Observation and Tracking of Plant Health using Computer Vision

Information

• Publication Type: Bachelor Thesis
• Workgroup(s)/Project(s):
  • Modeling the World at Scale
• Date: February 2025
• Date (Start): 19. April 2024
• Date (End): 19. February 2025
• Matrikelnummer: 12022506
• Note: 1
• First Supervisor: Stefan Ohrhallinger
• Keywords: plants, health monitoring, computer vision

Abstract

- select neural network for classification of diseases, dryness of soil etc. with multispectral analysis, with open source, input should be image of plant bed (with several diverse plants), pipeline with segmentation (in same paper, or find segmentation paper) - optional: classify and segment plants - optional: growth analysis: blueten, wie schnell waechst die pflanze - search for data sets for training for generic plants (as many plants as possible), possibly combine several - evaluation with cheap IP RGB camera, and multispectral camera, e.g., RGB+IR or more - optional: evaluate soil dryness from images with dryness sensor research question: how well does such a system work with a commodity setup - for indoor and outdoor ablation studies for indoor (more controlled environment) and outdoor, as well as RGB or RGB+IR++

Additional Files and Images

Weblinks

No further information available.

BibTeX

@bachelorsthesis{steinheber-2024-oto,
  title =      "Observation and Tracking of Plant Health using Computer
               Vision",
  author =     "Stefan Steinheber",
  year =       "2025",
  abstract =   "- select neural network for classification of diseases,
               dryness of soil etc. with multispectral analysis, with open
               source, input should be image of plant bed (with several
               diverse plants), pipeline with segmentation (in same paper,
               or find segmentation paper) - optional: classify and segment
               plants - optional: growth analysis: blueten, wie schnell
               waechst die pflanze - search for data sets for training for
               generic plants (as many plants as possible), possibly
               combine several - evaluation with cheap IP RGB camera, and
               multispectral camera, e.g., RGB+IR or more - optional:
               evaluate soil dryness from images with dryness sensor  
               research question: how well does such a system work with a
               commodity setup - for indoor and outdoor ablation studies
               for indoor (more controlled environment) and outdoor, as
               well as RGB or RGB+IR++",
  month =      feb,
  note =       "1",
  address =    "Favoritenstrasse 9-11/E193-02, A-1040 Vienna, Austria",
  school =     "Research Unit of Computer Graphics, Institute of Visual
               Computing and Human-Centered Technology, Faculty of
               Informatics, TU Wien ",
  keywords =   "plants, health monitoring, computer vision",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2025/steinheber-2024-oto/",
}