Proceeding of the Faculty of technical Sciences, Novi Sad

Electrotechnical and Computer Engineering

Vol. 35 No. 01 (2020): Proceedings of the Faculty of Technical Sciences

SYSTEM FOR OBJECT LOCALIZATION IN ROBOTICS

  • Miloš Arbanas
DOI:
https://doi.org/10.24867/06BE42Arbanas
Submitted
December 30, 2019
Published
2019-12-30

Abstract

This paper analyzes the development of a system that is able to detect objects of interest, and also find their position. A few approaches and solutions were analyzed, from using simple color detection sensor, to somewhat complicated systems that include image manipulation and machine learning. The system was implemented and the results are  shown for different methods, from which the conclusions were drawn. At the very end, some potential improvements are explained that could increase the performance of the system.

References

[1] Richard Szeliski, „Computer Vision: Algorithms and Applications“, September 2010.
[2] Joseph Redmon , Santosh Divvala, Ross Girshick, Ali Farhadi, „You Only Look Once: Unified, Real-Time Object Detection“ University of Washington, 2016.
[3] https://medium.com/@jonathan_hui/map-mean-average-precision-for-object-detection-45c121a31173 (pristupljeno u septembru 2019.)