This Author published in this journals
All Journal TEKNIK INFORMATIKA
Yit Hong Choo
Deakin University, Pigdons Road, Waurn Ponds, Australia

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Small Object Detection and Object Counting for Primary Roe Dataset Based on Yolo Wahyu Andi Saputra; Nicolaus Euclides Wahyu Nugroho; Dany Candra Febrianto; Andi Prademon Yunus; Muhammad Azrino Gustalika; Yit Hong Choo
JURNAL TEKNIK INFORMATIKA Vol 18, No 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v18i1.46063

Abstract

This research offers an initial exploration into the effectiveness of three variations of the YOLOv8 model original, trimmed, and YOLOv8n.pt in combination with two distinct datasets characterized by tight and loose distributions of roe, aimed at enhancing small object detection and counting accuracy. Utilizing a primary roe dataset across 776 images, the research systematically compares these model-dataset configurations to identify the most effective combination for precise object detection. The experimental results reveal that the YOLOv8n.pt model combined with the loosely distributed dataset achieves the highest detection performance, with a mean Average Precision (mAP) of 53.86%. This outcome underscores the critical impact of both model selection and data distribution on the detection accuracy in machine learning applications. The findings highlight the importance of tailored model and dataset synergies in optimizing detection tasks, particularly in complex scenarios involving small, densely clustered objects. This research contributes valuable insights into the strategic deployment of neural network architectures for refined object detection challenges.