Automated segmentation and annotation of 3D point clouds for plant phenotyping

Automated segmentation and annotation of 3D point clouds for plant phenotyping 

Supervisor: Prof. Grzegorz/Greg Cielniak 

What you will be doing 

The project aims to develop and deploy automated segmentation techniques for point cloud segmentation. The project targets the existing point cloud dataset, LAST-Straw (, which is a partially annotated set of 3D scans of strawberry plants at different growth stage used for phenotyping applications (see Fig. 1). The existing and limited annotations were done manually which required a significant manual effort. The project aims to address this challenge by deploying the state of the art techniques for point cloud/image segmentation that would speed up the annotation and segmentation process. The project provides a great opportunity to learn about the state of the art computer vision applications and techniques. 

Fig. 1 Data preview: Example time series of the same plant with original textures (row 1), class annotations (row 2), instance annotations (row 3), and temporally consistent leaf instance annotations (row 4). 

What skills would be useful to have for this project

The project requires some programming skills in Python or other popular languages such as C++/JavaScript. The knowledge of machine learning tools related to computer vision (e.g. pytorch) would be helpful but it is not required. 

How to get more information and apply 

The prospective candidates can apply by sending an email to Greg ( and providing a short background summary focusing on relevant interests and skills together with a CV. All candidates meeting the skills requirements will be accept and in case of multiple expressions of interest, the project scope will be negotiated with individual candidates. The application deadline is 25th of June and the candidates will be informed about the selection outcome by the 28th of June with an anticipated project start on the 1st of July (this is negotiable).