Abstract: Current CNN-based stereo depth estimation models can barely run under real-time
constraints on embedded graphic processing unit (GPU) devices. Moreover, state-of-the-art
evaluations usually do not consider model optimization techniques, being that it is unknown what is
the current potential on embedded GPU devices. In this work, we evaluate two state-of-the-art models
on three different embedded GPU devices, with and without optimization methods, presenting
performance results that illustrate the actual capabilities of embedded GPU devices for stereo depth
estimation. More importantly, based on our evaluation, we propose the use of a U-Net like architecture
for postprocessing the cost-volume, instead of a typical sequence of 3D convolutions, drastically
augmenting the runtime speed of current models. In our experiments, we achieve real-time inference
speed, in the range of 5–32 ms, for 1216  368 input stereo images on the Jetson TX2, Jetson Xavier,
and Jetson Nano embedded devices.

Abstract: This paper evaluates different wavelet-based cross-spectral image fusion strategies adopted to merge visible and infrared images. The objective is to find the best setup independently of the evaluation metric used to measure the performance. Quantitative performance results are obtained with state of the art approaches together with adaptations proposed in the current work. The options evaluated in the current work result from the combination of different setups in the wavelet image decomposition stage together with different fusion strategies for the final merging stage that generates the resulting representation. Most of the approaches evaluate results according to the application for which they are intended for. Sometimes a human observer is selected to judge the quality of the obtained results. In the current work, quantitative values are considered in order to find correlations between setups and performance of obtained results; these correlations can be used to define a criteria for selecting the best fusion strategy for a given pair of cross-spectral images. The whole procedure is evaluated with a large set of correctly registered visible and infrared image pairs, including both Near InfraRed (NIR) and LongWave InfraRed (LWIR).

Abstract: In gamification, the development of "visual metrics for educational
video games linked to social assistance robots in the framework of inclusive education" seeks to provide support, not only to regular children but also to children with specific psychosocial disabilities, such as those diagnosed with autism spectrum disorder (ASD). However, personalizing each child's experiences represents a limitation, especially for those with atypical behaviors. 'LOLY,' a social assistance robot, works together with mobile applications associated with the family of educational video game series called 'MIDI-AM,' forming a social robotic platform. This platform offers the user curricular digital content to reinforce the teaching-learning processes and motivate regular children and those with ASD. In the present study, technical, programmatic experiments and focus groups were carried out, using open-source facial recognition algorithms to monitor and evaluate the degree of user attention throughout the interaction. The objective is to evaluate the management of a social robot linked to educational video games
through established metrics, which allow monitoring the user's facial expressions
during its use and define a scenario that ensures consistency in the results for its applicability in therapies and reinforcement in the teaching process, mainly
adaptable for inclusive early childhood education.

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.

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.