Camera pose estimation by using aerial images as an external reference

2016 Fiscal Year Final Research Report

• Project/Area Number: 26330193
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Perceptual information processing
• Research Institution: Nara Institute of Science and Technology
• Principal Investigator: Sato Tomokazu 奈良先端科学技術大学院大学, 情報科学研究科, 准教授 (50362835)
• Project Period (FY): 2014-04-01 – 2017-03-31
• Keywords: 動画像からの三次元復元 / Structure from motion / 空撮画像 / Bundle adjustment / コンピュータビジョン

Outline of Final Research Achievements

In this research, we propose a novel method for estimating camera poses from a video sequence using aerial images as an external reference. Conventionally, there was a problem of accumulative errors in camera pose estimation especially in the case that the target video is taken with long-distance movement. In order to solve this problem, we have used feature points on both video images taken in the ground and aerial images. With the experiments, we have confirmed that our method can successfully reduce the accumulation or errors and which can much increase the accuracy of the camera pose estimation.

Free Research Field

コンピュータビジョン、ジオメトリ