Editor/Reviewer loginFrequency : 12 issues per year
Subject : Computer Applications and Technology
ISSN : 2319–8656 (Online)
IJCATR Volume 13 Issue 5
Processing of Image captured by Omnidirectional Camera for Object Detection
Panca Mudjirahardjo, Muhammad Aziz Muslim, Rahmadwati, Raden Arief Setyawan, Angger Abdul Razak
10.7753/IJCATR1305.1005
keywords : omnidirectional camera; YOLO; hemisphere view; panoramic view; object detection
In this paper, we introduce a method for processing of image captured by omnidirectional camera before object detection task in the image. The processing is necessary due to a limitation of image input for detection system. Here we use YOLO v.8 to detect objects in the image. So far we know YOLO successfully detect some objects in an image in panoramic view. However for hemisphere view, such as image captured by omnidirectional camera, YOLO fail to detect objects in it. Our experiment successfully convert hemisphere view into panoramic view, then YOLO successfully detect some objects in it.
@artical{p1352024ijcatr13051005,
Title = "Processing of Image captured by Omnidirectional Camera for Object Detection",
Journal ="International Journal of Computer Applications Technology and Research(IJCATR)",
Volume = "13",
Issue ="5",
Pages ="20 - 22",
Year = "2024",
Authors ="Panca Mudjirahardjo, Muhammad Aziz Muslim, Rahmadwati, Raden Arief Setyawan, Angger Abdul Razak"}
The paper proposes a conversion the hemisphere view into the panoramic view.
The paper proposes pixels correction at boundary of the resulted image.
The resulted image (the panoramic view) is an input for YOLO v.8.
YOLO successfully detected some objects in the resulted image.