Three-dimensional reconstruction of plant shoots from multiple images using an active vision system

Gibbs, Jonathon; Pound, Michael P.; Wells, Darren M.; Murchie, Erik H.; French, Andrew P.; Pridmore, Tony P.

Abstract

The reconstruction of 3D models of plant shoots is a challenging problem central to the emerging discipline of plant phenomics – the quantitative measurement of plant structure and function. Current approaches are, however, often limited by the use of static cameras. We propose an automated active phenotyping cell to reconstruct plant shoots from multiple images using a turntable capable of rotating 360 degrees and camera mounted robot arm. To overcome the problem of static camera positions we develop an algorithm capable of analysing the environment and determining viewpoints from which to capture initial images suitable for use by a structure from motion technique.

Citation

Gibbs, J., Pound, M. P., Wells, D. M., Murchie, E. H., French, A. P., & Pridmore, T. P. (2015). Three-dimensional reconstruction of plant shoots from multiple images using an active vision system

• Journal Article Type: Article
• Conference Name: Agri-Food Robotics Workshop
• Acceptance Date: Oct 1, 2015
• Publication Date: 2015
• Deposit Date: Aug 15, 2017
• Publicly Available Date: Aug 15, 2017
• Peer Reviewed: Peer Reviewed
• Public URL: https://nottingham-repository.worktribe.com/output/764685
• Publisher URL: http://library.wur.nl/WebQuery/wurpubs/508221
• Additional Information: Published in: Proceedings of the IEEE Workshop on Agri-Food Robotics. Hamburg, Germany. October 2, 2015. doi: 10.18174/392250
• Contract Date: Aug 15, 2017