BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.geoinfo-lab.org//foss4g-asia-2024//YEA9BU
BEGIN:VTIMEZONE
TZID:+07
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:+07
TZOFFSETFROM:+0700
TZOFFSETTO:+0700
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-foss4g-asia-2024-KQBSJ9@talks.geoinfo-lab.org
DTSTART;TZID=+07:20241216T153000
DTEND;TZID=+07:20241216T154500
DESCRIPTION:Automating land use surveys in rural areas using advanced AI te
 chniques can significantly enhance the efficiency and accuracy of identify
 ing various land features. This project focuses on utilizing the YOLOv8 fr
 amework for land use detection through image segmentation and object detec
 tion.\nTraditional land use surveys in rural areas are time-consuming and 
 often prone to inaccuracies due to manual methods. Leveraging artificial i
 ntelligence\, particularly deep learning models\, presents a promising sol
 ution to streamline this process and improve data reliability. The project
  addresses the challenge of automating land feature identification\, which
  includes detecting houses\, rivers\, roads\, and vegetation from visual d
 ata captured by satellite/drone. Accurate identification of these features
  is crucial for effective rural planning and development\, as it helps in 
 resource allocation and infrastructure development. The limitations of con
 ventional methods\, such as the need for extensive human labor and suscept
 ibility to human error\, further highlight the necessity for innovative so
 lutions like AI-driven land use surveys.\nThe primary aim of this study is
  to develop and train an AI model capable of accurately detecting and segm
 enting various land features in rural landscapes. By doing so\, the projec
 t seeks to demonstrate the applicability of AI in enhancing rural developm
 ent planning and management. The specific objectives include creating a re
 liable dataset of annotated aerial images\, optimizing a deep learning mod
 el for high accuracy\, and evaluating the model's performance across diffe
 rent types of land features. Ultimately\, the project aims to provide a sc
 alable and efficient tool that can assist policymakers\, researchers\, and
  rural development planners in making informed decisions.\nThe methodology
  involved several key steps to ensure the robustness and accuracy of the A
 I model. First\, a diverse dataset of aerial images was collected\, encomp
 assing various rural landscapes with distinct features such as houses\, ri
 vers\, roads\, and farms/vegetation. These images were meticulously annota
 ted using specialized tools to create ground truth data for training and v
 alidation. Data augmentation techniques\, including rotations\, flips\, an
 d color adjustments\, were employed to expand the dataset and improve the 
 model's generalization capabilities.\nThe YOLOv8 model was selected for it
 s state-of-the-art performance in object detection and segmentation tasks.
  YOLOv8's architecture is well-suited for real-time applications due to it
 s balance between accuracy and speed. The model was trained using the anno
 tated dataset\, with hyperparameters optimized to enhance its detection an
 d segmentation performance. Training was conducted on a high-performance c
 omputing setup\, leveraging GPU acceleration to expedite the process.\nThe
  results demonstrated the model's high precision in detecting and segmenti
 ng land features. The YOLOv8 model achieved notable accuracy metrics acros
 s various classes. The segmentation masks generated by the model closely m
 atched the ground truth annotations\, indicating its effectiveness in dist
 inguishing different land features.\nThe findings of this study underscore
  the potential of AI in transforming rural development practices. The succ
 essful application of the YOLOv8 model for land use detection highlights i
 ts capability to deliver precise and actionable insights. The practical im
 plications of this project are significant\, offering a scalable solution 
 for land survey automation\, which can greatly assist policymakers and rur
 al planners. The integration of such AI-driven methodologies can lead to m
 ore informed decision-making\, efficient resource allocation\, and ultimat
 ely\, the betterment of rural communities.\nThe study also highlights seve
 ral challenges and limitations encountered during the project. Data collec
 tion in rural areas can be logistically challenging\, often requiring coll
 aboration with local authorities and stakeholders. Ensuring the diversity 
 and quality of the dataset is crucial\, as biased or insufficient data can
  affect the model's performance. Additionally\, the model's accuracy is de
 pendent on the quality of annotations\, which requires meticulous effort a
 nd expertise.\nDespite these challenges\, the project demonstrates that AI
  can significantly enhance the accuracy and efficiency of land use surveys
 . The use of deep learning models like YOLOv8 can reduce the reliance on m
 anual methods\, providing a more reliable and scalable solution. However\,
  continuous efforts are needed to improve the dataset\, address potential 
 biases\, and refine the model to handle more complex scenarios.\nIn conclu
 sion\, this project not only advances the field of AI in rural development
  but also sets a precedent for future studies aiming to leverage AI for si
 milar applications. The integration of AI in land use surveys can revoluti
 onize the way rural areas are planned and developed\, leading to more sust
 ainable and efficient outcomes. The success of this project inspires furth
 er research and development in AI-driven solutions for rural development\,
  with the potential to make a lasting positive impact on rural communities
  worldwide.
DTSTAMP:20260511T145151Z
LOCATION:Auditorium Hall 2
SUMMARY:Land Use Detection Using Artificial Intelligence - Amritesh Hiras\,
  Anuj Sharad Mankumare\, Akshith Mynampati\, D ARUNA PRIYA
URL:https://talks.geoinfo-lab.org/foss4g-asia-2024/talk/KQBSJ9/
END:VEVENT
END:VCALENDAR