TOWARDS RELIABLE PLANT PHENOTYPING WITH DEEP LEARNING AND REMOTE SENSING
Abstract
Quantitative measurement of plant components (e.g., leaves, inflorescences, flowers, and fruits) is of great interest in precision agriculture since it provides essential information for breeding research and guided agricultural management to enhance crop quality and productivity, as well as for yield estimation and adjusting marketing strategies.The conventional manual phenotyping is time and labor intensive, and often destructive, which remains as the major bottleneck to the advancement of precision and intelligent agriculture.Such restrictions encouraged the growth of high throughput plant phenotyping (HTPP), which is primarily based on sensing technologies and automated data retrieval and processing.These automatic approaches acquire significant amounts of data, primarily in the format of digital images, which need to be thoroughly processed.This is today possible due to the development of powerful image analysis technologies that can automatically identify objects in images using machine learning methods.Due to a range of environmental conditions, field phenotyping still faces significant challenges; therefore, the progress of HTPP capabilities for field conditions can be highly relevant to support digitalization of farm data and precision farming.This thesis introduces an automated image-based phenotyping system using advanced computer vision techniques (i.e., deep learning and multi-object tracking) and appropriate pre-and post-processing methods (i.e., image contrast enhancement, density map-based
Keywords
Not available
Specialisations
Similar theses
- Enhancing Plant Disease Detection in Smart Agriculture Using Deep Learning Models and Advanced Data Augmentation Techniques Nurbol Mukhametzhan · Nazarbayev University · 2026
- Deep Learning for Plant Disease Detection Using Image Analysis Muhammad Butt · University of Eastern Finland · 2026
- Transfer Learning-Based EfficientNetB0 Model for Multi-Crop Plant Disease Classification Mebrahtu Yohannes · 2026
- Plant Disease Detection and Classification Using Deep Learning Techniques Mazhar Iqbal · University of Eastern Finland · 2025
- An efficient deep learning approach to detect plant diseases using image data Ahmad Anis ; Babli Saha ; Maisa Tarannum Srizee · BRAC University · 2025
- Performance comparison of traditional machine learning and deep learning methods in plant disease detection Musa Çetinkaya · 2024
