BlockNet: A Deep Neural Network for Block-Based Motion Estimation Using Representative Matching
SCIE
SCOPUS
- Title
- BlockNet: A Deep Neural Network for Block-Based Motion Estimation Using Representative Matching
- Authors
- Lee, Junggi; Kong, Kyeongbo; Bae, Gyujin; Song, Woo-Jin
- Date Issued
- 2020-05
- Publisher
- MDPI
- Abstract
- Owing to the limitations of practical realizations, block-based motion is widely used as an alternative for pixel-based motion in video applications such as global motion estimation and frame rate up-conversion. We hereby present BlockNet, a compact but effective deep neural architecture for block-based motion estimation. First, BlockNet extracts rich features for a pair of input images. Then, it estimates coarse-to-fine block motion using a pyramidal structure. In each level, block-based motion is estimated using the proposed representative matching with a simple average operator. The experimental results show that BlockNet achieved a similar average end-point error with and without representative matching, whereas the proposed matching incurred 18% lower computational cost than full matching.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/106763
- DOI
- 10.3390/sym12050840
- ISSN
- 2073-8994
- Article Type
- Article
- Citation
- SYMMETRY-BASEL, vol. 12, no. 5, 2020-05
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.