Overview
Background
I'm a Postdoctoral Platform Fellow in Computer Vision and Machine Learning at the Australian Plant Phenomics Network (APPN), The University of Queensland, where I lead method development for computer vision, imaging, and 3D reconstruction pipelines at the UQ node. My research applies deep learning and 3D computer vision to plant phenotyping for developing practical tools for agricultural research.
My work spans:
- 3D reconstruction (Structure-from-Motion, Neural Radiance Fields, 3D Gaussian Splatting) for whole-plant and organ-scale analysis
- Deep learning for object detection, segmentation, and counting in crops and plants
- UAV-based imaging and multispectral, X-ray/CT, and digital microscopy data pipelines
- Open datasets and software pipelines supporting high-throughput plant phenotyping
I completed my PhD at UQ on 3D imaging and deep learning for plant phenotyping, building on a Master of Science in Data Science. My research is grounded in close collaboration with crop physiologists, agronomists, and computer scientists, connecting agricultural questions to applied AI methods.
I also contribute to platform support, training, and education within APPN, helping build AI capability across the agricultural research community while supervising research students in applied computer vision.
Availability
- Mr Chris James is:
- Available for supervision
Fields of research
Qualifications
- Bachelor of Information Technology, Guru Gobind Singh Indraprastha University
- Masters (Coursework) of Data Science, The University of Queensland
- Doctor of Philosophy of Computer Vision, The University of Queensland
Research impacts
My research focuses on reducing the manual burden involved in measuring crop and plant traits. Many of the measurements breeders and researchers rely on, canopy structure, biomass, grain and organ counts, are still collected by hand in the field, which is time-consuming, inconsistent, and difficult to scale across large trials. I develop UAV imaging and 3D reconstruction pipelines that automate much of this process, enabling faster, more frequent, and non-destructive assessment of these traits.
As an early-career researcher, I am keen to build collaborations, whether with research groups working on related imaging problems, industry partners facing a specific measurement challenge, or students looking to develop skills in applied computer vision. While plant phenotyping has been the focus of my work to date, my interest lies in applied computer vision more broadly, and I welcome the opportunity to discuss problems in this space, whether research-based or otherwise.
Works
Search Professor Chris James’s works on UQ eSpace
2026
Other Outputs
Sorghum diversity head counting dataset
Karannagoda, Rukshan, Baktashmotlagh, Mahsa, Chapman, Scott, Wang, Zijian, Guo, Kaiyu, Luo, Yadan, James, Chrisbin and Zheng, Bangyou (2026). Sorghum diversity head counting dataset. The University of Queensland. (Dataset) doi: 10.48610/45beb77
2025
Conference Publication
Evaluating neural kernel surface reconstruction for extracting mesh geometry from pointclouds for volumetric analysis of sorghum panicles
James, Chrisbin, Chapman, Scott C. and Chandra, Shekhar S. (2025). Evaluating neural kernel surface reconstruction for extracting mesh geometry from pointclouds for volumetric analysis of sorghum panicles. 2025 International Geoscience and Remote Sensing Symposium-IGARSS-Annual, Brisbane, QLD, Australia, 3-8 August 2025. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/igarss55030.2025.11242439
2025
Other Outputs
2024 Scott Teaching Trial
Gho Brito, Carla, Chapman, Scott, Smith, Daniel, Chen, Xiaolong, James, Chris, MUGAMBA, Edward, Oya, Riku and Cave, Lleyton (2025). 2024 Scott Teaching Trial. The University of Queensland. (Dataset) doi: 10.48610/808c370
2024
Journal Article
GrainPointNet: a deep-learning framework for non-invasive sorghum panicle grain count phenotyping
James, Chrisbin, Smith, Daniel, He, Weigao, Chandra, Shekhar S. and Chapman, Scott C. (2024). GrainPointNet: a deep-learning framework for non-invasive sorghum panicle grain count phenotyping. Computers and Electronics in Agriculture, 217 108485, 108485. doi: 10.1016/j.compag.2023.108485
2023
Journal Article
VegAnn, Vegetation Annotation of multi-crop RGB images acquired under diverse conditions for segmentation
Madec, Simon, Irfan, Kamran, Velumani, Kaaviya, Baret, Frederic, David, Etienne, Daubige, Gaetan, Samatan, Lucas Bernigaud, Serouart, Mario, Smith, Daniel, James, Chrisbin, Camacho, Fernando, Guo, Wei, De Solan, Benoit, Chapman, Scott C. and Weiss, Marie (2023). VegAnn, Vegetation Annotation of multi-crop RGB images acquired under diverse conditions for segmentation. Scientific Data, 10 (1) 302, 1-12. doi: 10.1038/s41597-023-02098-y
2023
Other Outputs
Sorghum Panicle Detection Ground-UAV Dataset
Chapman, Scott and James, Chris (2023). Sorghum Panicle Detection Ground-UAV Dataset. The University of Queensland. (Dataset) doi: 10.48610/9c3dd16
2023
Other Outputs
Wheat Head Detection Ground-UAV Dataset
Chapman, Scott and James, Chris (2023). Wheat Head Detection Ground-UAV Dataset. The University of Queensland. (Dataset) doi: 10.48610/f6a6b07
2023
Journal Article
From prototype to inference: a pipeline to apply deep learning in sorghum panicle detection
James, Chrisbin, Gu, Yanyang, Potgieter, Andries, David, Etienne, Madec, Simon, Guo, Wei, Baret, Frédéric, Eriksson, Anders and Chapman, Scott (2023). From prototype to inference: a pipeline to apply deep learning in sorghum panicle detection. Plant Phenomics, 5 0017, 1-16. doi: 10.34133/plantphenomics.0017
Supervision
Availability
- Mr Chris James is:
- Available for supervision
Looking for a supervisor? Read our advice on how to choose a supervisor.
Media
Enquiries
For media enquiries about Mr Chris James's areas of expertise, story ideas and help finding experts, contact our Media team: