A Location-Aware Middleware Framework for Collaborative Visual Information Discovery and Retrieval
Abstract
This work addresses the problem of scalable location-aware distributed indexing to enable the leveraging of collaborative effort for the construction and maintenance of world-scale visual maps and models which could support numerous activities including navigation, visual localization, persistent surveillance, structure from motion, and hazard or disaster detection. Current distributed approaches to mapping and modeling fail to incorporate global geospatial addressing and are limited in their functionality to customize search. Our solution is a peer-to-peer middleware framework based on XOR distance routing which employs a Hilbert Space curve addressing scheme in a novel distributed geographic index. This allows for a universal addressing scheme supporting publish and search in dynamic environments while ensuring global availability of the model and scalability with respect to geographic size and number of users. The framework is evaluated using large-scale network simulations and a search application that supports visual navigation in real-world experiments.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 14, 2017
- Accession Number
- AD1051570
Entities
People
- Andrew J. Compton
Organizations
- Air Force Institute of Technology