Original image taken in lab

Translated image (i.e., this image is generated)

Real image of a plant taken in the field

• Camera and Resolution: GoPro Hero 7; 4000x3000 px
• Adjustable camera orientation and position
• Automatic labelling of images
• Imaging rate: appx. 1 image per 5 seconds
• Interior imaging volume: 115x84x71 cm³
• Publication: Beck et al. 2020
• Creator: TerraByte

Back

• Spectral sensitivity: 465-945 nm
• Spectral bands: RGB and NIR
• Imaging rate: 324 m²/hour
• Vendor: Phenospex
• Sample data

Back

• Spectral range: 400-1000 nm
• Spectral bands: 224 bands
• Spatial resolution: 1024x1 px
• Imaging rate: 327 FPS
• Vendor: Specim
• Sample data

Back

• Max ascent speed: 4m/s
• Max speed: 13m/s (46.8 km/h)
• Max flight time: 30 minutes
• 3-axis stabilized camera gimbal
• Camera: 12 MP, 4000x3000 px
• Video-Resolution: 2720x1530 px at 30 fps
• Vendor: DJI

Back

• Front- or rear-wheel drive
• Adjustable tracking width: 1.22-1.52 m.
• Maximum plant height below rover: 1.22 m.
• Motors: 650W, 7:1 gear ratio
• Solar panels: 300W
• Battery: Providing up to 2000W of continuous power at 24V
• Flexibility: 12V and 24V power delivery to attach sensors
• Creators: TerraByte, R-Tech, Northstar Robotis, Valley Prototyping Solutions

Back

• Walk-in growing chamber
• Temperature and humidity control
• Programmable full-spectrum LED lighting

Back

Convolutional neural networks generally perform better on data that is similar to the data they had been trained on. To ensure that the models we train at TerraByte perform under field-conditions we have different strategies at our disposal. A very common one is transfer learning: Here a trained model is retrained on data from the new environment, while carrying over already trained filters for low- to high-level features. Another way is to modify our data such that it appears similar to field-data, although the images had been taken in the greenhouse. For transfer learning we collect a large amount of (initially unlabeled) field data. For the second approach we use image segmentation and background removal to digitally "plant" our lab-data in field-like environments.

• Date: January 2020

Back

The multispectral 3D scanning project establishes a framework of generating labeled 3D imaging datasets of real plants and developing 3D convolutional neural networks to solve detection, classification and regression problems related to agriculture. The imaging scanner used in the project is the Phenospex PlantEye, which is a unique plant sensor that produces real-time multispectral 3D point models of plants and crops. The output of the scanner contains detailed information of more than 14 parameters related to the morphological and spectral specifications of plants such as plant height, 3D leaf area, leaf inclination, digital biomass and light penetration depth. PlantEye also allows the visualization of the 3D point models with different spectral indices like NDVI or PSRI, where each index enables the calculation of multiple measures related to the plant health, performance and photosynthesis. We create fully automated systems to conduct data preprocessing and analysis by developing 3D convolutional neural networks to learn, interpret and analyze 3D point models of plants in order to monitor plant growth and to improve plant health, quality and yield.

• Date: November 2020 - Today

Close Project

Insects see the world differently from humans. While our eyes have only three types of colour sensitive cells, butterflies for example have four types of colour receptors, allowing them to see more colours than we do. These insects have evolved this trait to better find food, mate, and to avoid predators. A device that has a similar superhuman ability is the hyperspectral camera. It scans the scene at hundreds of different wavelengths in the visible and infrared spectrum. In other words, a hyperspectral camera can distinguish hundreds of colours of light, way more than the three colours – red, green, and blue – our cell phone camera captures. Hyperspectral imaging of plants enables scientists to discover plant properties that are invisible to humans. At the University of Winnipeg, we use a hyperspectral camera to find new ways to visually characterise plants.

• Date: November 2020 - Today

The following video shows the reflectance of a plant under different wavelengths. The video is colorized such that the color of the each image corresponds roughly to each wavelength's color in the visible part of the spectrum. Note that wavelengths beyond 800 nm (Infrared) are normally not visible to the human eye. We still gave it a red hue in this video.

Close Project

A stochastic neural network (SNN) is a kind of artificial neural network that has probabilistic network weights and usually trained under the Bayesian framework. The SNN provides a set of probability distributions for the network weights instead of weight points comparing with the regular neural network. This allows SNN to reduce the risk of overfitting and overconfident for the network prediction. Although developing an efficient training algorithm is not easy, Bayesian statistics can provide a good solution to analyze and train the SNN. My research is to explore stochastic training algorithms for the SNN by using Bayesian methods and solve them with numerical methods such as the Markov Chain Monte Carlo method and the Sequential Monte Carlo method.

• Date: September 2020 - Today

Close Project

We investigate several methods of obtaining field data with different camera systems. From simply mounting several cameras on a tractor up to drones. We are developing a field rover with the goal of fully automating the collection of field data and starting first tests with it in the growing season of 2021. The imaging equipment ranges from normal RGB-cameras to multi- and hyperspectral cameras.

• Date: June 2019 - Today

Close Project

Drone Imaging

Team members become drone pilots

Three of our team members, Cara Godee, Manisha Ajmani and Michael Beck, received training in flying drones and to become officially certified drone pilots. Another step into more semi-autonomous field data collection.

• Date: August 2021

Back

Soapbox Science event celebrates women in STEM

Co-organised by Manisha Ajmani

The University of Winnipeg is proud to sponsor, taking place online Saturday, August 14. Through this event, women researchers will get an opportunity to share their research and experiences. Dr. Nisha Ajmani UWinnipeg Master of Science in Applied Computer Science student Maryam Bafandkar is one of eight leading female scientists sharing expertise in technology, science, medicine, and engineering. Her presentation, Artificial Intelligence in Agriculture, will provide insight into what Bafandkar has learned through her work with UWinnipeg’s cutting-edge which aims to transform food production in Manitoba and beyond. Through this project, she works closely with Dr. Manisha Ajmani, co-organizer for this year’s Soapbox Science event.

• Read more
• Date: August 2021

Back

New Data Rover

A semiautonomous field-imager

We are proud to present our new field rover! We work closely with the local industry partners R-Tech and Northstar Robotics to get this one in the fields to get close and personal with our plants.

• Date: June 2021

Back