Videos, photos, and narratives (audio, text, graphics) enriched with geospatial coordinates can be used to capture spatial data and associated contextual information for a variety of challenging environments. These data can fill gaps where no data exists, capture ephemeral or constantly changing information, and provide contextual insights that elevate local knowledge beyond more traditional methods. Example applications might include how a slum changes after a vaccination intervention following a cholera outbreak, or identifying patterns of homeless camps (and their temporal stability). In this project, we develop computing infrastructures that help users capture, manage, query, and visualize geo-encoded videos and narratives. The goal is to bridge the gap between the diversity of needs from researchers and practitioners and data challenges often encountered "in the field". The utilization of the tools spans across disciplines as diverse as anthropology, clinical health, criminology, disaster management, epidemiology, geography, planning, and sociology.

This project creates a set of software tools for various tasks including:

• Data capture: GeoVideo mobile app on both iOS and Android platforms
• Data compression: A Geovisuals compression tool for domain users to manage geo-videos for easy sharing and transfer
• Web-based data sharing and visualization: online GeoVisuals data repository
• Visual analytics software:

1. Geovisuals: a comprehensive data analysis software with a set of visualization functions that are integrated in two investigation modes: geo-video analysis and geo-location analysis. It requires preprocessed geo-videos and geo-narratives with extracted textual narratives.
2. VisualCommunity: a convenient software which facilitates direct study of mobile-captured videos. It integrates AI based audio transcription and image recognition with interactive editing functions and map-based visual analysis

GeoVideo app captures location-based video allowing users to record the audio narratives together with where they were and what they saw. The app is available in iOS and Anroid platforms.

Geovisuals Data Repository allows users to share data and access the analytical and visualization functions through a web-based platform. Users need to create an account in the system. Please send an email to geovisuals.project@gmail.com or contact the development team for an account to use the repository.

GeoVisuals software utilizes a visual analysis approach built on semantic data points that can be integrated spatially, which in turn enables management in a unified database with combined spatio-temporal and text querying. A set of visualization functions are integrated in two investigation modes: geo-video analysis and geo-location analysis.

The details of this software can be found in a published paper at https://doi.org/10.1080/13658816.2020.1737700
GeoVisuals: a visual analytics approach to leverage the potential of spatial videos and associated geonarratives, Suphanut Jamonnak, Ye Zhao, Shamal AL-Dohuki, Andrew Curtis, Xinyue Ye, Farah Kamw, Jing Yang, International Journal of Geographical Information Science (IJGIS), 2020, Taylor & Francis.

VisualCommunity helps users directly process and visualize the collected video and audio narrative information. It can automatically process the video data to extract important frames, perform AI-based semantic image segmentation and speech transcription, and finally integrate them into an intuitive visual interface for user editing and knowledge discovery.

GeoVisuals compressor allows you to compress your video file by frame-rate or by resolution. GeoVisuals compressor also extract geospatial coordinates both in Comma-Separated Values (CSV) and GPS Exchange Format (GPX). This compressor is the software utility for GeoVisuals System.