Future of Information and Communication Conference (FICC) 2025
28-29 April 2025
Publication Links
IJACSA
Special Issues
Future of Information and Communication Conference (FICC)
Computing Conference
Intelligent Systems Conference (IntelliSys)
Future Technologies Conference (FTC)
International Journal of Advanced Computer Science and Applications(IJACSA), Volume 16 Issue 1, 2025.
Abstract: This paper presents a deep learning methodology for a marked object-following system that incorporates the YOLOv8 (You Only Look Once version 8) object identification model and an inversely proportional distance estimation algorithm. The primary aim of this study is to develop a marked object-following algorithm capable of autonomously tracking a designated marker while maintaining a suitable distance through advanced computer vision techniques. In this study, a marked object is defined as an object that is explicitly labeled, tagged, or physically marked for identification, typically using visible markers such as QR codes, stickers, or distinct added features. Central to the system’s functionality is the YOLOv8 model, which detects objects and generates bounding boxes around identified target classes in real-time. The proposed marked object-following algorithm utilizes the distance estimation method, which leverages fluctuations in the bounding box width to determine the relative distance between the observed user and the camera. A pathfinding algorithm was created using tabu search and a-star to avoid obstacle and generate a path to continue following the marker object. Furthermore, the system’s efficacy was assessed using critical performance metrics, including the F1-score and Precision-Recall. The YOLOv8 model attained an F1-score of 0.95 at a confidence threshold of 0.461 and a mean Average Precision (mAP) of 0.961 at an IoU threshold of 0.5 for all target classes. These results indicate a high level of accuracy in object detection and tracking. However, it is important to note that this algorithm has close door and controlled environments.
Ken Gorro, Elmo Ranolo, Lawrence Roble, Rue Nicole Santillan, Anthony Ilano, Joseph Pepito, Emma Sacan and Deofel Balijon, “Marked Object-Following System Using Deep Learning and Metaheuristics” International Journal of Advanced Computer Science and Applications(IJACSA), 16(1), 2025. http://dx.doi.org/10.14569/IJACSA.2025.0160110
@article{Gorro2025,
title = {Marked Object-Following System Using Deep Learning and Metaheuristics},
journal = {International Journal of Advanced Computer Science and Applications},
doi = {10.14569/IJACSA.2025.0160110},
url = {http://dx.doi.org/10.14569/IJACSA.2025.0160110},
year = {2025},
publisher = {The Science and Information Organization},
volume = {16},
number = {1},
author = {Ken Gorro and Elmo Ranolo and Lawrence Roble and Rue Nicole Santillan and Anthony Ilano and Joseph Pepito and Emma Sacan and Deofel Balijon}
}
Copyright Statement: This is an open access article licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, even commercially as long as the original work is properly cited.