Translator Disclaimer
20 February 2020 Gradient-driven unsupervised video segmentation using deep learning techniques
Author Affiliations +

We propose a three-dimensional video segmentation method using deep learning convolutional neural nets. The algorithm utilizes the local gradient computed at each pixel location together with the global boundary map acquired through deep learning methods to generate initial pixel groups by traversing from low to high gradient regions. A local clustering method is then employed to refine these initial pixel groups. The refined subvolumes in the homogeneous regions of video are selected as initial seeds and iteratively combined with adjacent groups based on intensity similarities. The volume growth is terminated at the color boundaries of the video. The oversegments obtained from the above steps are then merged hierarchically by a multivariate approach yielding a final segmentation map for each frame. The results show that our proposed methodology compares favorably well, on a qualitative and quantitative level, in segmentation quality and computational efficiency, with the latest state-of-the-art techniques utilizing the video segmentation benchmark dataset.

© 2020 SPIE and IS&T 1017-9909/2020/$28.00 © 2020 SPIE and IS&T
Sankaranarayanan Piramanayagam, Eli Saber, and Nathan D. D. Cahill "Gradient-driven unsupervised video segmentation using deep learning techniques," Journal of Electronic Imaging 29(1), 013019 (20 February 2020).
Received: 26 March 2019; Accepted: 23 January 2020; Published: 20 February 2020

Back to Top