ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Machine-Attention-Based Video Coding for Machines
Cited 3 time in scopus Share share facebook twitter linkedin kakaostory
Authors
Yegi Lee, Shin Kim, Kyoungro Yoon, Hanshin Lim, Sangwoon Kwak, Hyon-Gon Choo
Issue Date
2023-10
Citation
International Conference on Image Processing (ICIP) 2023, pp.2700-2704
Publisher
IEEE
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.1109/ICIP49359.2023.10222037
Abstract
Conventional video coding methods have been developed based on the human visual system (HVS). However, in recent years, video has occupied a huge portion of internet traffic, and the mount of video data for machine consumption has increased rapidly due to the progress of neural networks. This paper proposes a novel machine-attention-based video coding method for machines. Inspired by the saliency-driven research, we first extract attention regions, sensitively affecting the machine vision performance, from the object detection network. Subsequently, a maximum a posterior (MAP)-based bit allocation method is applied to assign more bits to the attention regions. Our proposed method helps to maintain high machine vision performance whereas reducing the bitrate. Experimental results show that our proposed method achieves up to 34.89% bjøntegaard delta (BD)-rate reduction for the video dataset and up to 44.70% BD-rate reduction for the image dataset compared to state-of-the-art video coding technology.
KSP Keywords
Allocation method, Coding method, Human Visual System(HVS), Image datasets, Maximum a Posterior(MAP), Object detection, Video coding, Video dataset, bit allocation, internet traffic, machine vision