arXiv subjects

Oscar H. Ramírez-Agudelo

Publications and source records attributed to Oscar H. Ramírez-Agudelo.

3 recordsLinked to original sources

arXiv2026

Enhancing the quality of gauge images captured in smoke and haze scenes through deep learning

Images captured in hazy and smoky environments suffer from reduced visibility, posing a challenge when monitoring infrastructures and hindering emergency services during critical situations. The proposed work investigates the use of the deep learning models to enhance the automatic, machine-based readability of gauge in smoky environments, with accurate gauge data interpretation serving as a valuable tool for first responders. The study utilizes two deep learning architectures, FFA-Net and AECR-Net, to improve the visibility of gauge images, corrupted with light up to dense haze and smoke. Since benchmark datasets of analog gauge images are unavailable, a new synthetic dataset, containing over 14,000 images, was generated using the Unreal Engine. The models were trained with an 80\% train, 10\% validation, and 10\% test split for the haze and smoke dataset, respectively. For the synthetic haze dataset, the SSIM and PSNR metrics are about 0.98 and 43\,dB, respectively, comparing well to state-of-the art results. Additionally, more robust results are retrieved from the AECR-Net, when compared to the FFA-Net. Although the results from the synthetic smoke dataset are poorer, the trained models achieve interesting results. In general, imaging in the presence of smoke are more difficult to enhance given the inhomogeneity and high density. Secondly, FFA-Net and AECR-Net are implemented to dehaze and not to desmoke images. This work shows that use of deep learning architectures can improve the quality of analog gauge images captured in smoke and haze scenes immensely. Finally, the enhanced output images can be successfully post-processed for automatic autonomous reading of gauges

cs.CV↗

arXiv2026

The Role of Noisy Data in Improving CNN Robustness for Image Classification

Data quality plays a central role in the performance and robustness of convolutional neural networks (CNNs) for image classification. While high-quality data is often preferred for training, real-world inputs are frequently affected by noise and other distortions. This paper investigates the effect of deliberately introducing controlled noise into the training data to improve model robustness. Using the CIFAR-10 dataset, we evaluate the impact of three common corruptions, namely Gaussian noise, Salt-and-Pepper noise, and Gaussian blur at varying intensities and training set pollution levels. Experiments using a Resnet-18 model reveal that incorporating just 10\% noisy data during training is sufficient to significantly reduce test loss and enhance accuracy under fully corrupted test conditions, with minimal impact on clean-data performance. These findings suggest that strategic exposure to noise can act as a simple yet effective regularizer, offering a practical trade-off between traditional data cleanliness and real-world resilience.

cs.CV↗

arXiv2017

Massive pre-main sequence stars in M17

The formation process of massive stars is still poorly understood. Massive young stellar objects (mYSOs) are deeply embedded in their parental clouds, they are rare and thus typically distant, and their reddened spectra usually preclude the determination of their photospheric parameters. M17 is one of the best studied HII regions in the sky, is relatively nearby, and hosts a young stellar population. With X-shooter on the ESO Very Large Telescope we have obtained optical to near-infrared spectra of candidate mYSOs, identified by Hanson et al. (1997), and a few OB stars in this region. The large wavelength coverage enables a detailed spectroscopic analysis of their photospheres and circumstellar disks. We confirm the pre-main sequence (PMS) nature of six of the stars and characterise the O stars. The PMS stars have radii consistent with being contracting towards the main sequence and are surrounded by a remnant accretion disk. The observed infrared excess and the (double-peaked) emission lines provide the opportunity to measure structured velocity profiles in the disks. We compare the observed properties of this unique sample of young massive stars with evolutionary tracks of massive protostars by Hosokawa & Omukai (2009), and propose that these mYSOs near the western edge of the HII region are on their way to become main-sequence stars ($\sim 6 - 20$ $M_{\odot}$) after having undergone high mass-accretion rates (${\dot{M}_{\rm acc}} \sim 10^{-4} - 10^{-3}$ $M_{\odot}$ $\rm yr^{-1}$). Their spin distribution upon arrival at the zero age main sequence (ZAMS) is consistent with that observed for young B stars, assuming conservation of angular momentum and homologous contraction.

astro-ph.SR↗