TerraByte
Better data for a better world
Tell Me More

Home

At TerraByte we conduct research revolving around machine learning applications in agriculture. Our three main pillars are generating labelled plant data, developing machine learning models, and constructing a plant image database.

Generating Labelled Plant Images

With the help of embedded systems we create labelled data for applications in which machine learning meets agriculture. Good ML-models needs good data. ALITA and EAGL-I have already generated hundreds of thousands of labelled plant images, ranging from vegetables, over weeds, to typical crops found in the Prairies such as Canola and Soybeans. We keep imaging and soon extend our data acquisition to hyperspectral and 3d-imaging.

Training Machine Learning Models

We use high performance GPU-servers to train deep neural networks on our image data. Tasks range from simple plant identification, classifying a plant as crop or weed, or even evaluating a plant's well-being. These machine learning models train on the data we produced ourselves to be the "brains" in future robotic agents taking care of fields one plant at a time.

TerraByte Public Plant Image Database

All our data is stored and is available for researchers and eventually to everyone online. We have developed a front-end client that allows everyone to browse and filter the provided data to get exactly what they need for their application's development. The client can be found here. This publicly available data will accelerate the research community and the agriculture industry towards the next revolution in how we grow our food.

Research

The following research projects are currently conducted at TerraByte.

EAGL-I
Our imaging robot
Multispectral 3D Scanning
Models for multispectral 3D point clouds
Hyperspectral Imaging
Getting plants' spectra from IR to UV
Photogrammetry
Low cost 3D reconstruction for phenotyping
Field Data Collection
Automated data collection with our custom rover
Generative Models
Artificially created plant data
Convolutional Neural Networks
Architectures and topologies
From the Lab to Fields
Generalizing models to real world applications

Our Partners

TerraByte is proud to have collaborations and partnerships with the following organisations. We gratefully acknowledge the funding and financial support of Weston Seeding Food Innovation, Mitacs, Western Economic Diversification, NSERC, and University of Winnipeg. We thank Assiniboine Community College, Canola Council, DL Seeds, Haplotech, Manitoba Pulse and Soy Growers, Manitoba Crop Alliance, and University of Saskatchewan for providing us with seeds and seedlings.

Contact Us

For inquiries please contact one of TerraByte's principal investigators.