Naslov
Object Detection Using Synthesized Data

Autori
Burić, Matija ; Paulin, Goran ; Ivašić-Kos, Marina

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
ICT Innovations 2019, Web Proceedings / Gievska, Sonja ; Madjarov, Gjorgji - Ohrid : Springer, 2019, 110-124

Skup
11th International Conference ICT Innovations

Mjesto i datum
Ohrid, Sjeverna Makedonija, 17.10.2019. - 19.10.2019

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Object Detection ; Convolutional Neural Network ; YOLO ; Synthesized Data ; Sports ; Handball

Sažetak
Successful object detection, using CNN, requires lots of well-annotated training data which is currently not available for action recognition in the handball domain. Augmenting real-world image dataset with synthesized images is not a novel approach, but the effectiveness of the creation of such a dataset and the quantities of generated images required to improve the detection can be. Starting with relatively small training dataset, by combining traditional 3D modeling with proceduralism and optimizing generator-annotator pipeline to keep rendering and annotating time under 3 FPS, we achieved 3x better detection results, using YOLO, while only tripling the training dataset.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti

POVEZANOST RADA