Motion estimation and compensation using video object tracking Śledzenie obiektu w obrazie wideo w estymacji i kompensacji położenia

Tunç S., ILGIN H. A.

Przeglad Elektrotechniczny, cilt.89, sa.2 B, ss.223-227, 2013 (SCI-Expanded) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 89 Sayı: 2 B
  • Basım Tarihi: 2013
  • Dergi Adı: Przeglad Elektrotechniczny
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.223-227
  • Anahtar Kelimeler: Affine and perspective transformation, Object based motion estimation and compensation, Parameter estimation, Video objects
  • Ankara Üniversitesi Adresli: Evet

Özet

Motion estimation is one of the most important processes of video compression standards that affect the quality and compression ratio of encoded video stream. In this paper we present a motion estimation algorithm, which is based on ASIFT method. We segment foreground objects into regions by exploiting features which are obtained on the object. Motion model of a region is determined according to the number of features in the region. Obtained motion model is applied on the region of objects and if holes are occurred, they are closed by bilinear interpolation. Motion compensation results of our method are compared with the most common motion estimation methods used in video coding standards.