CS-TRD: a Cross-Section Tree Ring Detection Method
Henry Marichal, Diego Passarella, Gregory Randall
⚠ This is a preprint. It may change before it is accepted for publication.

Abstract

This work describes a Tree Ring Detection method for complete Cross-Sections of Trees (CS-TRD) that detects, processes, and connects edges corresponding to the tree's growth rings. The method relies on edge detection, and its parameters are set to default values and can be adjusted as needed. The only required input is the location of the biological center of the tree, the pith, which can be marked manually or using an automatic detection algorithm. CS-TRD achieves an F-Score of 91% in the UruDendro dataset (of Pinus taeda) and 97% in the Kennel dataset (of Abies alba) without specialized hardware requirements.

Download

Supplementary Materials

Additional experiments: supplementary