Translator Disclaimer
31 December 2019 Optimization of the OSVOS model
Author Affiliations +
Abstract
We solve the problem of video object segmentation by investigating how to expand the role of convolution in convolutional neural networks. Based on the One-Shot Video Object Segmentation (OSVOS) which can successfully tackle the task of semi-supervised video object segmentation, we introduce U-shape architecture. We first build a Global Guidance Module (GGM) on the bottom-up path to provide location information of potentially significant objects for layers of different feature levels. Then we design a Multi-scale Convolution Module (MCM) to fully get feature information and a Feature Fusion Module (FFM) to make the coarse-level semantic information well fused with the finelevel features from the top-down pathway. GGM and FFM allow the high-level semantic features to be progressively refined, yielding detail enriched segmentation maps. The experimental results on DAVIS 2016 data set shows that our proposed approach can more accurately locate the segmentation objects with sharpened details and our model has improved on all indicators than OSVOS.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Shizhan Hong, Tieyong Cao, Shengkai Xiang, Zheng Fang, Xiaotong Deng, Yifeng Peng, and Lei Xiang "Optimization of the OSVOS model", Proc. SPIE 11384, Eleventh International Conference on Signal Processing Systems, 113840Z (31 December 2019); https://doi.org/10.1117/12.2559779
PROCEEDINGS
6 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

A HWMSE for clue detection the system design and...
Proceedings of SPIE (October 26 2013)
Video co-saliency detection
Proceedings of SPIE (August 29 2016)
Knowledge-guided parsing in video databases
Proceedings of SPIE (April 14 1993)
Scenic classification methods for image and video databases
Proceedings of SPIE (November 21 1995)
WeatherDigest: an experiment in media conversion
Proceedings of SPIE (January 03 1996)
Video shot grouping using best-first model merging
Proceedings of SPIE (January 01 2001)

Back to Top