Exploració per tema "object recognition"
Ara es mostren els items 1-15 de 15
-
Boosting histograms of oriented gradients for human detection
(s. n., 2007)
Text en actes de congrés
Accés obertIn this paper we propose a human detection framework based on an enhanced version of Histogram of Oriented Gradients (HOG) features. These feature descriptors are computed with the help of a precalculated histogram of ... -
Camera alignment system for passive safety crash tests
(Universitat Politècnica de Catalunya, 2016-07-19)
Projecte Final de Màster Oficial
Accés restringit per decisió de l'autorThe use of digital high-speed cameras to acquire relevant information is a standard for all the laboratories and facilities working on passive safety crash tests. The recorded information from the cameras is used to develop ... -
Evaluation of three vision based object perception methods for a mobile robot
(2012)
Article
Accés obertThis paper addresses visual object perception applied to mobile robotics. Being able to perceive household objects in unstructured environments is a key capability in order to make robots suitable to perform complex tasks ... -
GPU-based low-level image processing for object recognition using HDR images
(Universitat Politècnica de Catalunya / Karlsruher Institut für Technology, 2012-06-15)
Projecte/Treball Final de Carrera
Accés obert
Realitzat a/amb: Karlsruher Institut für Technologie[ANGLÈS] The algorithm developed for object recognition using HDR images is divided in 3 modules. The first one obtain images without noise from the scene using a fusion method, which one is based on the pdf of each pixel ... -
Multimodal feedback fusion of laser, image and temporal information
(Association for Computing Machinery (ACM), 2014)
Text en actes de congrés
Accés obertIn the present paper, we propose a highly accurate and robust people detector, which works well under highly variant and uncertain conditions, such as occlusions, false positives and false detections. These adverse conditions, ... -
Multimodal object recognition using random clustering trees
(Springer, 2015)
Text en actes de congrés
Accés obertIn this paper, we present an object recognition approach that in addition allows to discover intra-class mo dalities exhibiting high-correlated visual information. Unlike to more conventional approaches based on computing ... -
Object detection and recognition: from saliency prediction to one-shot trained detectors
(Universitat Politècnica de Catalunya, 2014-09-03)
Projecte/Treball Final de Carrera
Accés obert
Realitzat a/amb: Massachusetts Institute of Technology[ANGLÈS] Computer vision capabilities have started to become available in smart devices this last years. The rapid growth of the smartphone world along with the big advance of the computer vision field in the last years ... -
Object recognition applied to mobile robotics
(Universitat Politècnica de Catalunya, 2012-09-19)
Projecte/Treball Final de Carrera
Accés obertInvestigació de les possibilitats dels mètodes actuals de detecció i reconeixement d'objectes. Adaptació del millor mètode seleccionat (MOPED) per tal de solucionar els problemes de la competició de robots domèstics "Robocup ... -
Objects recognition from their volumetric data for an autonomous kitchen
(Universitat Politècnica de Catalunya, 2016-06-27)
Treball Final de Grau
Accés obertEl presente trabajo se centra en resolver el problema relacionado con el reconocimiento de objetos en un entorno de cocina, describiendo cada objeto a partir de su color y volumetría. -
Online human-assisted learning using random ferns
(2012)
Text en actes de congrés
Accés obertWe present an Online Random Ferns (ORFs) classifier that progressively learns and builds enhanced models of object appearances. During the learning process, we allow the human intervention to assist the classifier and ... -
Optimization of robust loss functions for weakly-labeled image taxonomies
(2013)
Article
Accés restringit per política de l'editorialThe recently proposed ImageNet dataset consists of several million images, each annotated with a single object category. These annotations may be imperfect, in the sense that many images contain multiple objects belonging ... -
Precision and power grip detection in egocentric hand-object Interaction using machine learning
(Universitat Politècnica de Catalunya, 2023-06-26)
Projecte Final de Màster Oficial
Accés obertThis project, was carried out in Yverdon-les-Bains, Switzerland, between the University of Applied Sciences and Arts Western Switzerland (HEIG-VD / HES-SO) and the Centre Hospitalier Universitaire Vaudois (CHUV) in Lausanne, ... -
Scene understanding using deep learning
(Elsevier, 2017)
Capítol de llibre
Accés obertAutomation based on artificial intelligence becomes necessary when agents such as robots are deployed to perform complex tasks. Detailed representation of a scene makes robots better aware of their surroundings, thereby ... -
Semantic segmentation priors for object discovery
(IEEE Press, 2016)
Text en actes de congrés
Accés obertReliable object discovery in realistic indoor scenes is a necessity for many computer vision and service robot applications. In these scenes, semantic segmentation methods have made huge advances in recent years. Such ... -
Understanding the impact of on-chip communication on DNN accelerator performance
(2019)
Text en actes de congrés
Accés restringit per política de l'editorialDeep Neural Networks have flourished at an unprecedented pace in recent years. They have achieved outstanding accuracy in fields such as computer vision, natural language processing, medicine or economics. Specifically, ...