TY - JOUR
T1 - Maximum likelihood FIR filter for visual object tracking
AU - Min Pak, Jung
AU - Ki Ahn, Choon
AU - Hak Mo, Yung
AU - Taeg Lim, Myo
AU - Kyou Song, Moon
N1 - Funding Information:
This work was supported in part by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (Grant No. NRF-2016R1D1A1B01016071 ), in part by Basic Science Research Program through the NRF funded by the Ministry of Science, ICT, and Future Planning (Grant No. NRF-2014R1A1A1006101 ), and in part by Basic Science Research Program through the NRF funded by the Ministry of Education (Grant No. NRF-2013R1A1A2060663 ).
PY - 2016/12/5
Y1 - 2016/12/5
N2 - Visual object trackers usually adopt filters, such as the Kalman filter (KF) and the particle filter (PF), in order to improve tracking accuracy by suppressing measurement noises. However, if the filters have infinite impulse response (IIR) structures, the visual trackers adopting them can exhibit degraded tracking performance when system models have parameter uncertainties or when the noise information is incorrect. To overcome this problem, in this paper, we propose a new finite impulse response (FIR) filter for visual object tracking (VOT). The proposed filter is derived by maximizing the likelihood function, and it is referred to as the maximum likelihood FIR filter (MLFIRF). We conducted extensive experiments to show that the MLFIRF provides superior and more reliable tracking results compared with the KF, PF, and H∞ filter (HF) in VOT.
AB - Visual object trackers usually adopt filters, such as the Kalman filter (KF) and the particle filter (PF), in order to improve tracking accuracy by suppressing measurement noises. However, if the filters have infinite impulse response (IIR) structures, the visual trackers adopting them can exhibit degraded tracking performance when system models have parameter uncertainties or when the noise information is incorrect. To overcome this problem, in this paper, we propose a new finite impulse response (FIR) filter for visual object tracking (VOT). The proposed filter is derived by maximizing the likelihood function, and it is referred to as the maximum likelihood FIR filter (MLFIRF). We conducted extensive experiments to show that the MLFIRF provides superior and more reliable tracking results compared with the KF, PF, and H∞ filter (HF) in VOT.
KW - Finite impulse response (FIR) filter
KW - Maximum likelihood
KW - Maximum likelihood FIR filter (MLFIRF)
KW - Visual object tracking (VOT)
UR - http://www.scopus.com/inward/record.url?scp=84994121203&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84994121203&partnerID=8YFLogxK
U2 - 10.1016/j.neucom.2016.07.047
DO - 10.1016/j.neucom.2016.07.047
M3 - Article
AN - SCOPUS:84994121203
VL - 216
SP - 543
EP - 553
JO - Neurocomputing
JF - Neurocomputing
SN - 0925-2312
ER -