...

AI Technical Summary

Problems solved by technology

The existing texture image acquisition process relies on manual control, and the UAV flight trajectory and camera shooting interval are determined empirically

In order to ensure that the overlap rate of photos meets the requirements of 3D reconstruction, a large number of redundant images and photos are often taken by setting dense flight trajectories and small shooting intervals, causing 3D reconstruction software to spend a lot of time matching and processing redundant information , reducing the efficiency of 3D reconstruction

Images