TY - GEN
T1 - Region-of-Interest Detection Based on Graph Convolutional Network and H.266/VVC Encoded Video
AU - Chen, Ivane Delos Santos
AU - Lien, Chih Ming
AU - Chen, Mei Juan
AU - Yeh, Chia Hung
AU - Lin, Yuan Hong
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - This paper proposes a novel region-of-interest (ROI) detection method that utilizes a graph convolutional network (GCN) and information from H.266/Versatile Video Coding (VVC) encoded video. The GCN-based model takes various features, including the geometric features, coding mode, motion information, and quantization parameter of the coding unit (CU), as input and produces an output that indicates whether the CU belongs to the ROI. By combining the GCN-based model with the encoded video, the proposed approach significantly reduces the computation time, with an average time saving of 60.88% compared to that of YOLOv7. This paper provides a fast ROI detection method and facilitates post-processing tasks such as the quality enhancement of ROIs for H.266/VVC video.
AB - This paper proposes a novel region-of-interest (ROI) detection method that utilizes a graph convolutional network (GCN) and information from H.266/Versatile Video Coding (VVC) encoded video. The GCN-based model takes various features, including the geometric features, coding mode, motion information, and quantization parameter of the coding unit (CU), as input and produces an output that indicates whether the CU belongs to the ROI. By combining the GCN-based model with the encoded video, the proposed approach significantly reduces the computation time, with an average time saving of 60.88% compared to that of YOLOv7. This paper provides a fast ROI detection method and facilitates post-processing tasks such as the quality enhancement of ROIs for H.266/VVC video.
KW - H.266/VVC
KW - graph convolutional network
KW - region-of-interest
UR - http://www.scopus.com/inward/record.url?scp=85174926782&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85174926782&partnerID=8YFLogxK
U2 - 10.1109/ICCE-Taiwan58799.2023.10226932
DO - 10.1109/ICCE-Taiwan58799.2023.10226932
M3 - Conference contribution
AN - SCOPUS:85174926782
T3 - 2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings
SP - 631
EP - 632
BT - 2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023
Y2 - 17 July 2023 through 19 July 2023
ER -