Douglas Damiao de Carvalho Honorio

@ieav.cta.br

Brazilian Department of Science and Aerospace Technology
Institute for Advanced Studies

Douglas Damiao de Carvalho Honorio


                  Download Compact PDF  
https://researchid.co/douglashonorio

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Vision and Pattern Recognition, Artificial Intelligence, Computers in Earth Sciences
3

Scopus Publications

Scopus Publications

  • A Hybrid Approach for Target Discrimination in Remote Sensing: Combining YOLO and CNN-Based Classifiers
    Jamesson Lira Silva, Fabiano da Cruz Nogueira, Douglas Damião de Carvalho Honório, Elcio Hideiti Shiguemori, Angelo Passaro
    Journal of Aerospace Technology and Management, 2024
    With the increase in image production in recent years, there has been significant progress in the application of deep learning algorithms across various domains. Convolutional neural networks (CNNs) have been increasingly employed in remote sensing, covering all stages of target discrimination according to Johnson’s criteria (detection, recognition, and identification). These CNNs are applied in many conditions and imagery from many types of sensors. In this study, we explored the use of the YOLO-v8 method, the latest version of the You Only Look Once (YOLO) family of object detection models, in conjunction with CNN architectures and supervised learning algorithms. This approach was applied to detect, recognize, and identify targets in videos captured by optical sensors, considering varying resolutions and conditions. Additionally, our research investigated the use of two CNN architectures, Inception-v3 and VGG-16, to extract relevant information from the images. The attributes obtained from the CNNs were used as input for three classification algorithms: multilayer perceptron (MLP), logistic regression, and support vector machine (SVM), thereby completing the target discrimination process. It is worth noting that in the combination of Inception-v3 and MLP, we achieved an average accuracy of 90.67%, thus completing the target discrimination process.
  • Comparison of Feature Extraction and Matching Techniques Applied to Monocular UAV Images With Low-quality and Land Cover Variations
    Nathan A. Z. Xavier, Jonathan De A. Lapa, Douglas D. De C. Honório, Rafael C. De Oliveira, Elcio H. Shiguemori, Marcos R. O. A. Maximo, Marco A. P. Domiciano
    Proceedings 2023 Latin American Robotics Symposium 2023 Brazilian Symposium on Robotics and 2023 Workshop of Robotics in Education LARS Sbr Wre 2023, 2023
    Extracting features from images is a recurring task in applications highly dependent on cameras, mainly on UAV visual navigation. By using sequential images, on different land covers and low-quality images, variable performance is expected based on both modification characteristics. This study applies the techniques GFTT, SIFT, MSER, FAST, BRISK, ORB, AKAZE, and SuperGlue on the dataset KDD-BR 2022, which contains multiple UAV images of various land covers and low-quality images. The performance of each technique on feature extracting and matching is presented while verifying the methods that better generalize this process.
  • Performance of Speckle Filters for COSMO-SkyMed Images from the Brazilian Amazon
    Tahisa N. Kuck, Luis D. Gomez, Edson E. Sano, Polyanna da C. Bispo, Douglas D. C. Honorio
    IEEE Geoscience and Remote Sensing Letters, 2022
    Speckle filtering is an important step for target detection in SAR images since this effect makes it difficult or even impossible to extract information from these images. There are several filters available in the literature although evaluating their performances is not a trivial task since it requires comparing the filtered images with a speckle-free image, which is generally unknown. This evaluation is even more complex when the features in the images are heterogeneous, for example, from tropical forests. The objective of this study is to evaluate the performance of the Lee, deGrandi, GammaMAP, single Anisotropic Nonlinear Diffusion (ANLD), multitemporal ANLD, Fast Adaptive Nonlocal SAR (FANS), and Fast GPU-Based Enhanced Wiener filters to reduce the speckle present in the COSMO-SkyMed Stripmap X-band images from the Brazilian Amazon forest region. The evaluation was conducted qualitatively through the visual inspection of the ratio image and the edge detection in the ratio images and quantitatively through the $\\alpha \\beta $ estimator and other statistical parameters of the filtered images. The GammaMAP filter showed the best performances, both qualitatively and quantitatively, and the FANS filter only qualitative.