toggle visibility Search & Display Options
Select All    Deselect All << 1 2 3 4 5 6 7 8 9 10 >> [11–20]
List View
 | 
Citations
 | 
Details
  Records Links
Author Naveen Onkarappa; Angel Sappa edit  doi
isbn  openurl
  Title Laplacian Derivative based Regularization for Optical Flow Estimation in Driving Scenario Type Conference Article
  Year (down) 2013 Publication 15th International Conference on Computer Analysis of Images and Patterns Abbreviated Journal  
  Volume 8048 Issue Pages 483-490  
  Keywords Optical flow; regularization; Driver Assistance Systems; Performance Evaluation  
  Abstract Existing state of the art optical flow approaches, which are evaluated on standard datasets such as Middlebury, not necessarily have a similar performance when evaluated on driving scenarios. This drop on performance is due to several challenges arising on real scenarios during driving. Towards this direction, in this paper, we propose a modification to the regularization term in a variational optical flow formulation, that notably improves the results, specially in driving scenarios. The proposed modification consists on using the Laplacian derivatives of flow components in the regularization term instead of gradients of flow components. We show the improvements in results on a standard real image sequences dataset (KITTI).  
  Address York; UK; August 2013  
  Corporate Author Thesis  
  Publisher Springer Berlin Heidelberg Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-642-40245-6 Medium  
  Area Expedition Conference CAIP  
  Notes ADAS; 600.055; 601.215 Approved no  
  Call Number Admin @ si @ OnS2013b Serial 2244  
Permanent link to this record
 
 
Author German Ros; J. Guerrero; Angel Sappa; Antonio Lopez edit   pdf
doi  isbn
openurl 
  Title VSLAM pose initialization via Lie groups and Lie algebras optimization Type Conference Article
  Year (down) 2013 Publication Proceedings of IEEE International Conference on Robotics and Automation Abbreviated Journal  
  Volume Issue Pages 5740 - 5747  
  Keywords SLAM  
  Abstract We present a novel technique for estimating initial 3D poses in the context of localization and Visual SLAM problems. The presented approach can deal with noise, outliers and a large amount of input data and still performs in real time in a standard CPU. Our method produces solutions with an accuracy comparable to those produced by RANSAC but can be much faster when the percentage of outliers is high or for large amounts of input data. On the current work we propose to formulate the pose estimation as an optimization problem on Lie groups, considering their manifold structure as well as their associated Lie algebras. This allows us to perform a fast and simple optimization at the same time that conserve all the constraints imposed by the Lie group SE(3). Additionally, we present several key design concepts related with the cost function and its Jacobian; aspects that are critical for the good performance of the algorithm.  
  Address Karlsruhe; Germany; May 2013  
  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 1050-4729 ISBN 978-1-4673-5641-1 Medium  
  Area Expedition Conference ICRA  
  Notes ADAS; 600.054; 600.055; 600.057 Approved no  
  Call Number Admin @ si @ RGS2013a; ADAS @ adas @ Serial 2225  
Permanent link to this record
 
 
Author David Aldavert; Marçal Rusiñol; Ricardo Toledo; Josep Llados edit   pdf
doi  openurl
  Title Integrating Visual and Textual Cues for Query-by-String Word Spotting Type Conference Article
  Year (down) 2013 Publication 12th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume Issue Pages 511 - 515  
  Keywords  
  Abstract In this paper, we present a word spotting framework that follows the query-by-string paradigm where word images are represented both by textual and visual representations. The textual representation is formulated in terms of character $n$-grams while the visual one is based on the bag-of-visual-words scheme. These two representations are merged together and projected to a sub-vector space. This transform allows to, given a textual query, retrieve word instances that were only represented by the visual modality. Moreover, this statistical representation can be used together with state-of-the-art indexation structures in order to deal with large-scale scenarios. The proposed method is evaluated using a collection of historical documents outperforming state-of-the-art performances.  
  Address Washington; USA; August 2013  
  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 1520-5363 ISBN Medium  
  Area Expedition Conference ICDAR  
  Notes DAG; ADAS; 600.045; 600.055; 600.061 Approved no  
  Call Number Admin @ si @ ART2013 Serial 2224  
Permanent link to this record
 
 
Author Gemma Roig; Xavier Boix; R. de Nijs; Sebastian Ramos; K. Kühnlenz; Luc Van Gool edit   pdf
doi  openurl
  Title Active MAP Inference in CRFs for Efficient Semantic Segmentation Type Conference Article
  Year (down) 2013 Publication 15th IEEE International Conference on Computer Vision Abbreviated Journal  
  Volume Issue Pages 2312 - 2319  
  Keywords Semantic Segmentation  
  Abstract Most MAP inference algorithms for CRFs optimize an energy function knowing all the potentials. In this paper, we focus on CRFs where the computational cost of instantiating the potentials is orders of magnitude higher than MAP inference. This is often the case in semantic image segmentation, where most potentials are instantiated by slow classifiers fed with costly features. We introduce Active MAP inference 1) to on-the-fly select a subset of potentials to be instantiated in the energy function, leaving the rest of the parameters of the potentials unknown, and 2) to estimate the MAP labeling from such incomplete energy function. Results for semantic segmentation benchmarks, namely PASCAL VOC 2010 [5] and MSRC-21 [19], show that Active MAP inference achieves similar levels of accuracy but with major efficiency gains.  
  Address Sydney; Australia; December 2013  
  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 1550-5499 ISBN Medium  
  Area Expedition Conference ICCV  
  Notes ADAS; 600.057 Approved no  
  Call Number ADAS @ adas @ RBN2013 Serial 2377  
Permanent link to this record
 
 
Author Jiaolong Xu; David Vazquez; Antonio Lopez; Javier Marin; Daniel Ponsa edit   pdf
doi  isbn
openurl 
  Title Learning a Multiview Part-based Model in Virtual World for Pedestrian Detection Type Conference Article
  Year (down) 2013 Publication IEEE Intelligent Vehicles Symposium Abbreviated Journal  
  Volume Issue Pages 467 - 472  
  Keywords Pedestrian Detection; Virtual World; Part based  
  Abstract State-of-the-art deformable part-based models based on latent SVM have shown excellent results on human detection. In this paper, we propose to train a multiview deformable part-based model with automatically generated part examples from virtual-world data. The method is efficient as: (i) the part detectors are trained with precisely extracted virtual examples, thus no latent learning is needed, (ii) the multiview pedestrian detector enhances the performance of the pedestrian root model, (iii) a top-down approach is used for part detection which reduces the searching space. We evaluate our model on Daimler and Karlsruhe Pedestrian Benchmarks with publicly available Caltech pedestrian detection evaluation framework and the result outperforms the state-of-the-art latent SVM V4.0, on both average miss rate and speed (our detector is ten times faster).  
  Address Gold Coast; Australia; June 2013  
  Corporate Author Thesis  
  Publisher IEEE Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 1931-0587 ISBN 978-1-4673-2754-1 Medium  
  Area Expedition Conference IV  
  Notes ADAS; 600.054; 600.057 Approved no  
  Call Number XVL2013; ADAS @ adas @ xvl2013a Serial 2214  
Permanent link to this record
 
 
Author Patricia Marquez; Debora Gil; Aura Hernandez-Sabate; Daniel Kondermann edit   pdf
url  doi
isbn  openurl
  Title When Is A Confidence Measure Good Enough? Type Conference Article
  Year (down) 2013 Publication 9th International Conference on Computer Vision Systems Abbreviated Journal  
  Volume 7963 Issue Pages 344-353  
  Keywords Optical flow, confidence measure, performance evaluation  
  Abstract Confidence estimation has recently become a hot topic in image processing and computer vision.Yet, several definitions exist of the term “confidence” which are sometimes used interchangeably. This is a position paper, in which we aim to give an overview on existing definitions,
thereby clarifying the meaning of the used terms to facilitate further research in this field. Based on these clarifications, we develop a theory to compare confidence measures with respect to their quality.		  
  Address St Petersburg; Russia; July 2013  
  Corporate Author Thesis  
  Publisher Springer Link Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-642-39401-0 Medium  
  Area Expedition Conference ICVS  
  Notes IAM;ADAS; 600.044; 600.057; 600.060; 601.145 Approved no  
  Call Number IAM @ iam @ MGH2013a Serial 2218  
Permanent link to this record
 
 
Author David Vazquez; Jiaolong Xu; Sebastian Ramos; Antonio Lopez; Daniel Ponsa edit   pdf
doi  openurl
  Title Weakly Supervised Automatic Annotation of Pedestrian Bounding Boxes Type Conference Article
  Year (down) 2013 Publication CVPR Workshop on Ground Truth – What is a good dataset? Abbreviated Journal  
  Volume Issue Pages 706 - 711  
  Keywords Pedestrian Detection; Domain Adaptation  
  Abstract Among the components of a pedestrian detector, its trained pedestrian classifier is crucial for achieving the desired performance. The initial task of the training process consists in collecting samples of pedestrians and background, which involves tiresome manual annotation of pedestrian bounding boxes (BBs). Thus, recent works have assessed the use of automatically collected samples from photo-realistic virtual worlds. However, learning from virtual-world samples and testing in real-world images may suffer the dataset shift problem. Accordingly, in this paper we assess an strategy to collect samples from the real world and retrain with them, thus avoiding the dataset shift, but in such a way that no BBs of real-world pedestrians have to be provided. In particular, we train a pedestrian classifier based on virtual-world samples (no human annotation required). Then, using such a classifier we collect pedestrian samples from real-world images by detection. After, a human oracle rejects the false detections efficiently (weak annotation). Finally, a new classifier is trained with the accepted detections. We show that this classifier is competitive with respect to the counterpart trained with samples collected by manually annotating hundreds of pedestrian BBs.  
  Address Portland; Oregon; June 2013  
  Corporate Author Thesis  
  Publisher IEEE Place of Publication Editor  
  Language English Summary Language English Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference CVPRW  
  Notes ADAS; 600.054; 600.057; 601.217 Approved no  
  Call Number ADAS @ adas @ VXR2013a Serial 2219  
Permanent link to this record
 
 
Author Jiaolong Xu; David Vazquez; Sebastian Ramos; Antonio Lopez; Daniel Ponsa edit   pdf
doi  openurl
  Title Adapting a Pedestrian Detector by Boosting LDA Exemplar Classifiers Type Conference Article
  Year (down) 2013 Publication CVPR Workshop on Ground Truth – What is a good dataset? Abbreviated Journal  
  Volume Issue Pages 688 - 693  
  Keywords Pedestrian Detection; Domain Adaptation  
  Abstract Training vision-based pedestrian detectors using synthetic datasets (virtual world) is a useful technique to collect automatically the training examples with their pixel-wise ground truth. However, as it is often the case, these detectors must operate in real-world images, experiencing a significant drop of their performance. In fact, this effect also occurs among different real-world datasets, i.e. detectors' accuracy drops when the training data (source domain) and the application scenario (target domain) have inherent differences. Therefore, in order to avoid this problem, it is required to adapt the detector trained with synthetic data to operate in the real-world scenario. In this paper, we propose a domain adaptation approach based on boosting LDA exemplar classifiers from both virtual and real worlds. We evaluate our proposal on multiple real-world pedestrian detection datasets. The results show that our method can efficiently adapt the exemplar classifiers from virtual to real world, avoiding drops in average precision over the 15%.  
  Address Portland; oregon; June 2013  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language English Summary Language English Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference CVPRW  
  Notes ADAS; 600.054; 600.057; 601.217 Approved yes  
  Call Number XVR2013; ADAS @ adas @ xvr2013a Serial 2220  
Permanent link to this record
 
 
Author Katerine Diaz; Francesc J. Ferri; W. Diaz edit  doi
isbn  openurl
  Title Fast Approximated Discriminative Common Vectors using rank-one SVD updates Type Conference Article
  Year (down) 2013 Publication 20th International Conference On Neural Information Processing Abbreviated Journal  
  Volume 8228 Issue III Pages 368-375  
  Keywords  
  Abstract An efficient incremental approach to the discriminative common vector (DCV) method for dimensionality reduction and classification is presented. The proposal consists of a rank-one update along with an adaptive restriction on the rank of the null space which leads to an approximate but convenient solution. The algorithm can be implemented very efficiently in terms of matrix operations and space complexity, which enables its use in large-scale dynamic application domains. Deep comparative experimentation using publicly available high dimensional image datasets has been carried out in order to properly assess the proposed algorithm against several recent incremental formulations.
K. Diaz-Chito, F.J. Ferri, W. Diaz		  
  Address Daegu; Korea; November 2013  
  Corporate Author Thesis  
  Publisher Springer Berlin Heidelberg Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-642-42050-4 Medium  
  Area Expedition Conference ICONIP  
  Notes ADAS Approved no  
  Call Number Admin @ si @ DFD2013 Serial 2439  
Permanent link to this record
 
 
Author Marcelo D. Pistarelli; Angel Sappa; Ricardo Toledo edit  doi
isbn  openurl
  Title Multispectral Stereo Image Correspondence Type Conference Article
  Year (down) 2013 Publication 15th International Conference on Computer Analysis of Images and Patterns Abbreviated Journal  
  Volume 8048 Issue Pages 217-224  
  Keywords  
  Abstract This paper presents a novel multispectral stereo image correspondence approach. It is evaluated using a stereo rig constructed with a visible spectrum camera and a long wave infrared spectrum camera. The novelty of the proposed approach lies on the usage of Hough space as a correspondence search domain. In this way it avoids searching for correspondence in the original multispectral image domains, where information is low correlated, and a common domain is used. The proposed approach is intended to be used in outdoor urban scenarios, where images contain large amount of edges. These edges are used as distinctive characteristics for the matching in the Hough space. Experimental results are provided showing the validity of the proposed approach.  
  Address York; uk; August 2013  
  Corporate Author Thesis  
  Publisher Springer Berlin Heidelberg Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-642-40245-6 Medium  
  Area Expedition Conference CAIP  
  Notes ADAS; 600.055 Approved no  
  Call Number Admin @ si @ PST2013 Serial 2561  
Permanent link to this record
Select All    Deselect All << 1 2 3 4 5 6 7 8 9 10 >> [11–20]
List View
 | 
Citations
 | 
Details
toggle visibility
Save Citations:
Export Records: