Enhancing Obscured Regions in Thermal Imaging: A Novel GAN-Based Approach for Efficient Occlusion Inpainting

Mohammed Abuhussein (), Iyad Almadani, Aaron L. Robinson and Mohammed Younis
Additional contact information
Mohammed Abuhussein: Department of Electrical and Computer Engineering, Herff College of Engineering, University of Memphis, 3817 Central Ave, Memphis, TN 38111, USA
Iyad Almadani: Department of Electrical and Computer Engineering, Herff College of Engineering, University of Memphis, 3817 Central Ave, Memphis, TN 38111, USA
Aaron L. Robinson: Department of Electrical and Computer Engineering, Herff College of Engineering, University of Memphis, 3817 Central Ave, Memphis, TN 38111, USA
Mohammed Younis: Department of Electrical and Computer Engineering, Herff College of Engineering, University of Memphis, 3817 Central Ave, Memphis, TN 38111, USA

J, 2024, vol. 7, issue 3, 1-18

Abstract: This research paper presents a novel approach for occlusion inpainting in thermal images to efficiently segment and enhance obscured regions within these images. The increasing reliance on thermal imaging in fields like surveillance, security, and defense necessitates the accurate detection of obscurants such as smoke and fog. Traditional methods often struggle with these complexities, leading to the need for more advanced solutions. Our proposed methodology uses a Generative Adversarial Network (GAN) to fill occluded areas in thermal images. This process begins with an obscured region segmentation, followed by a GAN-based pixel replacement in these areas. The methodology encompasses building, training, evaluating, and optimizing the model to ensure swift real-time performance. One of the key challenges in thermal imaging is identifying effective strategies to mitigate critical information loss due to atmospheric interference. Our approach addresses this by employing sophisticated deep-learning techniques. These techniques segment, classify and inpaint these obscured regions in a patch-wise manner, allowing for more precise and accurate image restoration. We propose utilizing architectures similar to Pix2Pix and UNet networks for generative and segmentation tasks. These networks are known for their effectiveness in image-to-image translation and segmentation tasks. Our method enhances the segmentation and inpainting process by leveraging their architectural similarities. To validate our approach, we provide a quantitative analysis and performance comparison. We include a quantitative comparison between (Pix2Pix and UNet) and our combined architecture. The comparison focuses on how well each model performs in terms of accuracy and speed, highlighting the advantages of our integrated approach. This research contributes to advancing thermal imaging techniques, offering a more robust solution for dealing with obscured regions. The integration of advanced deep learning models holds the potential to significantly improve image analysis in critical applications like surveillance and security.

Keywords: thermal; LWIR; inpainting; GANs; segmentation; occlusion (search for similar items in EconPapers)
JEL-codes: I1 I10 I12 I13 I14 I18 I19 (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2571-8800/7/3/13/pdf (application/pdf)
https://www.mdpi.com/2571-8800/7/3/13/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jjopen:v:7:y:2024:i:3:p:13-235:d:1423364

Access Statistics for this article

J is currently edited by Ms. Angelia Su

More articles in J from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().