Computer Vision for OSINT Research

VFRAME researches and develops state-of-the-art computer vision technologies for application to human rights research and conflict zone monitoring. VFRAME works with Mnemonic.org to guide the development process of each new technology.

Our latest results in generating and training with high-fidelity synthetic image data show compelling performance at over 90% detection accuracy running at 400 FPS on a single GPU desktop. Case study / white paper estimated to be published in Q4 2021.

RBk-250 detections using synthetic data trained model
Research: These detections show the accuracy of a RBK-250 object detection algorithm trained using 100% 3D-rendered synthetic data.
Image © Mnemonic.org + VFRAME.io

Current Research and Prototypes

3D Printed Training Data
  • 3D Printed Training Data
  • Enriching synthetic data with 3D printed cluster munition replicas for use in image training datasets
3D Rendered Training Data
  • 3D Rendered Training Data
  • Using 3D modeled scenes to build synthetic training datasets for objects in conflict zones
Cluster Munition Detector
  • Cluster Munition Detector
  • Training object detection algorithms to locate illegal munitions
Scene Summarization
  • Scene Summarization
  • Content-based scene summarization to find the most representative frames in videos
Media Attribute Analysis
  • Media Attribute Analysis
  • Using simple media attributes to understand large OSINT video datasets

About VFRAME

Human rights researchers often rely on videos shared online to document war crimes, atrocities, and human rights violations. Manually reviewing these videos is expensive, does not scale, and can cause vicarious trauma. As an increasing number of videos are posted, a new approach is needed to understand these large datasets.

VFRAME has been working with Mnemonig.org, a Berlin-based organization dedicated to documenting war crimes and human rights violations, to develop computer vision tools to address these challenges.

Specifically, VFRAME has been developing a scalable computer vision system for large-scale analysis of video archives to detect illegal munitions, and redaction tools to blur faces. VFRAME can detect objects, such as the RBK-250 munition found in videos from the Syrian conflict, with over 90% accuracy at over 400 FPS on a single desktop.

Read more about who we are and what we do.

Recent Press

Collaborations

Form Labs
Syrian Archive

Funding

German Federal Ministry of Education and Research - BMBF
Meedan / Check Global
NLNet and NGI0
Prototype Fund

Awards

Ars Electronica
Beazley Design of the Year Awards 2019
STARTS

Publications

In development