TY - GEN
T1 - The Emerging Field of Graph Signal Processing for Moving Object Segmentation
AU - Giraldo, Jhony H.
AU - Javed, Sajid
AU - Sultana, Maryam
AU - Jung, Soon Ki
AU - Bouwmans, Thierry
N1 - Publisher Copyright:
© 2021, Springer Nature Switzerland AG.
PY - 2021/1/1
Y1 - 2021/1/1
N2 - Moving Object Segmentation (MOS) is an important topic in computer vision. MOS becomes a challenging problem in the presence of dynamic background and moving camera videos such as Pan–Tilt–Zoom cameras (PTZ). The MOS problem has been solved using unsupervised and supervised learning strategies. Recently, new ideas to solve MOS using semi-supervised learning have emerged inspired from the theory of Graph Signal Processing (GSP). These new algorithms are usually composed of several steps including: segmentation, background initialization, features extraction, graph construction, graph signal sampling, and a semi-supervised learning algorithm inspired from reconstruction of graph signals. In this work, we summarize and explain the theoretical foundations as well as the technical details of MOS using GPS. We also propose two architectures for MOS using semi-supervised learning and a new evaluation procedure for GSP-based MOS algorithms. GSP-based algorithms are evaluated in the Change Detection (CDNet2014) dataset for MOS, outperforming numerous State-Of-The-Art (SOTA) methods in several challenging conditions.
AB - Moving Object Segmentation (MOS) is an important topic in computer vision. MOS becomes a challenging problem in the presence of dynamic background and moving camera videos such as Pan–Tilt–Zoom cameras (PTZ). The MOS problem has been solved using unsupervised and supervised learning strategies. Recently, new ideas to solve MOS using semi-supervised learning have emerged inspired from the theory of Graph Signal Processing (GSP). These new algorithms are usually composed of several steps including: segmentation, background initialization, features extraction, graph construction, graph signal sampling, and a semi-supervised learning algorithm inspired from reconstruction of graph signals. In this work, we summarize and explain the theoretical foundations as well as the technical details of MOS using GPS. We also propose two architectures for MOS using semi-supervised learning and a new evaluation procedure for GSP-based MOS algorithms. GSP-based algorithms are evaluated in the Change Detection (CDNet2014) dataset for MOS, outperforming numerous State-Of-The-Art (SOTA) methods in several challenging conditions.
KW - Graph Signal Processing
KW - Moving Object Segmentation
KW - Semi-supervised learning
UR - https://www.scopus.com/pages/publications/85112723482
U2 - 10.1007/978-3-030-81638-4_3
DO - 10.1007/978-3-030-81638-4_3
M3 - Conference contribution
AN - SCOPUS:85112723482
SN - 9783030816377
T3 - Communications in Computer and Information Science
SP - 31
EP - 45
BT - Frontiers of Computer Vision - 27th International Workshop, IW-FCV 2021, Revised Selected Papers
A2 - Jeong, Hieyong
A2 - Sumi, Kazuhiko
PB - Springer Science and Business Media Deutschland GmbH
T2 - 27th International Workshop on Frontiers of Computer Vision, IW-FCV 2021
Y2 - 22 February 2021 through 23 February 2021
ER -