Computer Vision Techniques For Automated Segmentation of Different Wheat Plant Parts

Computer Vision Techniques For Automated Segmentation of Different Wheat Plant Parts 

Supervisor: Jaspreet Singh 

What you will be doing 

The project aims to develop the automated 2D/3D segmentation techniques for 2D images or point cloud. The project targets the recently collected 2D images and 3D wheat point cloud dataset, (see Fig. 1). The manual annotation of wheat parts e.g., stem, leaf, and spike, is highly time consuming and for large scale dataset is not possible. Thus, the project aims to address this challenge by deploying the state of the art deep learning based self-supervised, few-shot learning, and transfer learning techniques for point cloud/image segmentation that would speed up the segmentation process. The project provides a great opportunity to learn about the state of the art computer vision/image processing and machine/deep learning techniques. 

Fig. 1 Wheat plant and different parts of plant such as spike, stem, and leaf which are to be segmented using 2D/3D off-the-shelf segmentation techniques. 


What skills would be useful to have for this project 

The project requires some programming skills in Python or other popular languages such as Matlab/C++. The knowledge of machine learning tools related to computer vision (e.g. Keras, TensorFlow, 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 Jaspreet Singh ( 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).