BASS: Boundary-Aware Superpixel Segmentation

Antonio Rubio, Longlong Yu, Edgar Simo-Serra, Francesc Moreno-Noguer

研究成果: Conference contribution

9 被引用数 (Scopus)

抄録

We propose a new superpixel algorithm based on exploiting the boundary information of an image, as objects in images can generally be described by their boundaries. Our proposed approach initially estimates the boundaries and uses them to place superpixel seeds in the areas in which they are more dense. Afterwards, we minimize an energy function in order to expand the seeds into full superpixels. In addition to standard terms such as color consistency and compactness, we propose using the geodesic distance which concentrates small superpixels in regions of the image with more information, while letting larger superpixels cover more homogeneous regions. By both improving the initialization using the boundaries and coherency of the superpixels with geodesic distances, we are able to maintain the coherency of the image structure with fewer superpixels than other approaches. We show the resulting algorithm to yield smaller Variation of Information metrics in seven different datasets while maintaining Undersegmentation Error values similar to the state-of-the-art methods.

本文言語English
ホスト出版物のタイトル2016 23rd International Conference on Pattern Recognition, ICPR 2016
出版社Institute of Electrical and Electronics Engineers Inc.
ページ2824-2829
ページ数6
ISBN(電子版)9781509048472
DOI
出版ステータスPublished - 2016 1 1
イベント23rd International Conference on Pattern Recognition, ICPR 2016 - Cancun, Mexico
継続期間: 2016 12 42016 12 8

出版物シリーズ

名前Proceedings - International Conference on Pattern Recognition
0
ISSN(印刷版)1051-4651

Other

Other23rd International Conference on Pattern Recognition, ICPR 2016
CountryMexico
CityCancun
Period16/12/416/12/8

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

フィンガープリント 「BASS: Boundary-Aware Superpixel Segmentation」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル