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 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 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 (down) 2219  
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 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 (down) 2218  
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 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 (down) 2214  
Permanent link to this record
 
 
Author Jose Manuel Alvarez; Y. LeCun; Theo Gevers; Antonio Lopez edit   pdf
doi  isbn
openurl 
  Title Semantic Road Segmentation via Multi-Scale Ensembles of Learned Features Type Conference Article
  Year 2012 Publication 12th European Conference on Computer Vision – Workshops and Demonstrations Abbreviated Journal  
  Volume 7584 Issue Pages 586-595  
  Keywords road detection  
  Abstract Semantic segmentation refers to the process of assigning an object label (e.g., building, road, sidewalk, car, pedestrian) to every pixel in an image. Common approaches formulate the task as a random field labeling problem modeling the interactions between labels by combining local and contextual features such as color, depth, edges, SIFT or HoG. These models are trained to maximize the likelihood of the correct classification given a training set. However, these approaches rely on hand–designed features (e.g., texture, SIFT or HoG) and a higher computational time required in the inference process.
Therefore, in this paper, we focus on estimating the unary potentials of a conditional random field via ensembles of learned features. We propose an algorithm based on convolutional neural networks to learn local features from training data at different scales and resolutions. Then, diversification between these features is exploited using a weighted linear combination. Experiments on a publicly available database show the effectiveness of the proposed method to perform semantic road scene segmentation in still images. The algorithm outperforms appearance based methods and its performance is similar compared to state–of–the–art methods using other sources of information such as depth, motion or stereo.		  
  Address  
  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 978-3-642-33867-0 Medium  
  Area Expedition Conference ECCVW  
  Notes ADAS;ISE Approved no  
  Call Number Admin @ si @ ALG2012; ADAS @ adas Serial (down) 2187  
Permanent link to this record
 
 
Author Miguel Oliveira; V.Santos; Angel Sappa edit  openurl
  Title Short term path planning using a multiple hypothesis evaluation approach for an autonomous driving competition Type Conference Article
  Year 2012 Publication IEEE 4th Workshop on Planning, Perception and Navigation for Intelligent Vehicles Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Algarve; Portugal  
  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 PPNIV  
  Notes ADAS Approved no  
  Call Number Admin @ si @ OSS2012c Serial (down) 2159  
Permanent link to this record
 
 
Author Mohammad Rouhani; Angel Sappa edit  doi
isbn  openurl
  Title Non-Rigid Shape Registration: A Single Linear Least Squares Framework Type Conference Article
  Year 2012 Publication 12th European Conference on Computer Vision Abbreviated Journal  
  Volume 7578 Issue Pages 264-277  
  Keywords  
  Abstract This paper proposes a non-rigid registration formulation capturing both global and local deformations in a single framework. This formulation is based on a quadratic estimation of the registration distance together with a quadratic regularization term. Hence, the optimal transformation parameters are easily obtained by solving a liner system of equations, which guarantee a fast convergence. Experimental results with challenging 2D and 3D shapes are presented to show the validity of the proposed framework. Furthermore, comparisons with the most relevant approaches are provided.  
  Address Florencia  
  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 978-3-642-33785-7 Medium  
  Area Expedition Conference ECCV  
  Notes ADAS Approved no  
  Call Number Admin @ si @ RoS2012a Serial (down) 2158  
Permanent link to this record
 
 
Author Monica Piñol; Angel Sappa; Ricardo Toledo edit   pdf
doi  isbn
openurl 
  Title MultiTable Reinforcement for Visual Object Recognition Type Conference Article
  Year 2012 Publication 4th International Conference on Signal and Image Processing Abbreviated Journal  
  Volume 221 Issue Pages 469-480  
  Keywords  
  Abstract This paper presents a bag of feature based method for visual object recognition. Our contribution is focussed on the selection of the best feature descriptor. It is implemented by using a novel multi-table reinforcement learning method that selects among five of classical descriptors (i.e., Spin, SIFT, SURF, C-SIFT and PHOW) the one that best describes each image. Experimental results and comparisons are provided showing the improvements achieved with the proposed approach.  
  Address Coimbatore, India  
  Corporate Author Thesis  
  Publisher Springer India Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN 1876-1100 ISBN 978-81-322-0996-6 Medium  
  Area Expedition Conference ICSIP  
  Notes ADAS Approved no  
  Call Number Admin @ si @ PST2012 Serial (down) 2157  
Permanent link to this record
 
 
Author Jose Carlos Rubio; Joan Serrat; Antonio Lopez edit   pdf
doi  isbn
openurl 
  Title Video Co-segmentation Type Conference Article
  Year 2012 Publication 11th Asian Conference on Computer Vision Abbreviated Journal  
  Volume 7725 Issue Pages 13-24  
  Keywords  
  Abstract Segmentation of a single image is in general a highly underconstrained problem. A frequent approach to solve it is to somehow provide prior knowledge or constraints on how the objects of interest look like (in terms of their shape, size, color, location or structure). Image co-segmentation trades the need for such knowledge for something much easier to obtain, namely, additional images showing the object from other viewpoints. Now the segmentation problem is posed as one of differentiating the similar object regions in all the images from the more varying background. In this paper, for the first time, we extend this approach to video segmentation: given two or more video sequences showing the same object (or objects belonging to the same class) moving in a similar manner, we aim to outline its region in all the frames. In addition, the method works in an unsupervised manner, by learning to segment at testing time. We compare favorably with two state-of-the-art methods on video segmentation and report results on benchmark videos.  
  Address Daejeon, Korea  
  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 978-3-642-37443-2 Medium  
  Area Expedition Conference ACCV  
  Notes ADAS Approved no  
  Call Number Admin @ si @ RSL2012d Serial (down) 2153  
Permanent link to this record
 
 
Author Karel Paleček; David Geronimo; Frederic Lerasle edit  doi
isbn  openurl
  Title Pre-attention cues for person detection Type Conference Article
  Year 2012 Publication Cognitive Behavioural Systems, COST 2102 International Training School Abbreviated Journal  
  Volume Issue Pages 225-235  
  Keywords  
  Abstract Current state-of-the-art person detectors have been proven reliable and achieve very good detection rates. However, the performance is often far from real time, which limits their use to low resolution images only. In this paper, we deal with candidate window generation problem for person detection, i.e. we want to reduce the computational complexity of a person detector by reducing the number of regions that has to be evaluated. We base our work on Alexe’s paper [1], which introduced several pre-attention cues for generic object detection. We evaluate these cues in the context of person detection and show that their performance degrades rapidly for scenes containing multiple objects of interest such as pictures from urban environment. We extend this set by new cues, which better suits our class-specific task. The cues are designed to be simple and efficient, so that they can be used in the pre-attention phase of a more complex sliding window based person detector.  
  Address Dresden, Germany  
  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 978-3-642-34583-8 Medium  
  Area Expedition Conference COST-TS  
  Notes ADAS Approved no  
  Call Number Admin @ si @ PGL2012 Serial (down) 2148  
Permanent link to this record
 
 
Author Ferran Diego; G.D. Evangelidis; Joan Serrat edit   pdf
url  openurl
  Title Night-time outdoor surveillance by mobile cameras Type Conference Article
  Year 2012 Publication 1st International Conference on Pattern Recognition Applications and Methods Abbreviated Journal  
  Volume 2 Issue Pages 365-371  
  Keywords  
  Abstract This paper addresses the problem of video surveillance by mobile cameras. We present a method that allows online change detection in night-time outdoor surveillance. Because of the camera movement, background frames are not available and must be “localized” in former sequences and registered with the current frames. To this end, we propose a Frame Localization And Registration (FLAR) approach that solves the problem efficiently. Frames of former sequences define a database which is queried by current frames in turn. To quickly retrieve nearest neighbors, database is indexed through a visual dictionary method based on the SURF descriptor. Furthermore, the frame localization is benefited by a temporal filter that exploits the temporal coherence of videos. Next, the recently proposed ECC alignment scheme is used to spatially register the synchronized frames. Finally, change detection methods apply to aligned frames in order to mark suspicious areas. Experiments with real night sequences recorded by in-vehicle cameras demonstrate the performance of the proposed method and verify its efficiency and effectiveness against other methods.  
  Address Algarve, Portugal  
  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 ICPRAM  
  Notes ADAS Approved no  
  Call Number Admin @ si @ DES2012 Serial (down) 2035  
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: