LandScan: A Natural Language and Computer Vision System for Analyzing Aerial Images

Abstract

LandScan (LANguage Driven SCene ANalysis) is presented as an integrated vision system which covers most levels of both vision and natural language processing. Computations are both data-driven and query-driven. In the report we focus on the design of the vision and control modules. Future work will investigate in more detail the design of the natural language interface. The data-driven system employs active control of stereo cameras for image acquisition, and dynamically constructs a surface model from multiple aerial views of an urban scene. The query-driven system allows the user's natural language queries to focus analysis to pertinent regions of the scene. This is different than many image understanding systems which present a symbolic description of the entire scene regardless of what portions of that picture are actually of interest.