Survey on semantic segmentation using deep learning techniques

By Fahad Lateef, Yassine Ruichek. Neurocomputing, 2019

525 citations recorded by the source corpus.

Abstract Semantic segmentation is a challenging task in computer vision systems. A lot of methods have been developed to tackle this problem ranging from autonomous vehicles, human-computer interaction, to robotics, medical research, agriculture and so on. Many of these methods have been built using the deep learning paradigm that has shown a salient performance. For this reason, we propose to survey these methods by, first categorizing them into ten different classes according to the common concepts underlying their architectures. Second, by providing an overview of the publicly available datasets on which they have been assessed. In addition, we present the common evaluation matrix used to measure their accuracy. Moreover, we focus on some of the methods and look closely at their architectures in order to find out how they have achieved their reported performances. Finally, we conclude by discussing some of the open problems and their possible solutions.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/03903af055d5345251efc844091a6d713adbd1a6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Ming Liu
2. H. Wang
3. Shuai Liu
4. Yudong Zhang
5. Liping Song
6. Xiangbin Liu
7. Yuxiang Sun
8. Weixun Zuo

In Computer Vision and Pattern Recognition

1. Ming Liu
2. Yuxiang Sun
3. H. Wang
4. Shuai Liu
5. Yudong Zhang
6. Liping Song
7. Xiangbin Liu
8. Weixun Zuo

Citations in the corpus

• RTFNet: RGB-Thermal Fusion Network for Semantic Segmentation of Urban Scenes (2019, background): “As the Encoder-Decoder structure has been confirmed as an effective architecture in many semantic segmentation networks [13], RTFNet also adopts this structure.”
• Self-Supervised Drivable Area and Road Anomaly Segmentation Using RGB-D Data For Robotic Wheelchairs (2019, background): “Recent development of deep learning techniques has brought significant improvements on the semantic segmentation using RGB-D cameras [5]–[7].”
• A Review of Deep-Learning-Based Medical Image Segmentation Methods (2021, background): “By combining various new theories and new technologies, we are finding a general segmentation algorithm that can be applied to kind of images [1].”