NOMAD: A Natural, Occluded, Multi-scale Aerial Dataset, for Emergency Response Scenarios

TL;DR

NOMAD is a comprehensive aerial dataset designed to evaluate human detection performance under occlusion in emergency response scenarios, featuring multi-scale, natural occlusions, and detailed annotations to improve computer vision models for search and rescue.

Contribution

The paper introduces NOMAD, a novel dataset specifically addressing occlusion challenges in aerial human detection for emergency response, with diverse scenarios and detailed visibility annotations.

Findings

Dataset includes 42,825 frames with occlusion annotations.

Provides a benchmark for evaluating detection models under occlusion.

Supports development of more robust aerial human detection algorithms.

Abstract

With the increasing reliance on small Unmanned Aerial Systems (sUAS) for Emergency Response Scenarios, such as Search and Rescue, the integration of computer vision capabilities has become a key factor in mission success. Nevertheless, computer vision performance for detecting humans severely degrades when shifting from ground to aerial views. Several aerial datasets have been created to mitigate this problem, however, none of them has specifically addressed the issue of occlusion, a critical component in Emergency Response Scenarios. Natural, Occluded, Multi-scale Aerial Dataset (NOMAD) presents a benchmark for human detection under occluded aerial views, with five different aerial distances and rich imagery variance. NOMAD is composed of 100 different Actors, all performing sequences of walking, laying and hiding. It includes 42,825 frames, extracted from 5.4k resolution videos, and manually annotated with a bounding box and a label describing 10 different visibility levels, categorized according to the percentage of the human body visible inside the bounding box. This allows computer vision models to be evaluated on their detection performance across different ranges of occlusion. NOMAD is designed to improve the effectiveness of aerial search and rescue and to enhance collaboration between sUAS and humans, by providing a new benchmark dataset for human detection under occluded aerial views. Full dataset can be found at: https://github.com/ArtRuss/NOMAD.