Semantic Video Segmentation : Exploring Inference Efficiency
Computer Vision and Pattern Recognition
2015-09-09 v1
Abstract
We explore the efficiency of the CRF inference beyond image level semantic segmentation and perform joint inference in video frames. The key idea is to combine best of two worlds: semantic co-labeling and more expressive models. Our formulation enables us to perform inference over ten thousand images within seconds and makes the system amenable to perform video semantic segmentation most effectively. On CamVid dataset, with TextonBoost unaries, our proposed method achieves up to 8% improvement in accuracy over individual semantic image segmentation without additional time overhead. The source code is available at https://github.com/subtri/video_inference
Cite
@article{arxiv.1509.02441,
title = {Semantic Video Segmentation : Exploring Inference Efficiency},
author = {Subarna Tripathi and Serge Belongie and Youngbae Hwang and Truong Nguyen},
journal= {arXiv preprint arXiv:1509.02441},
year = {2015}
}
Comments
To appear in proc of ISOCC 2015