Exploració per tema "Classificació INSPEC::Pattern recognition::Computer vision"
Ara es mostren els items 1-20 de 139
-
2D-to-3D facial expression transfer
(Institute of Electrical and Electronics Engineers (IEEE), 2018)
Text en actes de congrés
Accés obertAutomatically changing the expression and physical features of a face from an input image is a topic that has been traditionally tackled in a 2D domain. In this paper, we bring this problem to 3D and propose a framework ... -
3D human pose estimation from a single image via distance matrix regression
(Institute of Electrical and Electronics Engineers (IEEE), 2017)
Text en actes de congrés
Accés obertThis paper addresses the problem of 3D human pose estimation from a single image. We follow a standard two-step pipeline by first detecting the 2D position of the N body joints, and then using these observations to infer ... -
3D human shape and pose from a single low-resolution image with self-supervised learning
(2020)
Text en actes de congrés
Accés obert3D human shape and pose estimation from monocular images has been an active area of research in computer vision, having a substantial impact on the development of new applications, from activity recognition to creating ... -
3D modelling of leaves from color and ToF data for robotized plant measuring
(2011)
Text en actes de congrés
Accés restringit per política de l'editorialSupervision of long-lasting extensive botanic experiments is a promising robotic application that some recent technological advances have made feasible. Plant modelling for this application has strong demands, particularly ... -
3D reconstruction of underwater structures
(2010)
Text en actes de congrés
Accés obertEnvironmental change is a growing international concern, calling for the regular monitoring, studying and preserving of detailed information about the evolution of underwater ecosystems. For example, fragile coral reefs ... -
A 3D descriptor to detect task-oriented grasping points in clothing
(2016)
Article
Accés obertManipulating textile objects with a robot is a challenging task, especially because the garment perception is difficult due to the endless configurations it can adopt, coupled with a large variety of colors and designs. ... -
A 3D System for training in endoscopical repair of subcondylar fractures of the mandible
(Springer Verlag, 2008)
Article
Accés obertPoster Session: 12th Annual Conference of Iscas. Conventional treatment of the subcondylar fractures of the mandible is challenging because of the medial and anterior displacement of the condylar fragment and the limited ... -
A comparison of three methods for measure of time to contact
(IEEE Press. Institute of Electrical and Electronics Engineers, 2009-10-11)
Comunicació de congrés
Accés obertTime to Contact (TTC) is a biologically inspired method for obstacle detection and reactive control of motion that does not require scene reconstruction or 3D depth estimation. Estimating TTC is difficult because it requires ... -
A hierarchical architecture to multiple target tracking
(s. n., 2007)
Text en actes de congrés
Accés obertThis work presents an architecture based on a modular and hierarchically-organised system to perform Multiple-Target Tracking (MTT). A set of co-operating modules, which work following both bottom-up and top-down paradigms, ... -
A high performance CRF model for clothes parsing
(Springer, 2014)
Text en actes de congrés
Accés obertIn this paper we tackle the problem of clothing parsing: Our goal is to segment and classify different garments a person is wearing. We frame the problem as the one of inference in a pose-aware Conditional Random Field ... -
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 scalable, efficient, and accurate solution to non-rigid structure from motion
(2018)
Article
Accés obertMost Non-Rigid Structure from Motion (NRSfM) solutions are based on factorization approaches that allow reconstructing objects parameterized by a sparse set of 3D points. These solutions, however, are low resolution and ... -
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. ... -
Action recognition based on efficient deep feature learning in the spatio-temporal domain
(Institute of Electrical and Electronics Engineers (IEEE), 2016)
Article
Accés obertHand-crafted feature functions are usually designed based on the domain knowledge of a presumably controlled environment and often fail to generalize, as the statistics of real-world data cannot always be modeled correctly. ... -
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 ... -
Active testing search for point cloud matching
(Springer, 2013)
Text en actes de congrés
Accés obertWe present a general approach for solving the point-cloud matching problem for the case of mildly nonlinear transformations. Our method quickly finds a coarse approximation of the solution by exploring a reduced set of ... -
Automatic generation of exploration paths for medical models
(Springer Verlag, 2008)
Article
Accés obertIn Supplement 1. Proceedings of the 22nd International Congress and Exhibition, Barcelona, Spain, June 25-28, 2008. Category: Image Processing and Display -
Automatic learning of conceptual knowledge in image sequences for human behavior interpretation
(Springer Verlag, 2007)
Capítol de llibre
Accés obertThis work describes an approach for the interpretation and explanation of human behavior in image sequences, within the context of a Cognitive Vision System. The information source is the geometrical data obtained by ... -
Background subtraction fusing colour, intensity and edge cues
(s. n., 2007)
Text en actes de congrés
Accés obertThis paper presents a new background subtraction algorithm for known mobile objects segmentation from a static background scene. Firstly, a casuistry of colour-motion segmentation problems is presented. Our approach first ... -
Boosted Random ferns for object detection
(2018-02-01)
Article
Accés obertIn this paper we introduce the Boosted Random Ferns (BRFs) to rapidly build discriminative classifiers for learning and detecting object categories. At the core of our approach we use standard random ferns, but we introduce ...