Mapping underwater ship hulls using a model-assisted bundle adjustment framework

详细信息    查看全文

• 作者：Paul Ozog^a ; ^{paulozog@umich.edu}Author Vitae ; Matthew Johnson-Roberson^b ; ^{mattjr@umich.edu}Author Vitae ; Ryan M. Eustice^b ; ^{eustice@umich.edu}Author Vitae
• 关键词：SLAM ; AUVs ; Underwater inspection ; Mapping ; Visualization
• 刊名：Robotics and Autonomous Systems
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：87
• 期：Complete
• 页码：329-347
• 全文大小：7316 K
• 卷排序：87

文摘

We present model-assisted bundle adjustment and mapping frameworks, evaluated in the challenging domain of underwater ship hull inspection. To our knowledge, this is the largest example of a model-assisted bundle adjustment system using imagery collected from a field robot. Our mapping system merges camera-derived foreign structure (such as biological growth) into a nominal CAD model of the ship (given a priori).