Adaptive convolutional neural network for large change in video object segmentation. Issue 5 (28th June 2019)

• Record Type: Journal Article
• Authors: Yin, Hui; Yang, Lin; Xu, Hongli; Wan, Jin
• Is Part Of: IET computer vision. Volume 13:Issue 5(2019)
• Page Start: 452
• Page End: 460
• Publication Date: 2019-06-28
• Subjects: video signal processing -- image segmentation -- image sequences -- optimisation -- convolutional neural nets; motion metric -- appearance metric -- consecutive video frames -- video object segmentation -- semisupervised segmentation task -- video sequence -- adaptive approach -- adaptive convolutional neural network -- VOS -- lightweight optimisation algorithm -- predictive binary mask -- pixel prediction -- discrete points cluster; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2018.5387
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : This study tackles the semi‐supervised segmentation task for the objects that have large motion or appearance change in a video sequence, which is very challenging to the existing methods of video object segmentation (VOS). In this study, a novel adaptive approach is presented, named adaptive convolutional neural network for large change VOS, which determines when and how to fine‐tune the convolutional neural network through the motion metric and the appearance metric among consecutive video frames. Additionally, a lightweight optimisation algorithm for the predictive binary mask is introduced which is effective for pixel prediction by eliminating the discrete points cluster. To illustrate the advantages of this approach, experiments have been performed on four VOS datasets, which demonstrate that the proposed method is highly effective and could achieve the state‐of‐the‐art on these datasets.