Search results for "020207 software engineering"
showing 10 items of 475 documents
Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks
2016
This paper proposes Markovian Generative Adversarial Networks (MGANs), a method for training generative networks for efficient texture synthesis. While deep neural network approaches have recently demonstrated remarkable results in terms of synthesis quality, they still come at considerable computational costs (minutes of run-time for low-res images). Our paper addresses this efficiency issue. Instead of a numerical deconvolution in previous work, we precompute a feed-forward, strided convolutional network that captures the feature statistics of Markovian patches and is able to directly generate outputs of arbitrary dimensions. Such network can directly decode brown noise to realistic textu…
An FPGA-based design for real-time Super Resolution Reconstruction
2018
Since several decades, the camera spatial resolution is gradually increasing with the CMOS technology evolution. The image sensors provide more and more pixels, generating new constraints for the suitable optics. As an alternative, promising solutions propose Super Resolution (SR) image reconstruction to extend the image size without modifying the sensor architecture. Convincing state-of art studies demonstrate that these methods could even be implemented in real-time. Nevertheless, artifacts can be observed in highly textured areas of the image. In this paper, we propose a Local Adaptive Spatial Super Resolution (LASSR) method to fix this limitation. A real-time texture analysis is include…
Meta-Tracking for Video Scene Understanding
2013
International audience; This paper presents a novel method to extract dominant motion patterns (MPs) and the main entry/exit areas from a surveillance video. The method first computes motion histograms for each pixel and then converts it into orientation distribution functions (ODFs). Given these ODFs, a novel particle meta-tracking procedure is launched which produces meta-tracks, i.e. particle trajectories. As opposed to conventional tracking which focuses on individual moving objects, meta-tracking uses particles to follow the dominant flow of the traffic. In a last step, a novel method is used to simultaneously identify the main entry/exit areas and recover the predominant MPs. The meta…
A spectral hazy image database
2020
We introduce a new database to promote visibility enhancement techniques intended for spectral image dehazing. SHIA (Spectral Hazy Image database for Assessment) is composed of two real indoor scenes M1 and M2 of 10 levels of fog each and their corresponding fog-free (ground-truth) images, taken in the visible and the near infrared ranges every 10 nm starting from 450 to 1000 nm. The number of images that form SHIA is 1540 with a size of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$1312\,\times \,1082$$\end{d…
Usability of Programming Languages
2016
Programming languages form the interface between programmers (the users) and the computation that they desire the computer to execute. Although studies exist for some aspects of programming language design (such as conditionals), other aspects have received little or no human factors evaluations. Designers thus have little they can rely on if they want to make new languages highly usable, and users cannot easily chose a language based on usability criteria. This SIG will bring together researchers and practitioners interested in increasing the depth and breadth of studies on the usability of programming languages, and ultimately in improving the usability of future languages. nonPeerReviewed
A wearable multimodal interface for exploring urban points of interest
2015
Locating points of interest (POIs) in cities is typically facilitated by visual aids such as paper maps, brochures, and mobile applications. However, these techniques require visual attention, which ideally should be on the surroundings. Non-visual techniques for navigating towards specific POIs typically lack support for free exploration of the city or more detailed guidance. To overcome these issues, we propose a multimodal, wearable system for alerting the user of nearby recommended POIs. The system, built around a tactile glove, provides audio-tactile cues when a new POI is in the vicinity, and more detailed information and guidance if the user expresses interest in this POI. We evaluat…
A New Set of Quartic Trivariate Polynomial Equations for Stratified Camera Self-calibration under Zero-Skew and Constant Parameters Assumptions
2012
This paper deals with the problem of self-calibrating a moving camera with constant parameters. We propose a new set of quartic trivariate polynomial equations in the unknown coordinates of the plane at infinity derived under the no-skew assumption. Our new equations allow to further enforce the constancy of the principal point across all images while retrieving the plane at infinity. Six such polynomials, four of which are independent, are obtained for each triplet of images. The proposed equations can be solved along with the so-called modulus constraints and allow to improve the performance of existing methods.
Exact Voronoi diagram of smooth convex pseudo-circles: General predicates, and implementation for ellipses
2013
International audience; We examine the problem of computing exactly the Voronoi diagram (via the dual Delaunay graph) of a set of, possibly intersecting, smooth convex \pc in the Euclidean plane, given in parametric form. Pseudo-circles are (convex) sites, every pair of which has at most two intersecting points. The Voronoi diagram is constructed incrementally. Our first contribution is to propose robust and efficient algorithms, under the exact computation paradigm, for all required predicates, thus generalizing earlier algorithms for non-intersecting ellipses. Second, we focus on \kcn, which is the hardest predicate, and express it by a simple sparse $5\times 5$ polynomial system, which a…
Simple and Flexible Power Loss Minimizer With Low-Cost MCU Implementation for High-Efficiency Three-Phase Induction Motor Drives
2021
This paper presents a simple, practical and low-cost implementation of a power losses minimization algorithm for three-phase induction motors taking also into account both iron core losses and magnetic saturation. The algorithm evaluates, in real-time, the optimal direct axis magnetizing flux component for efficiency enhancement of the drive. A further advantage of the proposed technique is represented by a flexible and low-cost implementation by means of an ATMEL ATSAM3X8E microcontroller. The power loss minimization algorithm is tested preliminarily by means of several simulations, then, experimentally validated by applying the proposed control strategy on a 5.5 kW Field Oriented Control …
Structural Knowledge Extraction from Mobility Data
2016
Knowledge extraction has traditionally represented one of the most interesting challenges in AI; in recent years, however, the availability of large collections of data has increased the awareness that “measuring” does not seamlessly translate into “understanding”, and that more data does not entail more knowledge. We propose here a formulation of knowledge extraction in terms of Grammatical Inference (GI), an inductive process able to select the best grammar consistent with the samples. The aim is to let models emerge from data themselves, while inference is turned into a search problem in the space of consistent grammars, induced by samples, given proper generalization operators. We will …