Deep Learning and Artificial Intelligence for Non-Vision Sensors and Imaging
1Hunan University, Changsha, China
2West Pomeranian University of Technology, Szczecin, Poland
3Changsha University, Changsha, China
Deep Learning and Artificial Intelligence for Non-Vision Sensors and Imaging
Description
Machine vision (MV) based on charge-coupled device (CCD) and complementary metal oxide semiconductor (CMOS) sensors provides a solution for many issues faced in the fields of intelligent manufacturing and quality assurance. However, with traditional machine vision, it can be difficult to detect the internal information of objects and to obtain information from other physical fields. Electromagnetic, acoustic, vibration, radiation, and thermal sensors and imaging are all also widely used in industry, because they can detect the inside of an object and other physical information. Recently, related deep learning and artificial intelligence (AI) techniques have been the subject of increasing research interest from both industry and academia.
However, there are still problems to be faced in research into the use of deep learning and AI for non-vision sensors and imaging. For example, current AI models are derived from machine vision but are not suitable for other kinds of sensors, the small amounts of data that can be used for training results; fusion methods and cross modal identification models of MV and other sensors are still lacking. In addition, temporal and spatial information of data have not been considered together, and there still exists a gap between laboratory-based experiments and real industrial applications.
This Special Issue aims to provide a platform to communicate and discuss the development of deep learning and AI techniques for non-vision sensors and imaging, especially in non-destructive testing, structural health monitoring, fault diagnosis, and condition monitoring. In addition, we aim to provide insights into the use of deep learning and AI models for processing data from non-vision sensors and imaging. We welcome both original research and review articles.
Potential topics include but are not limited to the following:
- Electromagnetic, acoustic, vibration, radiation, and thermal sensors
- Thermography
- Deep learning techniques for non-vision sensors and imaging
- AI techniques for non-vision sensors and imaging
- AI techniques of non-destructive testing, structural health monitoring, fault diagnosis, condition monitoring, and measurement and detection
- Applications of edge computing for non-vision sensors
- Night vision with non-vision sensors and imaging