Chairs: Prof. Lan Du (Xidian University),
Assistant Prof. Hao Shi (Beijing Institute of Technology),
Assistant Prof. Yuqi Han (Beijing Institute of Technology)
Abstract:
Recent years have witnessed the ever-growing availability of multi-source high-resolution remote sensing (RS) images (e.g., optical imagery, infrared and SAR) from sensors installed on satellites, aircraft, etc. These substantial quantities of RS images provide accurate, diverse, and complementary insights for a better understanding of Earth (e.g., fine-grained land cover classification and target recognition). To extract valuable information from massive remote sensing images automatically and rapidly, intelligent and real-time processing technology has become a hot topic in recent years. However, several challenges and open issues remain to be addressed in the typical RS tasks, including novel methods for feature representations and efficient algorithms design to handle massive imagery with large-scale and high-resolution. This Special Session devotes to developing state-of-the-art machine learning methods for more accurate remote sensing tasks. Prospective authors are invited to submit their original unpublished contributions to this special issue.
The broad topics include (but are not limited to):
•Real-time and intelligent processing system for remote sensing images
•Intelligent detection and tracking algorithms for remote sensing tasks
•Multi-modal remote sensing data fusion, analysis and understanding
•Large-scale remote sensing data compressing and transmission
•Pruning, quantization and compression for deep learning algorithms
•Emerging earth-Observation remote sensing applications