Shape-based time series analysis for remote phenology studies

• Grant number: 12/16285-1
• Support Opportunities: Scholarships abroad - Research
• Start date: December 04, 2012
• End date: March 03, 2013
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Ricardo da Silva Torres
• Grantee: Ricardo da Silva Torres
• Host Investigator: Salvatore-Antoine Tabbone
• Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Institution abroad: Université Nancy 2, France

Abstract

Plant phenology has gained importance in the context of global change research, stimulating the development of new technologies for phenological observation. Digital cameras have been successfully used as multi-channel imaging sensors, providing measures of leaf color change information (RGB channels), or leafing phenological changes in plants. We have been monitoring leaf-changing patterns of a cerrado-savanna vegetation by taken daily digital images. We extract RGB channels from digital images and correlated with phenological changes over time. A digital hemispherical lens camera was setup at the top of an 18 m high tower to automatically take a daily sequence of five JPEG images per hour, from 6:00 to 18:00h. Our study considers the analysis of over 2,700 images, recorded between August 28th and October 3rd, 2011. The image analysis was conducted by defining ten ROIs in the original digital image, including total or partial images, and six plant species. Time series associated with different regions in the images have been obtained, raising the need of using appropriate tools for mining patterns of interest. In this project, we aim to identify appropriate shape descriptors for characterizing time series. In our study, time series will be seen as open contours that will be characterized by traditional and recently proposed shape description algorithms. Our first goals are: i) to test, for each shape descriptor, if there is any statistical difference between time series from different hours of the day, ii) and to test if time series from different regions of interest (ROI) in the image differ from a combination of ROIs or the total image. Our study opens a new area of investigation related to the use of shape descriptors to identify and characterize phenology changes. (AU)