Target Localization from a UAV Using 3D Terrain Engine | ||||
| The International Conference on Electrical Engineering | ||||
| Article 42, Volume 10, 10th International Conference on Electrical Engineering ICEENG 2016, April 2016, Page 1-16 PDF (651.21 K) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/iceeng.2016.30337 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
| Ali Abbas1; Assef Jafar2; Zouhair Dahrouj3 | ||||
| 1Corresponding Author is a PhD candidate at the Department of Electromechanic Systems, HIAST. | ||||
| 2Department of Electromechanic Systems, HIAST. | ||||
| 3Department of Informatics, HIAST Higher Institute for Applied Science and Technology, Damascus, P.O.box: 31983, Syria. | ||||
| Abstract | ||||
| We present a new approach for localizing a ground target from a UAV using 3D terrain engine. We use inaccurate auxiliary sensors on the UAV to obtain an approximate measurement of the camera pose, we use this pose to move the virtual camera inside the engine, and then automatically we find multiple matches between the two images to find the 3D coordinates of the matches using 3D terrain engine. Finally, we test the coplanarity of the 3D points under the camera, depending on this test, we use coplanar or non-coplanar algorithm to estimate accurate global camera pose. The accurate pose is used for localizing targets seen in the image by transmitting a virtual ray from a pixel according to the camera pose until intersect the 3D terrain model in the requested point. We tested the proposed approach on a synthetic and real data. Experimental results proved the feasibility and robustness of the proposed approach and the precision is the same order as the 3D terrain engine. | ||||
| Keywords | ||||
| Target localization; 3D terrain engine and Feature matching | ||||
|
Statistics Article View: 152 PDF Download: 307 |
||||
