%0 Conference Proceedings
%T Object Detection in Very Low-Resolution Thermal Images through a Guided-Based Super-Resolution Approach
%A Rafael E. Rivadeneira
%A Henry Velesaca
%A Angel Sappa
%B 17th International Conference on Signal-Image Technology & Internet-Based Systems
%D 2023
%F Rafael E. Rivadeneira2023
%O MSIAU
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=4010), last updated on Mon, 10 Jun 2024 12:21:22 +0200
%X This work proposes a novel approach that integrates super-resolution techniques with off-the-shelf object detection methods to tackle the problem of handling very low-resolution thermal images. The suggested approach begins by enhancing the low-resolution (LR) thermal images through a guided super-resolution strategy, leveraging a high-resolution (HR) visible spectrum image. Subsequently, object detection is performed on the high-resolution thermal image. The experimental results demonstrate tremendous improvements in comparison with both scenarios: when object detection is performed on the LR thermal image alone, as well as when object detection is conducted on the up-sampled LR thermal image. Moreover, the proposed approach proves highly valuable in camouflaged scenarios where objects might remain undetected in visible spectrum images.
%U https://ieeexplore.ieee.org/document/10472816
%U http://dx.doi.org/10.1109/SITIS61268.2023.00056