Monocular-Vision-Based Moving Target Geolocation Using Unmanned Aerial Vehicle

This paper develops a framework for geolocating a ground moving target with images taken from an unmanned aerial vehicle (UAV). Unlike the usual moving target geolocation approaches that rely heavily on a laser rangefinder, multiple UAVs, prior information of the target or motion assumptions, the proposed framework performs the geolocation of a moving target with monocular vision and does not have any of the above restrictions. The proposed framework transforms the problem of moving target geolocation to the problem of stationary target geolocation by matching corresponding points. In the process of corresponding point matching, we first propose a Siamese-network-based model as the base model to match corresponding points between the current frame and the past frame. Besides the introduction of a base model, we further designed an enhanced model with two outputs, where a row-ness loss and a column-ness loss are defined for achieving a better performance. For the precision of corresponding point matching, we propose a compensation value, which is calculated from the outputs of the enhanced model and improves the accuracy of corresponding point matching. To facilitate the research on corresponding point matching, we constructed a dataset containing various aerial images with corresponding point annotations. The proposed method is shown to be valid and practical via the experiments in simulated and real environments.

Automated summary

This paper presents a framework for geolocating a ground moving target using images from a UAV. In contrast to conventional methods that rely on laser rangefinders, multiple UAVs, prior information or motion assumptions, this framework utilizes monocular vision and has no such restrictions. By matching corresponding points, the problem of moving target geolocation is transformed into that of stationary target geolocation. Siamese-network-based models are proposed for matching corresponding points, with an enhanced model incorporating row-ness and column-ness losses for improved performance. A compensation value is introduced to improve the accuracy of corresponding point matching. A dataset with aerial images and corresponding point annotations is constructed for research purposes. Experimental results demonstrate the validity and practicality of the proposed method.