Image Similarity Metrics Suitable for Infrared Video Stabilization during Active Wildfire Monitoring: A Comparative Analysis

Autor: Steven Verstockt, Oriol Rios, Christian Mata, Dan Jimenez, Eulàlia Planas, Elsa Pastor, LLoyd Queen, Mario M. Valero
Přispěvatelé: Universitat Politècnica de Catalunya. Departament d'Enginyeria de Sistemes, Automàtica i Informàtica Industrial, Universitat Politècnica de Catalunya. Departament d'Enginyeria Química, Universitat Politècnica de Catalunya. CERTEC - Centre d'Estudis del Risc Tecnològic
Jazyk: angličtina
Rok vydání: 2020
Předmět:
Teledetecció
Computer science
0211 other engineering and technologies
02 engineering and technology
Aerial video
Image similarity
video stabilization
ENERGY
remote sensing
sensitivity analysis
Incendis
Computer vision
SATELLITE
Image registration
MAXIMIZATION
image similarity
04 agricultural and veterinary sciences
Mutual information
Remote sensing
Metric (mathematics)
REGISTRATION
SENSITIVITY
Sensitivity analysis
Normalization (statistics)
Technology and Engineering
AIRBORNE
Science
Infrared imagery
FIRE RADIATIVE
REMOTE-SENSING TECHNIQUES
Enginyeria química [Àrees temàtiques de la UPC]
Similarity (network science)
Motion estimation
OPTIMIZATION
021101 geological & geomatics engineering
040101 forestry
Video stabilization
business.industry
NORMALIZED MUTUAL INFORMATION
PERFORMANCE
infrared imagery
Image stabilization
image registration
0401 agriculture
forestry
and fisheries
General Earth and Planetary Sciences
Artificial intelligence
Wildland fire
business
wildland fire
Zdroj: Remote Sensing, Vol 12, Iss 3, p 540 (2020)
Remote Sensing
Volume 12
Issue 3
Pages: 540
REMOTE SENSING
r-FSJD. Repositorio Institucional de Producción Científica de la Fundació Sant Joan de Déu
Universidad de las Islas Baleares
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
ISSN: 2072-4292
Popis: Aerial Thermal Infrared (TIR) imagery has demonstrated tremendous potential to monitor active forest fires and acquire detailed information about fire behavior. However, aerial video is usually unstable and requires inter-frame registration before further processing. Measurement of image misalignment is an essential operation for video stabilization. Misalignment can usually be estimated through image similarity, although image similarity metrics are also sensitive to other factors such as changes in the scene and lighting conditions. Therefore, this article presents a thorough analysis of image similarity measurement techniques useful for inter-frame registration in wildfire thermal video. Image similarity metrics most commonly and successfully employed in other fields were surveyed, adapted, benchmarked and compared. We investigated their response to different camera movement components as well as recording frequency and natural variations in fire, background and ambient conditions. The study was conducted in real video from six fire experimental scenarios, ranging from laboratory tests to large-scale controlled burns. Both Global and Local Sensitivity Analyses (GSA and LSA, respectively) were performed using state-of-the-art techniques. Based on the obtained results, two different similarity metrics are proposed to satisfy two different needs. A normalized version of Mutual Information is recommended as cost function during registration, whereas 2D correlation performed the best as quality control metric after registration. These results provide a sound basis for image alignment measurement and open the door to further developments in image registration, motion estimation and video stabilization for aerial monitoring of active wildland fires.
Databáze: OpenAIRE
Externí odkaz: