Earticle

다운로드

Innovative 3D Model Reconstruction from 2D Stereoscopic Plant Images with Investigation between YOLOv8 and Detectron2 AI Architectures for Plant Class Segmentation

원문정보

초록

영어
This paper presents an innovative method for reconstructing 3D models from 2D stereoscopic images captured from the front, back, left, and right sides of an object at 90 - degree horizontal rotations. The proposed process involves several key steps: plant class segmentation using artificial intelligence (AI), disparity and depth mapping from stereo images, point cloud generation, merging multiple point clouds into a single unified point cloud, and mesh application to ensure surface continuity of the 3D model. Recognizing the critical role of accurate segmentation in 3D reconstruction, this study compares two AI segmentation architectures-YOLOv8 and Detectron2-to determine which performs better in terms of segmentation accuracy, training speed, and memory consumption for the plant class. This research focuses on the 3D reconstruction phase of a parent study titled "Investigating Deep Learning for Predicting and Simulating Plant Growth Structures: A Preparatory Effort Towards the Digital Twin Paradigm in Agriculture," whose dataset comprises 2D stereo images of plants that require 3D visualization. Its long-term vision is to develop a user experience that assists farmers in making informed decisions by leveraging predictive models and 3D visualizations of crop growth.

목차

Abstract
I. INTRODUCTION
A. Goals and Objectves
B. Scope and Limitations
II. METHODOLOGY
A. AI-Driven Segmentation for Plant Class: YOLOv8 versus Detectron2
B. 3D Model Reconstruction
III. CONCLUSION
REFERENCES

저자

  • John Ivan T. Diaz [ Department of Computer Engineering University of San Carlos Cebu City, Philippines ]
  • Craig Joseph B. Goc-ong [ Department of Computer Engineering University of San Carlos Cebu City, Philippines ]
  • Kaye Louise A. Manilong [ Department of Computer Engineering University of San Carlos Cebu City, Philippines ]
  • Alvin Joseph S. Macapagal [ Department of Computer Engineering University of San Carlos Cebu City, Philippines ]
  • Philip Virgil B. Astillo [ Department of Computer Engineering University of San Carlos Cebu City, Philippines ] Corresponding Author

참고문헌

자료제공 : 네이버학술정보

    간행물 정보

    • 간행물
      한국차세대컴퓨팅학회 학술대회
    • 간기
      반년간
    • 수록기간
      2021~2025
    • 십진분류
      KDC 566 DDC 004