|This paper demonstrates the feasibility of recovering ﬁne-scale plant structure in 3D point clouds by leveraging recent advances in structure from motion and 3D point cloud segmentation techniques. The proposed pipeline is designed to be applicable to a broad variety of agricultural crops. A particular agricultural application is described, motivated by the need to estimate crop yield during the growing season. The structure of grapevines is classiﬁed into leaves, branches, and fruit using a combination of shape and color features, smoothed using a conditional random ﬁeld (CRF). Our experiments show a classiﬁcation accuracy (AUC) of 0.98 for grapes prior to ripening (while still green) and 0.96 for grapes during ripening (changing color), signiﬁcantly improving over the baseline performance achieved using established methods|
|Structure from Motion, robotics, agriculture, 3D reconstruction|
Sponsor: Intel Research, Pittsburgh
Note: This work was done by Debadeepta Dey while he was a Research Intern at Intel Research, Pittsburgh in the summer of 2010.
|Debadeepta Dey, Lily Mummert, and Rahul Sukthankar, "Classiﬁcation of Plant Structures from Uncalibrated Image Sequences," Workshop on Applications of Computer Vision, January, 2012.|
author = "Debadeepta Dey and Lily Mummert and Rahul Sukthankar",
editor = "Anderson Rocha",
title = "Classiﬁcation of Plant Structures from Uncalibrated Image Sequences",
booktitle = "Workshop on Applications of Computer Vision",
publisher = "IEEE",
month = "January",
year = "2012",
Notes = "This work was done by Debadeepta Dey while he was a Research Intern at Intel Research, Pittsburgh in the summer of 2010."
|The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University.|
Contact Us | Update Instructions