Search results for "scene"

Observing animals and humans : dogs target their gaze to the biological information in natural scenes

2020

Background This study examines how dogs observe images of natural scenes containing living creatures (wild animals, dogs and humans) recorded with eye gaze tracking. Because dogs have had limited exposure to wild animals in their lives, we also consider the natural novelty of the wild animal images for the dogs. Methods The eye gaze of dogs was recorded while they viewed natural images containing dogs, humans, and wild animals. Three categories of images were used: naturalistic landscape images containing single humans or animals, full body images containing a single human or an animal, and full body images containing a pair of humans or animals. The gazing behavior of two dog populations,…

Acoustic Scene Classification with Squeeze-Excitation Residual Networks

2020

Acoustic scene classification (ASC) is a problem related to the field of machine listening whose objective is to classify/tag an audio clip in a predefined label describing a scene location (e. g. park, airport, etc.). Many state-of-the-art solutions to ASC incorporate data augmentation techniques and model ensembles. However, considerable improvements can also be achieved only by modifying the architecture of convolutional neural networks (CNNs). In this work we propose two novel squeeze-excitation blocks to improve the accuracy of a CNN-based ASC framework based on residual learning. The main idea of squeeze-excitation blocks is to learn spatial and channel-wise feature maps independently…

Knowledge Base Approach for 3D Objects Detection in Point Clouds Using 3D Processing and Specialists Knowledge

2012

This paper presents a knowledge-based detection of objects approach using the OWL ontology language, the Semantic Web Rule Language, and 3D processing built-ins aiming at combining geometrical analysis of 3D point clouds and specialist's knowledge. Here, we share our experience regarding the creation of 3D semantic facility model out of unorganized 3D point clouds. Thus, a knowledge-based detection approach of objects using the OWL ontology language is presented. This knowledge is used to define SWRL detection rules. In addition, the combination of 3D processing built-ins and topological Built-Ins in SWRL rules allows a more flexible and intelligent detection, and the annotation of objects …

Multimodal Polarimetric And Color Fusion For Road Scene Analysis In Adverse Weather Conditions

2021

Distributed Systems for Fusion of Visual Information

1997

Water resource recovery by means of microalgae cultivation in outdoor photobioreactors using the effluent from an anaerobic membrane bioreactor fed w…

2016

[EN] With the aim of assessing the potential of microalgae cultivation for water resource recovery (WRR), the performance of three 0.55 m3 flat-plate photobioreactors (PBRs) was evaluated in terms of nutrient removal rate (NRR) and biomass production. The PBRs were operated outdoor (at ambient temperature and light intensity) using as growth media the nutrient-rich effluent from an AnMBR fed with pre-treated sewage. Solar irradiance was the most determining factor affecting NRR. Biomass productivity was significantly affected by temperatures below 20 °C. The maximum biomass productivity (52.3 mg VSS·L−1·d−1) and NRR (5.84 mg NH4-N·L−1·d−1 and 0.85 mg PO4-P·L−1·…

Short and long-term experiments on the effect of sulphide on microalgae cultivation in tertiary sewage treatment.

2017

[EN] Microalgae cultivation appears to be a promising technology for treating nutrient-rich effluents from anaerobic membrane bioreactors, as microalgae are able to consume nutrients from sewage without an organic carbon source, although the sulphide formed during the anaerobic treatment does have negative effects on microalgae growth. Short and long-term experiments were carried out on the effects of sulphide on a mixed microalgae culture. The short-term experiments showed that the oxygen production rate (OPR) dropped as sulphide concentration increased: a concentration of 5 mg S L¿1 reduced OPR by 43%, while a concentration of 50 mg S L¿1 came close to completely inhibiting microalgae gro…

Pompei all'opera: iconografie romane nella Jone di Errico Petrella

2019

All'interno degli studi dedicati alla storia della tradizione classica, non tutti i possibili campi di ricerca sono stati completamente esplorati. Un argomento scarsamente messo in evidenza è lo scenario delle opere che mettono in scena il mondo greco-romano. Tra le opere di ambientazione classica composte nel corso del XIX secolo, uno dei maggiori successi, anche se oggi quasi dimenticato, fu Jone di Errico Petrella (1813-1877). Il libretto di quest'opera (eseguita per la prima volta a Milano, al Teatro alla Scala, nel 1858) era stato tratto dal celebre romanzo The Last Days of Pompeii di Edward Bulwer-Lytton (1834). Within the studies dedicated to the history of the classical tradition, n…

Improved multi-resolution image fusion

2005

This work describes an automatic technique able to fuse different images of the same scene, acquired at different settings, in order to obtain an enhanced single representation of the scene of interest by an improved picture fusion scheme. This allows the extending of the functionalities (depth of field, dynamic range) of medium and low cost digital cameras. When multi-scale decomposition is used on multi-focused images, magnification effects of the lens focusing system cause an incorrect estimation of all pixels in the final image. In our approach new techniques able to reduce these artifacts are introduced. The algorithm has been applied both on full RGB and on color filter array (CFA) im…

Reconstructing urban scene 3D using VisualSfM

2013

New computer vision techniques use photo dataset to rapidly build detailed 3D models. Computer- vision researchers have explored many approaches to city-scale 3D reconstruc on. Among these systems stands out VisualSfM developed by the University of Washington & Google Inc. It is a open source GUI applica on of a Structure from Mo on (SfM) so! ware that uses a feature extractor called Si! GPU and the Mul core Bundle Adjustment. In addi on it embeds the CMVS/ PMVS2 able to reconstruct dense 3D point cloud. Our goal is to demonstrate the metric accuracy of VisualSfM+CMVS/PMVS2 and that to get run it, you can use an unstructured photo dataset but the result improves if you use a structured phot…