direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Short-Term Motion-Based Object Segmentation

Supplementary material for:

"Short-Term Motion-Based Object Segmentation"

Marina Georgia Arvanitidou, Michael Tok, Andreas Krutz and Thomas Sikora
IEEE International Conference on Multimedia & Expo (ICME), Barcelona, Spain, 11.07.2011 - 15.07.2011 

Abstract

Motion-based segmentation approaches employ either long-term motion information or suffer from lack of accuracy and robustness. We present an automatic motion-based object segmentation algorithm for video sequences with moving camera, employing short-term motion information solely. For every frame, two error frames are generated using motion compensation. They are combined and a thresholding segmentation algorithm is applied. Recent advances in the field of global motion estimation enable outlier elimination in the background area, and thus a more precise definition of the foreground is achieved. We propose a simple and effective error frame generation and we consider spatial error localization. Thus, we achieve improved performance compared with a previously proposed short-term motion-based method and we provide subjective as well as objective evaluation.

Allstars (352 x 288, 250 frames)

Frame 97 of the original (left), reference (middle) and proposed (right) sequence.
Lupe
Results and f-measure
Sequences
P
R
F
Allstars original
-
-
-
Allstars reference1
80%
48%
59%
Allstars proposed
73%
66%
68%

Biathlon (352 x 288, 200 frames)

What is alternative text oeo?
Frame 95 of the original (left), reference (middle) and proposed (right) sequence.
Lupe
Results and f-measure
Sequences

P

R
F
Biathlon original

-
-
-
Biathlon reference1

82%

69%
74%
Biathlon proposed

75%

85%
80%

Mountain (352 x 192, 100 frames)

Frame 81 of the original (left), reference (middle) and proposed (right) sequence.
Lupe
Results and f-measure
Sequences
P
R
F
Mountain original
-
-
-
Mountain reference1

92%
73%
81%
Mountain proposed
76%
91%
83%

Race (544 x 336, 100 frames)

Frame 15 of the original (left), reference (middle) and proposed (right) sequence.
Lupe
Results and f-measure
Sequences
P
R
F
Race original
-
-
-
Race reference1
86%
59%
68%
Race proposed
63%
89%
74%

Stefan (352 x 240, 300 frames)

Frame 196 of the original (left), reference (middle) and proposed (right) sequence.
Lupe
Results and f-measure
Sequences
P
R
F
Stefan original
-
-
-
Stefan reference1
90%
53%
63%
Stefan proposed
69%
82%
73%

References

1 R. Mech, and M. Wollborn, “A noise robust method for segmentation of moving objects in video sequences”, in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 1997

Zusatzinformationen / Extras