WaterNet: An adaptive matching pipeline for segmenting water with volatile appearance

Authors

Yongqing Liang, Louisiana State University
Navid Jafari, Louisiana State University
Xing Luo, Zhejiang University
Qin Chen, Northeastern University
Yanpeng Cao, Zhejiang University
Xin Li, Louisiana State University

Document Type

Article

Publication Date

3-1-2020

Abstract

We develop a novel network to segment water with significant appearance variation in videos. Unlike existing state-of-the-art video segmentation approaches that use a pre-trained feature recognition network and several previous frames to guide segmentation, we accommodate the object’s appearance variation by considering features observed from the current frame. When dealing with segmentation of objects such as water, whose appearance is non-uniform and changing dynamically, our pipeline can produce more reliable and accurate segmentation results than existing algorithms.

Publication Source (Journal or Book title)

Computational Visual Media

First Page

65

Last Page

78

Recommended Citation

Liang, Y., Jafari, N., Luo, X., Chen, Q., Cao, Y., & Li, X. (2020). WaterNet: An adaptive matching pipeline for segmenting water with volatile appearance. Computational Visual Media, 6 (1), 65-78. https://doi.org/10.1007/s41095-020-0156-x