Drone and Land Visual Informatics for Digital Twin and AI Service

In the presentation, object detection in drone imagery and land views is a crutialtopic in the Computer Vision field. This work is widely applied in traffic analysis and control, rescue systems, smart agriculture, etc. for extensible projects. However, many challenges exist in developing and optimizing applications because of object density, multi-scale and view direction, and blur motion and so on. This speech will focus on analyzing and assessing several famous drone imagery datasets and their challenges in AI service. Also, it covers the related land imagery related recent projects for digital twin and other AI service application which are performed in Codepro Inc. in coordination with Intelligent Systems Laboratory (ISLab), University of Ulsan (UOU), Korea