Internship : Probabilistic plant detection
Inria
Montbonnot-Saint-Martin, 38330
Internship : Probabilistic plant detection
Le descriptif de l’offre ci-dessous est en Anglais
Type de contrat : Stage
Niveau de diplôme exigé : Bac + 3 ou équivalent
Fonction : Stagiaire de la recherche
A propos du centre ou de la direction fonctionnelle
The Centre Inria de l’Université de Grenoble groups together almost 600 people in 22 research teams and 7 research support departments.
Staff is present on three campuses in Grenoble, in close collaboration with other research and higher education institutions (Université Grenoble Alpes, CNRS, CEA, INRAE, …), but also with key economic players in the area.
The Centre Inria de l’Université Grenoble Alpe is active in the fields of high-performance computing, verification and embedded systems, modeling of the environment at multiple levels, and data science and artificial intelligence. The center is a top-level scientific institute with an extensive network of international collaborations in Europe and the rest of the world.
Contexte et atouts du poste
The agricultural industry is increasingly embracing digital technologies to enhance productivity, manage uncertainties, and adapt to evolving regulatory frameworks. One specific challenge faced by farmers is the need to reduce the use of biocidal products in their production methods. To address the issue of weeds, precision hoeing (mechanical weeding) presents a viable and easily implementable solution. This approach relies on simple equipment, the hoe, coupled to a tractor through a hydraulically shifted support controlled by a camera that detects crop rows.
Mission confiée
The objective of this internship is to develop a system for detecting crop rows during the advancement of the hoeing machine to generate commands for controlling the translation cylinder. In particular, we will develop a probabilistic approach to detect young plants by leveraging known a priori information, such as the distance between plants and rows. We will employ Bayes' theorem to refine estimates based on ongoing observations
Principales activités
To achieve this goal, you will: (1) familiarise yourself with the application domain, specifically inter-row mechanical weeding, (2) conduct a state-of-the-art review of possible approaches to this type of problem, (3) implement an algorithm for detecting young plants in both synthetic and real images.
If the results are positive, your algorithm may be tested on a farm located in Pontcharra.
Compétences
- Currently pursuing a M1 or M2 degree in computer science, electrical engineering, robotics, or a related field.
- Good programming skills in Python, C++ or similar
- Familiarity with computer vision concepts.
- Solid understanding of mathematics, especially linear algebra and statistics.
- Strong problem-solving skills and the ability to work both independently and in a collaborative team environment.
- Excellent communication and presentation skills.
Avantages
- Subsidized meals
- Partial reimbursement of public transport costs
- Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
- Professional equipment available (videoconferencing, loan of computer equipment, etc.)
- Social, cultural and sports events and activities
- Access to vocational training
- Social security coverage
Rémunération
Gratification = 4,05€ gross / hour