Semantic Video Segmentation: A Review on Recent Approaches

TL;DR

This survey reviews recent semantic video segmentation methods, compares datasets and evaluation metrics, and highlights CNN-based systems' superiority on key benchmarks, while discussing challenges and future directions.

Contribution

It provides a comprehensive overview of recent approaches, datasets, and evaluation methods in semantic segmentation, emphasizing CNN-based systems' advantages.

Findings

CNN-based systems outperform traditional methods on CamVid and NYUDv2 datasets.

The survey identifies challenges and potential future research areas in semantic segmentation.

Different datasets and evaluation parameters are discussed for benchmarking progress.

Abstract

This paper gives an overview on semantic segmentation consists of an explanation of this field, it's status and relation with other vision fundamental tasks, different datasets and common evaluation parameters that have been used by researchers. This survey also includes an overall review on a variety of recent approaches (RDF, MRF, CRF, etc.) and their advantages and challenges and shows the superiority of CNN-based semantic segmentation systems on CamVid and NYUDv2 datasets. In addition, some areas that is ideal for future work have mentioned.