Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Structural similarity-based object tracking in multimodality surveillance videos
AU - Łoza, Artur
AU - Mihaylova, Lyudmila
AU - Bull, David
AU - Canagarajah, Nishan
PY - 2009/2
Y1 - 2009/2
N2 - This paper addresses the problem of object tracking in video sequences for surveillance applications by using a recently proposed structural similarity-based image distance measure. Multimodality surveillance videos pose specific challenges to tracking algorithms, due to, for example, low or variable light conditions and the presence of spurious or camouflaged objects. These factors often cause undesired luminance and contrast variations in videos produced by infrared sensors (due to varying thermal conditions) and visible sensors (e.g., the object entering shadowy areas). Commonly used colour and edge histogram-based trackers often fail in such conditions. In contrast, the structural similarity measure reflects the distance between two video frames by jointly comparing their luminance, contrast and spatial characteristics and is sensitive to relative rather than absolute changes in the video frame. In this work, we show that the performance of a particle filter tracker is improved significantly when the structural similarity-based distance is applied instead of the conventional Bhattacharyya histogram-based distance. Extensive evaluation of the proposed algorithm is presented together with comparisons with colour, edge and mean-shift trackers using real-world surveillance video sequences from multimodal (infrared and visible) cameras.
AB - This paper addresses the problem of object tracking in video sequences for surveillance applications by using a recently proposed structural similarity-based image distance measure. Multimodality surveillance videos pose specific challenges to tracking algorithms, due to, for example, low or variable light conditions and the presence of spurious or camouflaged objects. These factors often cause undesired luminance and contrast variations in videos produced by infrared sensors (due to varying thermal conditions) and visible sensors (e.g., the object entering shadowy areas). Commonly used colour and edge histogram-based trackers often fail in such conditions. In contrast, the structural similarity measure reflects the distance between two video frames by jointly comparing their luminance, contrast and spatial characteristics and is sensitive to relative rather than absolute changes in the video frame. In this work, we show that the performance of a particle filter tracker is improved significantly when the structural similarity-based distance is applied instead of the conventional Bhattacharyya histogram-based distance. Extensive evaluation of the proposed algorithm is presented together with comparisons with colour, edge and mean-shift trackers using real-world surveillance video sequences from multimodal (infrared and visible) cameras.
KW - Structural similarity measure · Object tracking · Video sequences · Particle filtering · Colour and edge cues · Multimodal data
KW - DCS-publications-id
KW - art-903
KW - DCS-publications-credits
KW - dsp
KW - DCS-publications-personnel-id
KW - 121
U2 - 10.1007/s00138-007-0107-x
DO - 10.1007/s00138-007-0107-x
M3 - Journal article
VL - 20
SP - 71
EP - 83
JO - Machine Vision and Applications
JF - Machine Vision and Applications
SN - 1432-1769
IS - 2
ER -