Dr David Hall

Postdoctoral Research Fellow

General Information


    • Australian Centre for Robotic Vision (ACRV)

    • Queensland University of Technology

Fields of Expertise:

    • Robotic Vision

    • Machine Learning

    • Evaluation Measures

    • Clustering

    • Plant Recognition

Staff Profile: profile

Arxiv Profile: arxiv home

Githib Page: https://github.com/david2611

Contact: d20.hall@qut.edu.au

Hi, I am Dr David Hall, Postdoctoral Research Fellow at the Queensland University of Technology. This website outlines my current publications and general information about myself as a researcher. My research focuses are on making robotic vision systems applicable for real-world. My PhD focused on producing a weed classification system for agricultural robotics which can be applied rapidly to any field assuming plant species knowledge in advance. My current research with the ACRV robotic vision challenge project focuses on how we evaluate vision systems for robotics applications. Ensuring they are robust, probabilistic, and adaptable to changing environments and conditions. It is my hope that in future, robots will be smart enough to implement basic tasks in more open environments, with management and guidance from human operators.

Recent 1st Author Publications

This is a list of my recent published papers (not arxiv) where I was 1st author on the paper. For a complete list of all papers I have assisted in publishing please go to my "All Publications" page.

Title: Probabilstic Object Detection: Definition and Evaluation

Authors: David Hall, Feras Dayoub, John Skinner, Haoyang Zhang, Dimity Miller, Peter Corke, Gustavo Carneiro, Anelia Angelova, Niko Suenderhauf

Year: 2020

Published in: 2020 IEEE Winter Conference on Applications of Computer Vision

Manuscript Download Link: WACV2020-arxiv

Bibtex: prod2020.bib

Probability-based Detection Quality


Title: A rapidly deployable approach for automated visual weed classification without prior species knowledge

Authors: David Hall

Year: 2018

Published by: Queensland University of Technology

Link to Paper: thesis2018.pdf

Bibtex: thesis.bib

Title: A rapidly deployable classification system using visual data for the application of precision weed management.

Authors: David Hall, Feras Dayoub, Tristan Perez, Chris McCool

Year: 2018

Published in: Computers and Electronics in Agriculture, Vol. 148

Manuscript Download Link: COMPAG2018_manuscript.pdf

Official Paper Link:


Bibtex: compag2018.bib

Title: A Transplantable System for Weed Classification by Agricultural Robotics

Authors: David Hall, Feras Dayoub, Tristan Perez, Chris McCool

Year: 2017

Published in: 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems

Paper Link: IROS2017.pdf

Bibtex: iros2017.bib

Title: Towards Unsupervised Weed Scouting for Agricultural Robotics

Authors: David Hall, Feras Dayoub, Jason Kulk, Chris McCool

Year: 2017

Published in: IEEE International Conference on Robotics and Automation 2017

Paper Link: ICRA2017.pdf

Bibtex: icra2017.bib

Title: Evaluation of Features for Leaf Classification in Challenging Conditions

Authors: David Hall, Chris McCool, Feras Dayoub, Niko Sünderhauf, Ben Upcroft

Year: 2015

Published in: 2015 IEEE Winter Conference on Applications of Computer Vision

Paper Link: WACV2015.pdf

Bibtex: wacv2015.bib