System for Automatic and Real-time Generalization of Catastrophe Maps based on Deep Learning Methods

主要研究课题《基于深度学习方法的灾变地图自动实时综合系统》分为不同的子课题。例如：分割与超分辨率库的建立、实时地图分割的应用、基于深度学习的高精度语义构建、行人轨迹预测与监控、高精度模式识别精度提升的超分辨率集成方法、变化检测等。

The main research topic “System for Automatic and Real-time Generalization of Catastrophe Maps based on Deep Learning Methods” was splitted into different subtopics. For instance: segmentation and super-resolution library establishment, real-time map segmentation application, high accuracy building semantic based on deep learning, the pedestrian trajectory prediction and surveillance, super-resolution integrated method for accuracy pattern recognition accuracy enhancement, change detection, etc.