3D Detection and Quantification of Weeds in Vegetable Crops Using Drone Imaging and a Digital Twin

Innoptech is building VegForecast™, a digital twin platform for vegetable fields that combines rapid drone flyovers with computer vision and 3D reconstruction to deliver field-level insights as maps and KPIs that support scouting, intervention planning, and in-season decision making. This internship aims to deliver a complete AI module for weeds by training a detection and segmentation model on a proprietary dataset, then defining a reliable methodology to translate 2D predictions into field-level quantification integrated with the existing VegForecast™ 3D digital twin. The ultimate objective is to produce operationally useful indicators, such as weed pressure and its evolution over time, delivered as maps and KPIs by plot or zone.
This internship is designed to transform a detection capability into a directly marketable VegForecast™ feature by providing actionable, map-based quantification to prioritize interventions and measure their effectiveness. It will strengthen the value of the VegForecast™ digital twin by demonstrating vision plus 3D fusion, while standardizing a reusable pipeline that can be applied across fields and seasons. The results will enhance the value proposition for growers and support in-season commercialization.

Faculty Supervisor:

Davoud Torkamaneh

Student:

Partner:

Innoptech

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

Université Laval

Program:

Accelerate

Current openings

Find the perfect opportunity to put your academic skills and knowledge into practice!

Find Projects