sensors-logo

Journal Browser

Journal Browser

Advances in Infrared Imaging: Sensing, Exploitation and Applications 2021-2022

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensing and Imaging".

Deadline for manuscript submissions: closed (14 April 2023) | Viewed by 8842

Special Issue Editors


E-Mail Website
Guest Editor
Computer Vision Center, Campus UAB, 08193 Bellaterra, Spain
Interests: multispectral imaging; 2D / 3D images and model registration; fast 3D scene flow estimation; modeling dynamic environments using adaptive gridmaps; multimodal stereo systems; implicit functions for object representations; cross-spectral image segmentation

Website
Guest Editor
BAE Systems, Burlington, MA 01803, USA
Interests: video and image understanding, exploitation and analytics (object detection, tracking, feature extraction, recognition, geo/registration, multi-camera activity pattern modeling and recognition, multi-sensory data fusion, text mining and fusion with video data; automatic target recognition, etc.); ground/aerial/underwater robotics (assisted perception, supervised tele-autonomy, autonomous navigation), geo-localization and big data analytics (content/feature extraction, topic modeling, indexing, matching); machine learning (classification and clustering, pattern learning, and deep learning)

Special Issue Information

Dear Colleagues,

The number of infrared image applications has been growing considerably over the last few decades; this evolution is mainly motivated by the appearance of new devices, as well as the reduction in the price of technology. Today, infrared-based devices can be found in domains that range from medical applications to computer games or industrial solutions. Infrared images are divided into different categories, including near infrared (NIR), short-wave infrared (SWIR), mid-wave infrared (MWIR) and long-wave infrared (LWIR). Images from each one of these subcategories have their own characteristics that make them attractive to specific applications. It should be noted that these characteristics are not only used to develop new applications, but also to improve the appearance of the corresponding VS image in case it is available, for instance, in noise filtering, image enhancement, and dehazing. In other words, infrared imaging is becoming a solid source of additional information for a wide range of applications.

This Special Issue is intended to review the state of the art on infrared imaging, from image acquisition to processing, and understanding of all the infrared spectra. The following infrared imaging topics will be covered, but this Special Issue is not limited to only these topics:

  • Imaging systems (NIR/SWIR/MWIR/LWIR);
  • Processing (filtering, coloring, feature extraction, and matching);
  • Representation (fusion, thermal mapping);
  • Understanding (machine learning, pattern recognition);
  • Deep/transfer learning, domain adaptation;
  • Vision-aided navigation;
  • Sensing for agriculture and food safety;
  • Autonomous driving;
  • Thermal image applications;
  • Remote sensing

Prof. Dr. Angel D. Sappa
Dr. Riad Hammoud
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (3 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

21 pages, 7827 KiB  
Article
Learning-Based Near-Infrared Band Simulation with Applications on Large-Scale Landcover Classification
by Xiangtian Yuan, Jiaojiao Tian and Peter Reinartz
Sensors 2023, 23(9), 4179; https://doi.org/10.3390/s23094179 - 22 Apr 2023
Cited by 1 | Viewed by 2632
Abstract
Multispectral sensors are important instruments for Earth observation. In remote sensing applications, the near-infrared (NIR) band, together with the visible spectrum (RGB), provide abundant information about ground objects. However, the NIR band is typically not available on low-cost camera systems, which presents challenges [...] Read more.
Multispectral sensors are important instruments for Earth observation. In remote sensing applications, the near-infrared (NIR) band, together with the visible spectrum (RGB), provide abundant information about ground objects. However, the NIR band is typically not available on low-cost camera systems, which presents challenges for the vegetation extraction. To this end, this paper presents a conditional generative adversarial network (cGAN) method to simulate the NIR band from RGB bands of Sentinel-2 multispectral data. We adapt a robust loss function and a structural similarity index loss (SSIM) in addition to the GAN loss to improve the model performance. With 45,529 multi-seasonal test images across the globe, the simulated NIR band had a mean absolute error of 0.02378 and an SSIM of 89.98%. A rule-based landcover classification using the simulated normalized difference vegetation index (NDVI) achieved a Jaccard score of 89.50%. The evaluation metrics demonstrated the versatility of the learning-based paradigm in remote sensing applications. Our simulation approach is flexible and can be easily adapted to other spectral bands. Full article
Show Figures

Figure 1

15 pages, 6937 KiB  
Article
The Influence of Optical Alignment Error on Compression Coding Superresolution Imaging
by Chao Wang, Siyuan Xing, Miao Xu, Haodong Shi, Xingkai Wu, Qiang Fu and Huilin Jiang
Sensors 2022, 22(7), 2717; https://doi.org/10.3390/s22072717 - 1 Apr 2022
Cited by 3 | Viewed by 2180
Abstract
Superresolution (SR) imaging technology based on compression coding has always been considered as the key to break through the geometric resolution of the detector. In addition to factors such as the reconstruction algorithm and mounting platform vibrations, the impact of inherent errors in [...] Read more.
Superresolution (SR) imaging technology based on compression coding has always been considered as the key to break through the geometric resolution of the detector. In addition to factors such as the reconstruction algorithm and mounting platform vibrations, the impact of inherent errors in the optical system itself on the reconstruction results of SR imaging is also obvious. To address this issue, a study on the design of the SR optical system and the influence of optical alignment errors on SR imaging was conducted. The design of the SR optical system based on digital micro-mirror device (DMD) for long-wave infrared wavelength was completed, and an athermal analysis of the system was carried out. The design results showed that the SR optical system has good imaging quality in the operating temperature range. The imaging model of the DMD SR imaging optical system is established according to the designed SR optical system. We investigated the influence of various alignment errors, including decenter, tilt, lens interval error and defocus, on the imaging properties of the SR optical system. Various random combinations of alignment errors were introduced into the optical system, respectively, and the SR reconstructed image quality of the imaging system was analyzed using the inverse sensitivity method to obtain the tolerance limits when the system was assembled. Finally, the effectiveness of the method to obtain the alignment tolerance limit of the compression coding SR imaging optical system was verified through a desktop demonstration experiment. Full article
Show Figures

Figure 1

14 pages, 1104 KiB  
Article
A Novel Domain Transfer-Based Approach for Unsupervised Thermal Image Super-Resolution
by Rafael E. Rivadeneira, Angel D. Sappa, Boris X. Vintimilla and Riad Hammoud
Sensors 2022, 22(6), 2254; https://doi.org/10.3390/s22062254 - 14 Mar 2022
Cited by 6 | Viewed by 3120
Abstract
This paper presents a transfer domain strategy to tackle the limitations of low-resolution thermal sensors and generate higher-resolution images of reasonable quality. The proposed technique employs a CycleGAN architecture and uses a ResNet as an encoder in the generator along with an attention [...] Read more.
This paper presents a transfer domain strategy to tackle the limitations of low-resolution thermal sensors and generate higher-resolution images of reasonable quality. The proposed technique employs a CycleGAN architecture and uses a ResNet as an encoder in the generator along with an attention module and a novel loss function. The network is trained on a multi-resolution thermal image dataset acquired with three different thermal sensors. Results report better performance benchmarking results on the 2nd CVPR-PBVS-2021 thermal image super-resolution challenge than state-of-the-art methods. The code of this work is available online. Full article
Show Figures

Figure 1

Back to TopTop