TY - GEN
T1 - Joint technique of fine object boundary recovery and foreground image deblur for video including moving objects
AU - Matsushita, Yuki
AU - Kawasaki, Hiroshi
AU - Takano, Teruhisa
AU - Ono, Shintaro
AU - Ikeuchi, Katsushi
N1 - Publisher Copyright:
© 2017 SPIE.
PY - 2017
Y1 - 2017
N2 - Capturing large scale outdoor scene by video camera becomes common for various purposes, such as city modeling, surveillance, etc., and demand of recovering high quality image from video data is increasing. Because outdoor scene includes several barriers with multiple depths and motions, e.g.., cars or fences, simply applying motion deblur technique to each frame makes some noise. Furthermore, since color is mixed with foreground and background object near occluding boundary, color separation method during debluring process is needed to restore the objects. In this paper, we propose a method to recover original boundary of foreground object from multiple blurred input images of video data. By using the refined object boundary, artifact around the border is reduced and accurate deblurring in the whole image is performed. Since both techniques are based on statistical method, quality of recovered image becomes better, if a number of input image increases. Experimental results are shown to prove that our method successfully recovers the deblurred image even if there are severe motion blur and color mixture near occluding boundary.
AB - Capturing large scale outdoor scene by video camera becomes common for various purposes, such as city modeling, surveillance, etc., and demand of recovering high quality image from video data is increasing. Because outdoor scene includes several barriers with multiple depths and motions, e.g.., cars or fences, simply applying motion deblur technique to each frame makes some noise. Furthermore, since color is mixed with foreground and background object near occluding boundary, color separation method during debluring process is needed to restore the objects. In this paper, we propose a method to recover original boundary of foreground object from multiple blurred input images of video data. By using the refined object boundary, artifact around the border is reduced and accurate deblurring in the whole image is performed. Since both techniques are based on statistical method, quality of recovered image becomes better, if a number of input image increases. Experimental results are shown to prove that our method successfully recovers the deblurred image even if there are severe motion blur and color mixture near occluding boundary.
UR - https://www.scopus.com/pages/publications/85020296330
UR - https://www.scopus.com/pages/publications/85020296330#tab=citedBy
U2 - 10.1117/12.2266746
DO - 10.1117/12.2266746
M3 - Conference contribution
AN - SCOPUS:85020296330
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Thirteenth International Conference on Quality Control by Artificial Vision 2017
A2 - Yamashita, Atsushi
A2 - Nagahara, Hajime
A2 - Umeda, Kazunori
PB - SPIE
T2 - 13th International Conference on Quality Control by Artificial Vision, QCAV 2017
Y2 - 14 May 2017 through 16 May 2017
ER -