Deep learning-based face detection and recognition on drones

Unmanned aerial vehicles as known as drones, are aircraft that can comfortably search locations which are excessively dangerous or difficult for humans and take data from bird's-eye view. Enabling unmanned aerial vehicles to detect and recognize humans on the ground is essential for various app...

Full description

Saved in:
Bibliographic Details
Published in:Journal of ambient intelligence and humanized computing 2024, Vol.15 (1), p.373-387
Main Authors: Rostami, Mohsen, Farajollahi, Amirhamzeh, Parvin, Hashem
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Artificial Intelligence
Artificial neural networks
Classification
Clustering
Computational Intelligence
Deep learning
Drone aircraft
Drone vehicles
Drones
Engineering
Face recognition
Facial recognition technology
High altitude
Machine learning
Original Research
Pattern recognition
Performance evaluation
Remote monitoring
Robotics and Automation
Semantics
Surveillance
Unmanned aerial vehicles
User Interfaces and Human Computer Interaction
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Unmanned aerial vehicles as known as drones, are aircraft that can comfortably search locations which are excessively dangerous or difficult for humans and take data from bird's-eye view. Enabling unmanned aerial vehicles to detect and recognize humans on the ground is essential for various applications, such as remote monitoring, people search, and surveillance. The current face detection and recognition models are able to detect or recognize faces on unmanned aerial vehicles using various limits in height, angle and distance, mainly where drones take images from high altitude or long distance. In the present paper, we proposed a novel face detection and recognition model on drones for improving the performance of face recognition when query images are taken from high altitudes or long distances that do not show much facial information of the humans. Moreover, we aim to employ deep neural network to perform these tasks and reach an enhanced top performance. Experimental evaluation of the proposed framework compared to state-of-the-art models over the DroneFace dataset demonstrates that our method can attain competitive accuracy on both the recognition and detection protocols.
ISSN:1868-5137
1868-5145
DOI:10.1007/s12652-022-03897-8