|DUNCAN, KEITH - Danforth Plant Science Center
|TOPP, CHRISTOPHER - Danforth Plant Science Center
Submitted to: IEEE Winter Conference on Applications of Computer Vision
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 1/19/2018
Publication Date: 3/11/2018
Citation: Tabb, A., Duncan, K.E., Topp, C.N. 2018. Segmenting root systems in xray computed tomography images using level sets. IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION. https://doi.org/10.1109/WACV.2018.00070.
Interpretive Summary: To study the shape of roots, it is necessary to be able to view and quantify their shape efficiently. This work describes the use of xray computed tomography to image the root system of a growing plant, and algorithms described in the paper separate the root from non-root areas in the computed tomography image using a novel technique. The impact of this work is the potential to study root system architecture traits of plants growing in soil-like mediums through the use of this algorithm.
Technical Abstract: The segmentation of plant roots from soil and other growing mediums in xray computed tomography images is needed to effectively study the shapes of roots without excavation. However, segmentation is a challenging problem in this context because the root and non-root regions share similar features. In this paper, we describe a method based on level sets and specifically adapted for this segmentation problem. In particular, we deal with the issues of using a level sets approach on large image volumes and track active regions of the front using an occupancy grid. This method allows for straightforward modifications to a narrow-band algorithm such that excessive forward and backward movements of the front can be avoided and distance map computations in a narrow band context can be done in linear time through modification of Meijster et al.'s algorithm. Results are shown with three plant species of different maturity levels grown in three different growing mediums.