Keypoint of interest based on spatio-temporal feature considering mutual dependency and camera motion

Takahiro Suzuki*, Takeshi Ikenaga

*この研究の対応する著者

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

Recently, cloud systems start to be utilized for services to analyze user's data in the region of computer vision. In these services, keypoints are extracted from images or videos and the data is identified by machine learning with large database of cloud. Conventional keypoint extraction algorithms utilize only spatial information and many unnecessary keypoints for recognition are detected. Thus, the systems have to communicate large data and require processing time of descriptor calculations. This paper proposes a spatio-temporal keypoint extraction algorithm that detects only Keypoints of Interest (KOI) based on spatio-temporal feature considering mutual dependency and camera motion. The proposed method includes an approximated Kanade-Lucas-Tomasi (KLT) tracker to calculate the positions of keypoints and optical flow. This algorithm calculates the weight at each keypoint using two kinds of features: intensity gradient and optical flow. It reduces noise of extraction by comparing with states of surrounding keypoints. The camera motion estimation is added and it calculates camera-motion invariant optical flow. Evaluation results show that the proposed algorithm achieves 95% reduction of keypoint data and 53% reduction of computational complexity comparing a conventional keypoint extraction. KOI are extracted in the region whose motion and gradient are large.

本文言語English
ホスト出版物のタイトル6th International Conferences on Advances in Multimedia, MMEDIA 2014
編集者Pascal Lorenz
出版社International Academy, Research and Industry Association, IARIA
ページ20-25
ページ数6
ISBN(電子版)9781612083209
出版ステータスPublished - 2014 1 1
イベント6th International Conferences on Advances in Multimedia, MMEDIA 2014 - Nice, France
継続期間: 2014 2 232014 2 27

出版物シリーズ

名前MMEDIA - International Conferences on Advances in Multimedia
ISSN(印刷版)2308-4448

Conference

Conference6th International Conferences on Advances in Multimedia, MMEDIA 2014
国/地域France
CityNice
Period14/2/2314/2/27

ASJC Scopus subject areas

  • コンピュータ グラフィックスおよびコンピュータ支援設計
  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Keypoint of interest based on spatio-temporal feature considering mutual dependency and camera motion」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