Exploració per tema "Computer vision"
Ara es mostren els items 21-40 de 625
-
A Learning from demonstration approach for robot trajectories through motion-sensing human demonstrations
(Universitat Politècnica de Catalunya, 2020-04-20)
Projecte Final de Màster Oficial
Accés obertThe objective of this thesis is to teach a Baxter robot to learn certain arm trajectories. The robot must be capable of generalizing the primitive movement of the trajectory to new unseen poses. The thesis is framed ... -
A morphological approach for segmentation and tracking of human faces
(Barcelona, 2000)
Comunicació de congrés
Accés obertA new technique for segmenting and tracking human faces in video sequences is presented. The technique relies on morphological tools such as using connected operators to extract the connected component that more likely ... -
A new graph matching method for point-set correspondence using the EM algorithm and Softassign
(2012)
Article
Accés restringit per política de l'editorialFinding correspondences between two point-sets is a common step in many vision applications (e.g., image matching or shape retrieval). We present a graph matching method to solve the point-set correspondence problem, which ... -
A novel real-time edge-preserving smoothing filter
(2013)
Text en actes de congrés
Accés obertThe segmentation of textured and noisy areas in images is a very challenging task due to the large variety of objects and materials in natural environments, which cannot be solved by a single similarity measure. In this ... -
A Preliminary study of deep learning sensor fusion for pedestrian detection
(Multidisciplinary Digital Publishing Institute (MDPI), 2023-04)
Article
Accés obertMost pedestrian detection methods focus on bounding boxes based on fusing RGB with lidar. These methods do not relate to how the human eye perceives objects in the real world. Furthermore, lidar and vision can have difficulty ... -
A simple method of multiple camera calibration for the joint top view projection
(Springer, 2007)
Capítol de llibre
Accés obertA simple method for multiple camera calibration based on a novel geometric derivation is presented. The main advantage of this method is that it uses only three points in the world coordinate system to achieve the calibration. ... -
A survey on model based approaches for 2D and 3D visual human pose recovery
(2014-03-03)
Article
Accés obertHuman Pose Recovery has been studied in the field of Computer Vision for the last 40 years. Several approaches have been reported, and significant improvements have been obtained in both data representation and model design. ... -
Action recognition using the Rf Transform on optical flow images
(SCITEPRESS, 2017)
Text en actes de congrés
Accés obertThe objective of this paper is the automatic recognition of human actions in video sequences. The use of spatio-temporal features for action recognition has become very popular in recent literature Instead of extracting ... -
Action selection for robotic manipulation of deformable objects
(ESF-JSPS, 2008)
Text en actes de congrés
Accés obertThis paper deals with the manipulation of planar deformable objects for typical service robot applications. Specifically, we present a system that straightens pieces of cloth from any arbitrary initial wrinkle condition ... -
Action selection for single-camera SLAM
(2010)
Article
Accés obertA method for evaluating, at video rate, the quality of actions for a single camera while mapping unknown indoor environments is presented. The strategy maximizes mutual information between measurements and states to help ... -
Active Appearance Models for People Recognition with a RGB-D Sensor
(Universitat Politècnica de Catalunya, 2014-06)
Projecte Final de Màster Oficial
Accés restringit per decisió de l'autorActive Appearance Models (AAMs) is a computer vision procedure for statistical matching of object shape and appearance between images. The present work will analyze how AAMs can be employed with RGB-Depth technology, so ... -
Active camera calibration for robotic systems
(Universitat Politècnica de Catalunya, 2016)
Projecte Final de Màster Oficial
Accés obert
Realitzat a/amb: Eidgenössische Technische Hochschule ZürichCamera calibration is an essential process embedded in any computer vision system that involves the extraction of spatial information from captured images. Traditional techniques for calibration require an expert to take ... -
Active deep learning for medical imaging segmentation
(Universitat Politècnica de Catalunya, 2017)
Treball Final de Grau
Accés obert
Realitzat a/amb: Institut national polytechnique de ToulouseThis thesis proposes a novel active learning framework capable to train effectively a convolutional neural network for semantic segmentation of medical imaging, with a limited amount of training labeled data. Our approach ... -
Adaptive transfer functions: improved multiresolution visualization of medical models
(Springer, 2016-05-14)
Article
Accés obertMedical datasets are continuously increasing in size. Although larger models may be available for certain research purposes, in the common clinical practice the models are usually of up to 512x512x2000 voxels. These ... -
Adquisición y procesado de imágenes para el control de calidad en piezas de mecanizado
(Universitat Politècnica de Catalunya, 2007-07-09)
Projecte/Treball Final de Carrera
Accés obertEste proyecto se particulariza en el estudio y uso de técnicas de visión artificial. Las técnicas que nos ofrece el mercado actual y el uso del software de programación LabVIEW han permitido desarrollar una aplicación de ... -
Age & Gender Recognition in The Wild
(Universitat Politècnica de Catalunya, 2022-06-28)
Treball Final de Grau
Accés obertL'estimació de grups demogràfics a partir d'imatges, i en particular pel que fa a l'estimació d'edat i sexe, és un sector amb un ampli ventall d'aplicacions. Tanmateix, l'estat de l'art actual està poc encarat a escenaris ... -
Aliasing is a driver of adversarial attacks
(Universitat Politècnica de Catalunya, 2022-05)
Treball Final de Grau
Accés restringit per acord de confidencialitat -
AmodalAppleSize_RGB-D dataset: RGB-D images of apple trees annotated with modal and amodal segmentation masks for fruit detection, visibility and size estimation
(Elsevier, 2024-02)
Article
Accés obertThe present dataset comprises a collection of RGB-D apple tree images that can be used to train and test computer vision-based fruit detection and sizing methods. This dataset encompasses two distinct sets of data obtained ... -
An analysis of modeling and training decisions for greener computer vision systems
(Universitat Politècnica de Catalunya, 2023-01-26)
Projecte Final de Màster Oficial
Accés restringit per acord de confidencialitatThe main goal of this study is to analyze the impact of the model architecture and training strategy when building green computer vision systems. We divide this goal into two research questions. In the first one, we ... -
An approach for physiological motion compensation in robotic-assisted cardiac surgery
(2014-11-14)
Article
Accés obertThe lack of physiological motion compensation is a major problem in robotic-assisted cardiac surgery. Since the heart is beating while the surgeon carried out the procedure, dexterity of the surgeon’s and precision are ...