Target Geolocation from Airborne Video

by Kyng min Han

Motivation

The task of geolocating targets from airborne video is required for many applications in surveillance, law enforce-ment, reconnaissance, etc. The usual approaches to target geolo-cation involve terrain data, single target tracking, gimbal control of camera heads, altimeters, etc. The main goal of this research was to develop an accurate, robust, and efficient vision-based method for geolocation that can be carried out for multiple targets simultaneously and that can be deployed in small UAVs – that is, low payload. In that sense, the proposed improvements to the current state-of-the-art in geolocation is fourfold: 1) to eliminate the requirement for gimbal control of the cameras or any particular path planning control for the UAV; 2) to perform instaneous geolocation of multiple targets even when they are not previously observed by the camera; 3) to eliminate the requirements for geo-referenced terrain database or for an altimeter for estimating the UAV’s and target’s altitudes; and 4) to use one single camera while still maintaining good overall accuracy by employing a multi-stereo technique over the image sequence.

The result is a method that can reach approximately 25 meters of accuracy for an UAV flying at 155 meters away from the target. Such performance is demonstrated by computer simulation, in- scale data using a model city, and real airborne video with ground truth.

Results

References

1. Han, K. and DeSouza, G. N., " Two Phased Bayesian Filter Applied to Vision Based Geolocation of Moving Targets", Journal of Intelligent and Robotic Systems (submitted)
    

2. Han, K. and DeSouza, G. N., " Target Geolocation from Airborne Video without Terrain Data: A Comprehensive Framework", Journal of Intelligent and Robotic Systems (accepted).
    

3. Han, K., Dong Y. and DeSouza, G.N., " Tracking Moving Objects from Airborne Video Using Sparse SIFT Flows and Relaxation Labeling", in the Proceedings of the 2011 IEEE International Conference on Robotic System (IEEE-ICRA) (submitted).
    

4. Han, K. and DeSouza, G. N., "Multiple Target Geo-location using SIFT and Multi-Stereo Vision on Airborne Video Sequences", in Proceedings of the 2009 IEEE International Conference on Robotic System (IROS), pp. 5327-5332, Oct./09.
    

5. Han, K. and DeSouza, G. N., "Instantaneous Geo-Location of Multiple Targets From Monocular Airborne Video", 2009 IEEE International Geoscience & Remote Sensing Symposium (IGARSS), pp. IV 1003-6, July 2009, Cape Town, South Africa.