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: The simultaneous use of images from different spectra can be helpful to improve the performance of many com- puter vision tasks. The core idea behind the usage of cross- spectral approaches is to take advantage of the strengths of each spectral band providing a richer representation of a scene, which cannot be obtained with just images from one spectral band. In this work we tackle the cross-spectral image similarity problem by using Convolutional Neural Networks (CNNs). We explore three different CNN archi- tectures to compare the similarity of cross-spectral image patches. Specifically, we train each network with images from the visible and the near-infrared spectrum, and then test the result with two public cross-spectral datasets. Ex- perimental results show that CNN approaches outperform the current state-of-art on both cross-spectral datasets. Ad- ditionally, our experiments show that some CNN architec- tures are capable of generalizing between different cross- spectral domains.

Abstract: This paper presents a novel model to estimate human activities – a human activity is defined by a set of human actions. The proposed approach is based on the usage of Recurrent Neural Networks (RNN) and Bayesian inference through the continuous monitoring of human actions and its surrounding environment. In the current work human activities are inferred considering not only visual analysis but also additional resources; external sources of information, such as context information, are incorporated to contribute to the activity estimation. The novelty of the proposed approach lies in the way the information is encoded, so that it can be later associated according to a predefined semantic structure. Hence, a pattern representing a given activity can be defined by a set of actions, plus contextual information or other kind of information that could be relevant to describe the activity. Experimental results with real data are provided showing the validity of the proposed approach.