Graph Construction for Salient Object Detection in Videos
Paper i proceeding, 2014

Recently many graph-based salient region/object detection methods have been developed. They are rather effective for still images. However, little attention has been paid to salient region detection in videos. This paper addresses salient region detection in videos. A unified approach towards graph construction for salient object detection in videos is proposed. The proposed method combines static appearance and motion cues to construct graph, enabling a direct extension of original graph based salient region detection to video processing. To maintain coherence in both intra- and inter-frames, a spatial-temporal smoothing operation is proposed on a structured graph derived from consecutive frames. The effectiveness of the proposed method is tested and validated using seven videos from two video datasets.

Optical flows

Video processing

Salient region detection

Graph construction

Författare

Keren Fu

Signaler och system, Signalbehandling och medicinsk teknik, Signalbehandling

Irene Yu-Hua Gu

Signaler och system, Signalbehandling och medicinsk teknik, Signalbehandling

Yixiao Yun

Signaler och system, Signalbehandling och medicinsk teknik, Signalbehandling

C Gong

Shanghai Jiao Tong University

Jie Yang

Shanghai Jiao Tong University

22th International Conference on Pattern Recognition, 24-28 Aug. 2014, Stockholm, Sweden

1051-4651 (ISSN)

2371-2376

Styrkeområden

Informations- och kommunikationsteknik

Ämneskategorier

Signalbehandling

Datorseende och robotik (autonoma system)

DOI

10.1109/ICPR.2014.411

ISBN

978-147995208-3