Joint Inference of Groups, Events and Human Roles in Aerial Videos

TL;DR

This paper presents a joint inference framework for analyzing low-resolution aerial videos, enabling the simultaneous grouping, event recognition, and role assignment of people in large outdoor scenes, which is crucial for drone-based surveillance.

Contribution

It introduces a novel spatiotemporal inference method using AND-OR graphs and templates, specifically designed for low-resolution aerial video analysis, and provides a new dataset for evaluation.

Findings

Effective joint inference of groups, events, and roles in aerial videos

Improved accuracy over isolated inference methods

Demonstrated robustness in challenging low-resolution conditions

Abstract

With the advent of drones, aerial video analysis becomes increasingly important; yet, it has received scant attention in the literature. This paper addresses a new problem of parsing low-resolution aerial videos of large spatial areas, in terms of 1) grouping, 2) recognizing events and 3) assigning roles to people engaged in events. We propose a novel framework aimed at conducting joint inference of the above tasks, as reasoning about each in isolation typically fails in our setting. Given noisy tracklets of people and detections of large objects and scene surfaces (e.g., building, grass), we use a spatiotemporal AND-OR graph to drive our joint inference, using Markov Chain Monte Carlo and dynamic programming. We also introduce a new formalism of spatiotemporal templates characterizing latent sub-events. For evaluation, we have collected and released a new aerial videos dataset using a hex-rotor flying over picnic areas rich with group events. Our results demonstrate that we successfully address above inference tasks under challenging conditions.