ForestPersons: A Large-Scale Dataset for Under-Canopy Missing Person Detection

2026-03-02

AI Summary

This work addresses the challenge of detecting missing persons in forest search-and-rescue operations, where dense tree canopies severely obstruct conventional aerial views. To bridge this gap, the authors introduce ForestPersons, a novel dataset comprising 96,482 images with 204,078 annotated instances, specifically captured from understory low-altitude and ground-level perspectives to emulate the visual conditions of micro-aerial vehicles. The dataset spans diverse environments and times of day and provides bounding boxes, human pose annotations, and visibility labels to facilitate occlusion-aware person detection research. Baseline experiments demonstrate that existing general-purpose and search-and-rescue-oriented detection models exhibit significantly degraded performance in this setting, underscoring the necessity and value of ForestPersons for advancing person detection technologies tailored to complex forested environments.

Technology Category

• Computer Vision: Image and Video Retrieval
• Search and Optimization: Mixed Discrete/Continuous Search
• Humans and AI: Crowd Sourcing and Human Computation

Application Category

• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Detecting missing persons in forest environments remains a challenge, as dense canopy cover often conceals individuals from detection in top-down or oblique aerial imagery typically captured by Unmanned Aerial Vehicles (UAVs). While UAVs are effective for covering large, inaccessible areas, their aerial perspectives often miss critical visual cues beneath the forest canopy. This limitation underscores the need for under-canopy perspectives better suited for detecting missing persons in such environments. To address this gap, we introduce ForestPersons, a novel large-scale dataset specifically designed for under-canopy person detection. ForestPersons contains 96,482 images and 204,078 annotations collected under diverse environmental and temporal conditions. Each annotation includes a bounding box, pose, and visibility label for occlusion-aware analysis. ForestPersons provides ground-level and low-altitude perspectives that closely reflect the visual conditions encountered by Micro Aerial Vehicles (MAVs) during forest Search and Rescue (SAR) missions. Our baseline evaluations reveal that standard object detection models, trained on prior large-scale object detection datasets or SAR-oriented datasets, show limited performance on ForestPersons. This indicates that prior benchmarks are not well aligned with the challenges of missing person detection under the forest canopy. We offer this benchmark to support advanced person detection capabilities in real-world SAR scenarios. The dataset is publicly available at https://huggingface.co/datasets/etri/ForestPersons.

Problem

• missing person detection
• forest canopy
• under-canopy perspective
• search and rescue
• occlusion

Innovation

• under-canopy detection
• missing person search
• ForestPersons dataset
• occlusion-aware annotation
• micro aerial vehicles (MAVs)