hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.20532/cit.2018.1003802

Body Part Extraction and Pose Estimation Method in Rowing Videos

Gábor Szűcs   ORCID icon orcid.org/0000-0002-5781-1088 ; Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary
Bence Tamás ; Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary

Puni tekst: engleski, pdf (699 KB) str. 29-43 preuzimanja: 300* citiraj
APA 6th Edition
Szűcs, G. i Tamás, B. (2018). Body Part Extraction and Pose Estimation Method in Rowing Videos. Journal of computing and information technology, 26 (1), 29-43. https://doi.org/10.20532/cit.2018.1003802
MLA 8th Edition
Szűcs, Gábor i Bence Tamás. "Body Part Extraction and Pose Estimation Method in Rowing Videos." Journal of computing and information technology, vol. 26, br. 1, 2018, str. 29-43. https://doi.org/10.20532/cit.2018.1003802. Citirano 05.03.2021.
Chicago 17th Edition
Szűcs, Gábor i Bence Tamás. "Body Part Extraction and Pose Estimation Method in Rowing Videos." Journal of computing and information technology 26, br. 1 (2018): 29-43. https://doi.org/10.20532/cit.2018.1003802
Harvard
Szűcs, G., i Tamás, B. (2018). 'Body Part Extraction and Pose Estimation Method in Rowing Videos', Journal of computing and information technology, 26(1), str. 29-43. https://doi.org/10.20532/cit.2018.1003802
Vancouver
Szűcs G, Tamás B. Body Part Extraction and Pose Estimation Method in Rowing Videos. Journal of computing and information technology [Internet]. 2018 [pristupljeno 05.03.2021.];26(1):29-43. https://doi.org/10.20532/cit.2018.1003802
IEEE
G. Szűcs i B. Tamás, "Body Part Extraction and Pose Estimation Method in Rowing Videos", Journal of computing and information technology, vol.26, br. 1, str. 29-43, 2018. [Online]. https://doi.org/10.20532/cit.2018.1003802

Sažetak
This paper describes an image processing approach capable for estimating the pose of athletes exercising on indoor rowing machines in video sequences. The proposed algorithm finds and tracks the hand, elbow, shoulder, ankle, knee, hip and head, and the line of the back also. Our contribution is twofold. The first is a new background subtraction method, which can reliable separate the silhouette of athletes under some assumptions related to the videos. Furthermore the paper introduces – as the second contribution – a skeleton fitting method to find the joints of the athletes based on the results of the background subtraction. This algorithm is based on anthropometric data and special movement patterns. The overall solution works on a real time setting in the test environment. Comparing the results it is presented that our method surpasses the most accurate state-of-the-art general pose estimation solution for indoor rowing specific videos based on two common used metrics as well.

Ključne riječi
rowing machine; background subtraction; pose estimation; image and video processing

Hrčak ID: 203981

URI
https://hrcak.srce.hr/203981

Posjeta: 453 *