Home [11–20] << 21 22 23 24 25 26 27 28 29 30 >> [31–40]
List View
 | 
Citations
 | 
Details
   web
Records
Author Ariel Amato; Mikhail Mozerov; Andrew Bagdanov; Jordi Gonzalez
Title (up) Accurate Moving Cast Shadow Suppression Based on Local Color Constancy detection Type Journal Article
Year 2011 Publication IEEE Transactions on Image Processing Abbreviated Journal TIP
Volume 20 Issue 10 Pages 2954 - 2966
Keywords
Abstract This paper describes a novel framework for detection and suppression of properly shadowed regions for most possible scenarios occurring in real video sequences. Our approach requires no prior knowledge about the scene, nor is it restricted to specific scene structures. Furthermore, the technique can detect both achromatic and chromatic shadows even in the presence of camouflage that occurs when foreground regions are very similar in color to shadowed regions. The method exploits local color constancy properties due to reflectance suppression over shadowed regions. To detect shadowed regions in a scene, the values of the background image are divided by values of the current frame in the RGB color space. We show how this luminance ratio can be used to identify segments with low gradient constancy, which in turn distinguish shadows from foreground. Experimental results on a collection of publicly available datasets illustrate the superior performance of our method compared with the most sophisticated, state-of-the-art shadow detection algorithms. These results show that our approach is robust and accurate over a broad range of shadow types and challenging video conditions.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1057-7149 ISBN Medium
Area Expedition Conference
Notes ISE Approved no
Call Number Admin @ si @ AMB2011 Serial 1716
Permanent link to this record
 
 
Author Mikhail Mozerov; Joost Van de Weijer
Title (up) Accurate stereo matching by two step global optimization Type Journal Article
Year 2015 Publication IEEE Transactions on Image Processing Abbreviated Journal TIP
Volume 24 Issue 3 Pages 1153-1163
Keywords
Abstract In stereo matching cost filtering methods and energy minimization algorithms are considered as two different techniques. Due to their global extend energy minimization methods obtain good stereo matching results. However, they tend to fail in occluded regions, in which cost filtering approaches obtain better results. In this paper we intend to combine both approaches with the aim to improve overall stereo matching results. We show that a global optimization with a fully connected model can be solved by cost fil tering methods. Based on this observation we propose to perform stereo matching as a two-step energy minimization algorithm. We consider two MRF models: a fully connected model defined on the complete set of pixels in an image and a conventional locally connected model. We solve the energy minimization problem for the fully connected model, after which the marginal function of the solution is used as the unary potential in the locally connected MRF model. Experiments on the Middlebury stereo datasets show that the proposed method achieves state-of-the-arts results.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1057-7149 ISBN Medium
Area Expedition Conference
Notes ISE; LAMP; 600.079; 600.078 Approved no
Call Number Admin @ si @ MoW2015a Serial 2568
Permanent link to this record
 
 
Author Lluis Barcelo
Title (up) Accurate video mosaicing with moving objects Type Report
Year 2002 Publication CVC Technical Report # 59 Abbreviated Journal
Volume Issue Pages
Keywords
Abstract
Address CVC (UAB)
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes Approved no
Call Number Admin @ si @ Bar2002 Serial 326
Permanent link to this record
 
 
Author Ariel Amato; Mikhail Mozerov; Ivan Huerta; Jordi Gonzalez; Juan J. Villanueva
Title (up) ackground Subtraction Technique Based on Chromaticity and Intensity Patterns Type Conference Article
Year 2008 Publication 19th International Conference on Pattern Recognition, Abbreviated Journal
Volume Issue Pages 1–4
Keywords
Abstract
Address Tampa (Florida)
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference ICPR
Notes ISE Approved no
Call Number ISE @ ise @ AMH2008 Serial 1071
Permanent link to this record
 
 
Author Albert Clapes; Alex Pardo; Oriol Pujol; Sergio Escalera
Title (up) Action detection fusing multiple Kinects and a WIMU: an application to in-home assistive technology for the elderly Type Journal Article
Year 2018 Publication Machine Vision and Applications Abbreviated Journal MVAP
Volume 29 Issue 5 Pages 765–788
Keywords Multimodal activity detection; Computer vision; Inertial sensors; Dense trajectories; Dynamic time warping; Assistive technology
Abstract We present a vision-inertial system which combines two RGB-Depth devices together with a wearable inertial movement unit in order to detect activities of the daily living. From multi-view videos, we extract dense trajectories enriched with a histogram of normals description computed from the depth cue and bag them into multi-view codebooks. During the later classification step a multi-class support vector machine with a RBF- 2 kernel combines the descriptions at kernel level. In order to perform action detection from the videos, a sliding window approach is utilized. On the other hand, we extract accelerations, rotation angles, and jerk features from the inertial data collected by the wearable placed on the user’s dominant wrist. During gesture spotting, a dynamic time warping is applied and the aligning costs to a set of pre-selected gesture sub-classes are thresholded to determine possible detections. The outputs of the two modules are combined in a late-fusion fashion. The system is validated in a real-case scenario with elderly from an elder home. Learning-based fusion results improve the ones from the single modalities, demonstrating the success of such multimodal approach.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes HUPBA; no proj Approved no
Call Number Admin @ si @ CPP2018 Serial 3125
Permanent link to this record
 
 
Author Wenjuan Gong
Title (up) Action priors for human pose tracking by particle filter Type Report
Year 2009 Publication CVC Technical Report Abbreviated Journal
Volume Issue Pages
Keywords
Abstract
Address
Corporate Author Computer Vision Center Thesis Master's thesis
Publisher Place of Publication Bellaterra, Barcelona Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes ISE Approved no
Call Number Admin @ si @ Gon2009 Serial 2401
Permanent link to this record
 
 
Author Mohammad Ali Bagheri; Qigang Gao; Sergio Escalera
Title (up) Action Recognition by Pairwise Proximity Function Support Vector Machines with Dynamic Time Warping Kernels Type Conference Article
Year 2016 Publication 29th Canadian Conference on Artificial Intelligence Abbreviated Journal
Volume 9673 Issue Pages 3-14
Keywords
Abstract In the context of human action recognition using skeleton data, the 3D trajectories of joint points may be considered as multi-dimensional time series. The traditional recognition technique in the literature is based on time series dis(similarity) measures (such as Dynamic Time Warping). For these general dis(similarity) measures, k-nearest neighbor algorithms are a natural choice. However, k-NN classifiers are known to be sensitive to noise and outliers. In this paper, a new class of Support Vector Machine that is applicable to trajectory classification, such as action recognition, is developed by incorporating an efficient time-series distances measure into the kernel function. More specifically, the derivative of Dynamic Time Warping (DTW) distance measure is employed as the SVM kernel. In addition, the pairwise proximity learning strategy is utilized in order to make use of non-positive semi-definite (PSD) kernels in the SVM formulation. The recognition results of the proposed technique on two action recognition datasets demonstrates the ourperformance of our methodology compared to the state-of-the-art methods. Remarkably, we obtained 89 % accuracy on the well-known MSRAction3D dataset using only 3D trajectories of body joints obtained by Kinect
Address Victoria; Canada; May 2016
Corporate Author Thesis
Publisher Springer International Publishing Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference AI
Notes HuPBA;MILAB; Approved no
Call Number Admin @ si @ BGE2016b Serial 2770
Permanent link to this record
 
 
Author Maryam Asadi-Aghbolaghi; Hugo Bertiche; Vicent Roig; Shohreh Kasaei; Sergio Escalera
Title (up) Action Recognition from RGB-D Data: Comparison and Fusion of Spatio-temporal Handcrafted Features and Deep Strategies Type Conference Article
Year 2017 Publication Chalearn Workshop on Action, Gesture, and Emotion Recognition: Large Scale Multimodal Gesture Recognition and Real versus Fake expressed emotions at ICCV Abbreviated Journal
Volume Issue Pages
Keywords
Abstract
Address Venice; Italy; October 2017
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference ICCVW
Notes HUPBA; no menciona Approved no
Call Number Admin @ si @ ABR2017 Serial 3068
Permanent link to this record
 
 
Author Jordi Gonzalez
Title (up) Action recognition in application domains Type Report
Year 1999 Publication CVC Technical Report #13 Abbreviated Journal
Volume Issue Pages
Keywords
Abstract
Address CVC (UAB)
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes Approved no
Call Number ISE @ ise @ Gon1999 Serial 357
Permanent link to this record
 
 
Author Cesar de Souza
Title (up) Action Recognition in Videos: Data-efficient approaches for supervised learning of human action classification models for video Type Book Whole
Year 2018 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract In this dissertation, we explore different ways to perform human action recognition in video clips. We focus on data efficiency, proposing new approaches that alleviate the need for laborious and time-consuming manual data annotation. In the first part of this dissertation, we start by analyzing previous state-of-the-art models, comparing their differences and similarities in order to pinpoint where their real strengths come from. Leveraging this information, we then proceed to boost the classification accuracy of shallow models to levels that rival deep neural networks. We introduce hybrid video classification architectures based on carefully designed unsupervised representations of handcrafted spatiotemporal features classified by supervised deep networks. We show in our experiments that our hybrid model combine the best of both worlds: it is data efficient (trained on 150 to 10,000 short clips) and yet improved significantly on the state of the art, including deep models trained on millions of manually labeled images and videos. In the second part of this research, we investigate the generation of synthetic training data for action recognition, as it has recently shown promising results for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation and other computer graphics techniques of modern game engines. We generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for “Procedural Human Action Videos”. It contains a total of 39,982 videos, with more than 1,000 examples for each action of 35 categories. Our approach is not limited to existing motion capture sequences, and we procedurally define 14 synthetic actions. We then introduce deep multi-task representation learning architectures to mix synthetic and real videos, even if the action categories differ. Our experiments on the UCF-101 and HMDB-51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance, outperforming fine-tuning state-of-the-art unsupervised generative models of videos.
Address April 2018
Corporate Author Thesis Ph.D. thesis
Publisher Ediciones Graficas Rey Place of Publication Editor Antonio Lopez;Naila Murray
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes ADAS; 600.118 Approved no
Call Number Admin @ si @ Sou2018 Serial 3127
Permanent link to this record
 
 
Author Ikechukwu Ofodile; Ahmed Helmi; Albert Clapes; Egils Avots; Kerttu Maria Peensoo; Sandhra Mirella Valdma; Andreas Valdmann; Heli Valtna Lukner; Sergey Omelkov; Sergio Escalera; Cagri Ozcinar; Gholamreza Anbarjafari
Title (up) Action recognition using single-pixel time-of-flight detection Type Journal Article
Year 2019 Publication Entropy Abbreviated Journal ENTROPY
Volume 21 Issue 4 Pages 414
Keywords single pixel single photon image acquisition; time-of-flight; action recognition
Abstract Action recognition is a challenging task that plays an important role in many robotic systems, which highly depend on visual input feeds. However, due to privacy concerns, it is important to find a method which can recognise actions without using visual feed. In this paper, we propose a concept for detecting actions while preserving the test subject’s privacy. Our proposed method relies only on recording the temporal evolution of light pulses scattered back from the scene.
Such data trace to record one action contains a sequence of one-dimensional arrays of voltage values acquired by a single-pixel detector at 1 GHz repetition rate. Information about both the distance to the object and its shape are embedded in the traces. We apply machine learning in the form of recurrent neural networks for data analysis and demonstrate successful action recognition. The experimental results show that our proposed method could achieve on average 96.47% accuracy on the actions walking forward, walking backwards, sitting down, standing up and waving hand, using recurrent
neural network.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes HuPBA; no proj Approved no
Call Number Admin @ si @ OHC2019 Serial 3319
Permanent link to this record
 
 
Author Ignasi Rius; J. Varona; Jordi Gonzalez; Juan J. Villanueva
Title (up) Action Spaces for Efficient Bayesian Tracking of Human Motion Type Miscellaneous
Year 2006 Publication International Conference on Pattern Recognition (ICPR´06), 1: 472–475 Abbreviated Journal
Volume Issue Pages
Keywords
Abstract
Address Hong Kong (China)
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes Approved no
Call Number ISE @ ise @ RVG2006 Serial 770
Permanent link to this record
 
 
Author Yi Xiao; Felipe Codevilla; Christopher Pal; Antonio Lopez
Title (up) Action-Based Representation Learning for Autonomous Driving Type Conference Article
Year 2020 Publication Conference on Robot Learning Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Human drivers produce a vast amount of data which could, in principle, be used to improve autonomous driving systems. Unfortunately, seemingly straightforward approaches for creating end-to-end driving models that map sensor data directly into driving actions are problematic in terms of interpretability, and typically have significant difficulty dealing with spurious correlations. Alternatively, we propose to use this kind of action-based driving data for learning representations. Our experiments show that an affordance-based driving model pre-trained with this approach can leverage a relatively small amount of weakly annotated imagery and outperform pure end-to-end driving models, while being more interpretable. Further, we demonstrate how this strategy outperforms previous methods based on learning inverse dynamics models as well as other methods based on heavy human supervision (ImageNet).
Address virtual; November 2020
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference CORL
Notes ADAS; 600.118 Approved no
Call Number Admin @ si @ XCP2020 Serial 3487
Permanent link to this record
 
 
Author Ignasi Rius; Jordi Gonzalez; J. Varona; Xavier Roca
Title (up) Action-specific motion prior for efficient bayesian 3D human body tracking Type Journal Article
Year 2009 Publication Pattern Recognition Abbreviated Journal PR
Volume 42 Issue 11 Pages 2907–2921
Keywords
Abstract In this paper, we aim to reconstruct the 3D motion parameters of a human body
model from the known 2D positions of a reduced set of joints in the image plane.
Towards this end, an action-specific motion model is trained from a database of real
motion-captured performances. The learnt motion model is used within a particle
filtering framework as a priori knowledge on human motion. First, our dynamic
model guides the particles according to similar situations previously learnt. Then, the solution space is constrained so only feasible human postures are accepted as valid solutions at each time step. As a result, we are able to track the 3D configuration of the full human body from several cycles of walking motion sequences using only the 2D positions of a very reduced set of joints from lateral or frontal viewpoints.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0031-3203 ISBN Medium
Area Expedition Conference
Notes ISE Approved no
Call Number ISE @ ise @ RGV2009 Serial 1159
Permanent link to this record
 
 
Author Alex Pardo; Albert Clapes; Sergio Escalera; Oriol Pujol
Title (up) Actions in Context: System for people with Dementia Type Conference Article
Year 2013 Publication 2nd International Workshop on Citizen Sensor Networks (Citisen2013) at the European Conference on Complex Systems Abbreviated Journal
Volume Issue Pages 3-14
Keywords Multi-modal data Fusion; Computer vision; Wearable sensors; Gesture recognition; Dementia
Abstract In the next forty years, the number of people living with dementia is expected to triple. In the last stages, people affected by this disease become dependent. This hinders the autonomy of the patient and has a huge social impact in time, money and effort. Given this scenario, we propose an ubiquitous system capable of recognizing daily specific actions. The system fuses and synchronizes data obtained from two complementary modalities – ambient and egocentric. The ambient approach consists in a fixed RGB-Depth camera for user and object recognition and user-object interaction, whereas the egocentric point of view is given by a personal area network (PAN) formed by a few wearable sensors and a smartphone, used for gesture recognition. The system processes multi-modal data in real-time, performing paralleled task recognition and modality synchronization, showing high performance recognizing subjects, objects, and interactions, showing its reliability to be applied in real case scenarios.
Address Barcelona; September 2013
Corporate Author Thesis
Publisher Springer International Publishing Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN 978-3-319-04177-3 Medium
Area Expedition Conference ECCS
Notes HUPBA;MILAB Approved no
Call Number Admin @ si @ PCE2013 Serial 2354
Permanent link to this record