Maritime surveillance systems employing thermal imaging encounter numerous challenges, where image quality significantly affects their effective range of vision. Adverse weather conditions such as haze, fog, and smog can obscure thermal imaging scenes, complicating the detection, identification, and tracking of objects of interest. For instance, these systems must track moving ships from a considerable distance using thermal imaging, while adapting to dynamic backgrounds and various weather conditions. Image quality assessment, a crucial research area, evaluates the perceived quality of an image. Standards for quantifying images often align with human perception, adopting user-focused approaches that consider an observer's ability to perform specific tasks, as outlined in the Johnson criteria. However, in real-time maritime surveillance applications, these criteria may prove inadequate in capturing image properties. This study explores the general factors that measure the dynamic range of marine surveillance thermal images, along with specific challenges in interpreting images using various quality assessment parameters.
Unmanned Aerial Vehicles (UAVs) are gaining more popularity for various applications such as surveillance, monitoring and mapping. However, navigating UAVs in low-features areas or GPS-denied areas poses a significant challenge, as conventional GPS-based method for estimating velocity become ineffective. Optical flow algorithms have become a promising approach for UAV velocity estimation in such scenarios. This paper proposes a novel method for UAV velocity estimation for a vision-based navigation system in GPS-denied low-features environments. The proposed method is evaluated and compared to various optical flow methods considering computational efficiency, accuracy, and robustness when predicting UAV velocity. Understanding the strengths and limitations of these optical flow methods will certainly enable the development and implementation of UAV navigation systems in challenging environments.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.