High accurate and stable circuler object detection based on ellipse fitting

2016 Fiscal Year Final Research Report

• Project/Area Number: 26330192
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Perceptual information processing
• Research Institution: Toyohashi University of Technology
• Principal Investigator: sugaya yasuyuki 豊橋技術科学大学, 工学(系)研究科(研究院), 准教授 (00335580)
• Project Period (FY): 2014-04-01 – 2017-03-31
• Keywords: 楕円検出 / 楕円当てはめ

Outline of Final Research Achievements

In this research, we developed a technology that can stably detect circular objects in images. This technology effectively detects elliptic arcs from an input point sequence that includes non-elliptic arcs line a line segment.
We fit an ellipse to the input point sequence and divide it at the intersections of the fitted ellipse into several partial arcs. Then, we detect elliptic arcs from these partial arcs. By repeating these processes, we automatically elliptic arcs from the input point sequence. Using simulated data and real images, we confirmed the efficiency of our proposed method. By using this proposed technology, we also developed a mixed reality system for museums.

Free Research Field

コンピュータビジョン