Napredna pretraga

Pregled bibliografske jedinice broj: 999075

Adapting YOLO Network for Ball and Player Detection


Burić, Matija; Pobar, Miran; Ivašić-Kos, Marina
Adapting YOLO Network for Ball and Player Detection // Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
Prag, Češka: SciTePress, 2019. str. 845-851 doi:10.5220/0007582008450851 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


Naslov
Adapting YOLO Network for Ball and Player Detection

Autori
Burić, Matija ; Pobar, Miran ; Ivašić-Kos, Marina

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

Izvornik
Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM / - Prag, Češka : SciTePress, 2019, 845-851

ISBN
978-989-758-351-3

Skup
8th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2019)

Mjesto i datum
Prag, Češka, 19.-21.02.2019

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Object Detector, Convolutional Neural Networks ; YOLO ; Sports ; Handball

Sažetak
In this paper, we consider the task of detecting the players and sports balls in real-world handball images, as a building block for action recognition. Detecting the ball is still a challenge because it is a very small object that takes only a few pixels in the image but carries a lot of information relevant to the interpretation of scenes. Balls can vary greatly regarding color and appearance due to various distances to the camera and motion blur. Occlusion is also present, especially as handball players carry the ball in their hands during the game and it is understood that the player with the ball is a key player for the current action. Handball players are located at different distances from the camera, often occluded and have a posture that differs from ordinary activities for which most object detectors are commonly learned. We compare the performance of 6 models based on the YOLOv2 object detector, trained on an image dataset of publicly available sports images and images from custom handball recordings. The performance of a person and ball detection is measured on the whole dataset and the custom part regarding mean average precision metric.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti



POVEZANOST RADA


Projekt / tema
HRZZ-IP-2016-06-8345 - Automatsko raspoznavanje akcija i aktivnosti u multimedijalnom sadržaju iz domene sporta (Marina Ivašić-Kos, )

Ustanove
Sveučilište u Rijeci - Odjel za informatiku

Časopis indeksira:


  • Scopus


Citati