|
Rafael E. Rivadeneira, A. D. S., Boris X. Vintimilla, Chenyang Wang, Junjun Jiang, Xianming Liu, Zhiwei Zhong, Dai Bin, Li Ruodi, Li Shengye. (2023). Thermal Image Super-Resolution Challenge Results – PBVS 2023. In 19th IEEE Workshop on Perception Beyond the Visible Spectrum de la Conferencia Computer Vision & Pattern Recognition CVPR 2023, junio 18-28 (Vol. 2023-June, pp. 470–478).
|
|
|
Jorge L. Charco, Angel D. Sappa, Boris X. Vintimilla, & Henry O. Velesaca. (2020). Transfer Learning from Synthetic Data in the Camera Pose Estimation Problem. In The 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020); Valletta, Malta; 27-29 Febrero 2020 (Vol. 4, pp. 498–505).
Abstract: This paper presents a novel Siamese network architecture, as a variant of Resnet-50, to estimate the relative camera pose on multi-view environments. In order to improve the performance of the proposed model
a transfer learning strategy, based on synthetic images obtained from a virtual-world, is considered. The
transfer learning consist of first training the network using pairs of images from the virtual-world scenario
considering different conditions (i.e., weather, illumination, objects, buildings, etc.); then, the learned weight
of the network are transferred to the real case, where images from real-world scenarios are considered. Experimental results and comparisons with the state of the art show both, improvements on the relative pose
estimation accuracy using the proposed model, as well as further improvements when the transfer learning
strategy (synthetic-world data – transfer learning – real-world data) is considered to tackle the limitation on
the training due to the reduced number of pairs of real-images on most of the public data sets.
|
|
|
Rafael E. Rivadeneira, Angel D. Sappa, & Boris X. Vintimilla. (2020). Thermal Image Super-Resolution: a Novel Architecture and Dataset. In The 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020); Valletta, Malta; 27-29 Febrero 2020 (Vol. 4, pp. 111–119).
Abstract: This paper proposes a novel CycleGAN architecture for thermal image super-resolution, together with a large
dataset consisting of thermal images at different resolutions. The dataset has been acquired using three thermal
cameras at different resolutions, which acquire images from the same scenario at the same time. The thermal
cameras are mounted in rig trying to minimize the baseline distance to make easier the registration problem.
The proposed architecture is based on ResNet6 as a Generator and PatchGAN as Discriminator. The novelty
on the proposed unsupervised super-resolution training (CycleGAN) is possible due to the existence of aforementioned thermal images—images of the same scenario with different resolutions. The proposed approach
is evaluated in the dataset and compared with classical bicubic interpolation. The dataset and the network are
available.
|
|
|
Rafael E. Rivadeneira, Angel D. Sappa, Boris X. Vintimilla, Lin Guo, Jiankun Hou, Armin Mehri, et al. (2020). Thermal Image Super-Resolution Challenge – PBVS 2020. In The 16th IEEE Workshop on Perception Beyond the Visible Spectrum on the Conference on Computer Vision and Pattern Recongnition (CVPR 2020) (Vol. 2020-June, pp. 432–439).
Abstract: This paper summarizes the top contributions to the first challenge on thermal image super-resolution (TISR) which was organized as part of the Perception Beyond the Visible Spectrum (PBVS) 2020 workshop. In this challenge, a novel thermal image dataset is considered together with stateof-the-art approaches evaluated under a common framework.
The dataset used in the challenge consists of 1021 thermal images, obtained from three distinct thermal cameras at different resolutions (low-resolution, mid-resolution, and high-resolution), resulting in a total of 3063 thermal images. From each resolution, 951 images are used for training and 50 for testing while the 20 remaining images are used for two proposed evaluations. The first evaluation consists of downsampling the low-resolution, midresolution, and high-resolution thermal images by x2, x3 and x4 respectively, and comparing their super-resolution
results with the corresponding ground truth images. The second evaluation is comprised of obtaining the x2 superresolution from a given mid-resolution thermal image and comparing it with the corresponding semi-registered highresolution thermal image. Out of 51 registered participants, 6 teams reached the final validation phase.
|
|
|
Patricia L. Suarez, Angel D. Sappa, & Boris X. Vintimilla. (2017). Colorizing Infrared Images through a Triplet Condictional DCGAN Architecture. In 19th International Conference on Image Analysis and Processing. (pp. 287–297).
|
|
|
Patricia L. Suarez, Angel D. Sappa, & Boris X. Vintimilla. (2017). Learning Image Vegetation Index through a Conditional Generative Adversarial Network. In 2nd IEEE Ecuador Tehcnnical Chapters Meeting (ETCM).
|
|
|
Milton Mendieta, F. Panchana, B. Andrade, B. Bayot, C. Vaca, Boris X. Vintimilla, et al. (2018). Organ identification on shrimp histological images: A comparative study considering CNN and feature engineering. In IEEE Ecuador Technical Chapters Meeting ETCM 2018. Cuenca, Ecuador (pp. 1–6).
Abstract: The identification of shrimp organs in biology using
histological images is a complex task. Shrimp histological images
poses a big challenge due to their texture and similarity among
classes. Image classification by using feature engineering and
convolutional neural networks (CNN) are suitable methods to
assist biologists when performing organ detection. This work
evaluates the Bag-of-Visual-Words (BOVW) and Pyramid-Bagof-
Words (PBOW) models for image classification leveraging big
data techniques; and transfer learning for the same classification
task by using a pre-trained CNN. A comparative analysis
of these two different techniques is performed, highlighting
the characteristics of both approaches on the shrimp organs
identification problem.
|
|
|
Patricia L. Suarez, Angel D. Sappa, Boris X. Vintimilla, & Riad I. Hammoud. (2018). Deep Learning based Single Image Dehazing. In 14th IEEE Workshop on Perception Beyond the Visible Spectrum – In conjunction with CVPR 2018. Salt Lake City, Utah. USA.
Abstract: This paper proposes a novel approach to remove haze
degradations in RGB images using a stacked conditional
Generative Adversarial Network (GAN). It employs a triplet
of GAN to remove the haze on each color channel independently.
A multiple loss functions scheme, applied over a
conditional probabilistic model, is proposed. The proposed
GAN architecture learns to remove the haze, using as conditioned
entrance, the images with haze from which the clear
images will be obtained. Such formulation ensures a fast
model training convergence and a homogeneous model generalization.
Experiments showed that the proposed method
generates high-quality clear images.
|
|
|
Patricia L. Suarez, Angel D. Sappa, & Boris X. Vintimilla. (2018). Vegetation Index Estimation from Monospectral Images. In 15th International Conference, Image Analysis and Recognition (ICIAR 2018), Póvoa de Varzim, Portugal. Lecture Notes in Computer Science (Vol. 10882, pp. 353–362).
Abstract: This paper proposes a novel approach to estimate Normalized
Difference Vegetation Index (NDVI) from just the red channel of
a RGB image. The NDVI index is defined as the ratio of the difference
of the red and infrared radiances over their sum. In other words, information
from the red channel of a RGB image and the corresponding
infrared spectral band are required for its computation. In the current
work the NDVI index is estimated just from the red channel by training a
Conditional Generative Adversarial Network (CGAN). The architecture
proposed for the generative network consists of a single level structure,
which combines at the final layer results from convolutional operations
together with the given red channel with Gaussian noise to enhance
details, resulting in a sharp NDVI image. Then, the discriminative model
estimates the probability that the NDVI generated index came from the
training dataset, rather than the index automatically generated. Experimental
results with a large set of real images are provided showing that
a Conditional GAN single level model represents an acceptable approach
to estimate NDVI index.
|
|
|
Patricia L. Suarez, Angel D. Sappa, Boris X. Vintimilla, & Riad I. Hammoud. (2018). Near InfraRed Imagery Colorization. In 25 th IEEE International Conference on Image Processing, ICIP 2018 (pp. 2237–2241).
Abstract: This paper proposes a stacked conditional Generative
Adversarial Network-based method for Near InfraRed
(NIR) imagery colorization. We propose a variant architecture
of Generative Adversarial Network (GAN) that uses multiple
loss functions over a conditional probabilistic generative model.
We show that this new architecture/loss-function yields better
generalization and representation of the generated colored IR
images. The proposed approach is evaluated on a large test
dataset and compared to recent state of the art methods using
standard metrics.1
Index Terms—Convolutional Neural Networks (CNN), Generative
Adversarial Network (GAN), Infrared Imagery colorization.
|
|