TY - GEN
T1 - A joint compression scheme for local binary feature descriptors and their corresponding bag-of-words representation
AU - Van Opdenbosch, Dominik
AU - Oelsch, Martin
AU - Garcea, Adrian
AU - Steinbach, Eckehard
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/2
Y1 - 2017/7/2
N2 - For real-time computer vision tasks, binary feature descriptors are an efficient alternative to their real-valued counterparts. While providing comparable results for many applications, the computational complexity of extracting and processing binary descriptors is significantly lower. In many application scenarios, the local features are transmitted over a channel with limited capacity and processed at a more powerful central processing unit, which requires efficient compression and transmission approaches. In this paper, we present a compression scheme for local binary features, which jointly encodes the descriptors and their respective Bag-of-Words representation using a shared vocabulary between client and server. By sending the visual word index and the entropy-coded residual vector containing the differences between the visual word and the descriptor, we are able to reduce ORB features to 60.62 % of their uncompressed size.
AB - For real-time computer vision tasks, binary feature descriptors are an efficient alternative to their real-valued counterparts. While providing comparable results for many applications, the computational complexity of extracting and processing binary descriptors is significantly lower. In many application scenarios, the local features are transmitted over a channel with limited capacity and processed at a more powerful central processing unit, which requires efficient compression and transmission approaches. In this paper, we present a compression scheme for local binary features, which jointly encodes the descriptors and their respective Bag-of-Words representation using a shared vocabulary between client and server. By sending the visual word index and the entropy-coded residual vector containing the differences between the visual word and the descriptor, we are able to reduce ORB features to 60.62 % of their uncompressed size.
KW - ATC
KW - Bag-of-Words
KW - ORB
KW - Visual features
KW - binary descriptors
KW - feature coding
UR - https://www.scopus.com/pages/publications/85050591315
U2 - 10.1109/VCIP.2017.8305155
DO - 10.1109/VCIP.2017.8305155
M3 - Conference contribution
AN - SCOPUS:85050591315
T3 - 2017 IEEE Visual Communications and Image Processing, VCIP 2017
SP - 1
EP - 4
BT - 2017 IEEE Visual Communications and Image Processing, VCIP 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 IEEE Visual Communications and Image Processing, VCIP 2017
Y2 - 10 December 2017 through 13 December 2017
ER -