---
title: "LandScan: A Natural Language and Computer Vision System for Analyzing Aerial Images"
authors:
  - "Ruzena Bajcsy"
  - "Aravind K. Joshi"
  - "Eric Krotkov"
  - "Amy E. Zwarico"
doi: ""
url: "https://ijcai.org/proceedings/1985/185"
pdf: "https://ijcai.org/proceedings/1985/0185.pdf"
venue: "Proceedings of the Ninth International Joint Conference on Artificial Intelligence"
year: 1985
pages: "919-920"
track: "Perception"
keywords:
---

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

Ruzena Bajcsy, Aravind K. Joshi, Eric Krotkov, Amy E. Zwarico

*Proceedings of the Ninth International Joint Conference on Artificial Intelligence*, pages 919-920.

## Abstract

LandScan (LANguage Driven SCene ANalysis) is presented as an integrated vision system which covers most Ievels 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 camcras 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 l:m guage queries to focus analysis to pertincnt 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.