Video-Based Performance Evaluation for ECR Drills

Published:Dec 29, 2025 19:30
1 min read
ArXiv

Analysis

This paper addresses the challenge of automatically assessing performance in military training exercises (ECR drills) within synthetic environments. It proposes a video-based system that uses computer vision to extract data (skeletons, gaze, trajectories) and derive metrics for psychomotor skills, situational awareness, and teamwork. This approach offers a less intrusive and potentially more scalable alternative to traditional methods, providing actionable insights for after-action reviews and feedback.

Reference

The system extracts 2D skeletons, gaze vectors, and movement trajectories. From these data, we develop task-specific metrics that measure psychomotor fluency, situational awareness, and team coordination.