Semantic Crop Segmentation Using Deep Leaning Technique

Mukhopadhyay, Venkatesh (2022) Semantic Crop Segmentation Using Deep Leaning Technique. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Hunger and Malnutrition are two of the major concerns that the whole world is currently dealing with. Hunger can be dealt effectively by understanding Agricultural growth and studying the food system, that may provide valuable insight before applying advanced agriculture analytics. Plenty of papers in this field, work with the land images but do not study the effects of irregular land shapes, cloud coverage as well as small crop segments, which in turn provides an outcome which is driven using fewer practical data. This study focuses on applying data mining methodologies as well as deep learning methods such as Modified UNet with MobileNet V2 encoder, to identify crop segmentation by using images taken from Sentinel 2 satellite. Dataset is subjected to image augmentation which creates a balance in classes and provides more scalable data to work with. All results are evaluated based on Accuracy, precision, and Cross entropy loss and are compared with previous studies for a better understanding on the subject. This study will help in identifying the core issues or improvement areas to advise a food system that is effective in increasing the crop yield along with creating fitting schemes and policies for farmers in need.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Crop Segmentation; Deep learning; Semantic image segmentation; Modified UNet; MobileNet V2 Encoder; Vegetation Indices; Transfer learning
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science S Agriculture > SB Plant culture H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Agriculture Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	23 Feb 2023 16:11
Last Modified:	02 Mar 2023 08:42
URI:	https://norma.ncirl.ie/id/eprint/6235

Actions (login required)

View Item