Semantic Video Segmentation : Exploring Inference Efficiency
This work addresses the challenge of efficient video segmentation for computer vision applications, but it is incremental as it builds on existing methods like CRF inference and TextonBoost.
The paper tackles the problem of improving efficiency and accuracy in video semantic segmentation by combining semantic co-labeling with more expressive models, achieving up to 8% accuracy improvement on the CamVid dataset without extra time overhead.
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