N. Chebrolu: Spatio-temporal registration of plant point clouds for phenotyping


Bio Information

Nived Chebrolu is a PhD candidate at Photogrammetry and Robotics Lab of the University of Bonn since 2015. He received his masters degree in Robotics from Ecole Centrale de Nantes (ECN), France and University of Genoa, Italy. His research focuses on techniques for long-term registration, localization and mapping for robots in agricultural fields. He has been involved in an EU-funded project the FLOURISH for developing an aerial-ground robotics system for precision agriculture.


Presentation Abstract

In this talk, I will describe our approach for spatio-temporal registration of plant point clouds captured over a period of time. Registering plants over time is challenging due to its anisotropic growth, changing topology, and non-rigid motion in between the time of the measurements.

We develop a novel approach that extracts a compact representation of the plant in the form of a skeleton that encodes both topology and semantic information, and then use this skeletal structure to determine correspondences over time and drive the registration process. This approach has the potential to automate the phenotyping process and form the backbone for applications aimed at tracking the traits of plants over time.


Video

Ask the Speaker

You can post your questions for the speaker of this talk here until Nov 8. Your questions are visible to all other registered participants of the conference and will be visible together with your username that consists of the beginning of your email address. Participants can “like” your question. Questions with more like are more likely to be discussed during the live Q&A session on November 10, 2020.