Video Labeling for Automatic Video Surveillance in Security Domains

TL;DR

This paper introduces VIOLA, a novel tool for efficient labeling of UAV videos in security domains, facilitating large-scale data collection for security and wildlife monitoring applications.

Contribution

The paper presents VIOLA, a new labeling application with a workload distribution framework and specialized interface for UAV video annotation in security contexts.

Findings

VIOLA enables large-scale data collection from UAV videos.

Development of VIOLA improved labeling efficiency.

Facilitates deep learning applications for real-time security detection.

Abstract

Beyond traditional security methods, unmanned aerial vehicles (UAVs) have become an important surveillance tool used in security domains to collect the required annotated data. However, collecting annotated data from videos taken by UAVs efficiently, and using these data to build datasets that can be used for learning payoffs or adversary behaviors in game-theoretic approaches and security applications, is an under-explored research question. This paper presents VIOLA, a novel labeling application that includes (i) a workload distribution framework to efficiently gather human labels from videos in a secured manner; (ii) a software interface with features designed for labeling videos taken by UAVs in the domain of wildlife security. We also present the evolution of VIOLA and analyze how the changes made in the development process relate to the efficiency of labeling, including when seemingly obvious improvements did not lead to increased efficiency. VIOLA enables collecting massive amounts of data with detailed information from challenging security videos such as those collected aboard UAVs for wildlife security. VIOLA will lead to the development of new approaches that integrate deep learning for real-time detection and response.