Scheduled System Maintenance
On Tuesday, September 26, IEEE Xplore will undergo scheduled maintenance from 1:00-4:00 PM ET.
During this time, there may be intermittent impact on performance. We apologize for any inconvenience.

2016 13th Conference on Computer and Robot Vision (CRV)

1-3 June 2016

Filter Results

Displaying Results 1 - 25 of 78
  • [Front cover]

    Publication Year: 2016, Page(s): C4
    Request permission for commercial reuse | PDF file iconPDF (831 KB)
    Freely Available from IEEE
  • [Title page i]

    Publication Year: 2016, Page(s): i
    Request permission for commercial reuse | PDF file iconPDF (12 KB)
    Freely Available from IEEE
  • [Title page iii]

    Publication Year: 2016, Page(s): iii
    Request permission for commercial reuse | PDF file iconPDF (48 KB)
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2016, Page(s): iv
    Request permission for commercial reuse | PDF file iconPDF (119 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2016, Page(s):v - x
    Request permission for commercial reuse | PDF file iconPDF (140 KB)
    Freely Available from IEEE
  • Welcome message

    Publication Year: 2016, Page(s):xi - xii
    Request permission for commercial reuse | PDF file iconPDF (108 KB)
    Freely Available from IEEE
  • Message de Bienvenue

    Publication Year: 2016, Page(s):xiii - xiv
    Request permission for commercial reuse | PDF file iconPDF (92 KB)
    Freely Available from IEEE
  • Conference Organization

    Publication Year: 2016, Page(s): xv
    Request permission for commercial reuse | PDF file iconPDF (76 KB)
    Freely Available from IEEE
  • Program Committee

    Publication Year: 2016, Page(s):xvi - xvii
    Request permission for commercial reuse | PDF file iconPDF (101 KB)
    Freely Available from IEEE
  • Reviewers

    Publication Year: 2016, Page(s):xviii - xix
    Request permission for commercial reuse | PDF file iconPDF (101 KB)
    Freely Available from IEEE
  • Keynotes

    Publication Year: 2016, Page(s):xx - xxi
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (111 KB)

    Provides an abstract for each of the keynote presentations and a brief professional biography of each presenter. The complete presentations were not made available for publication as part of the conference proceedings. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Symposium Talks

    Publication Year: 2016, Page(s):xxii - xxix
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (154 KB)

    Provides an abstract for each of the presentations and a brief professional biography of each presenter. The complete presentations were not made available for publication as part of the conference proceedings. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Awards [6 awards]

    Publication Year: 2016, Page(s):xxx - xxxi
    Request permission for commercial reuse | PDF file iconPDF (103 KB)
    Freely Available from IEEE
  • Conference Schedule

    Publication Year: 2016, Page(s):xxxii - xxxix
    Request permission for commercial reuse | PDF file iconPDF (110 KB)
    Freely Available from IEEE
  • Learning Neural Networks with Ranking-Based Losses for Action Retrieval

    Publication Year: 2016, Page(s):1 - 7
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1470 KB) | HTML iconHTML

    We consider the problem of learning image/video retrieval using a neural network based approach that optimizes the ROC loss function. Neural network is one of the most widely used techniques in computer vision. Standard neural network uses simple loss functions, such as the softmax loss or hinge loss over labels. Such loss functions are suitable for standard classification problems where the perfo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Genaralizing Generative Models: Application to Image Super-Resolution

    Publication Year: 2016, Page(s):8 - 15
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1325 KB) | HTML iconHTML

    Generative models such as neural networks or markov random fields are difficult to extend beyond a limited spatial extent due to the large configuration spaces involved. Their usage in applications such as super resolution is thus problematic, despite their capacity for learning rich descriptions from local receptive fields. For example, due to model complexity, the number of parameters grows expo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dense Image Labeling Using Deep Convolutional Neural Networks

    Publication Year: 2016, Page(s):16 - 23
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1024 KB) | HTML iconHTML

    We consider the problem of dense image labeling. In recent work, many state-of-the-art techniques make use of Deep Convolutional Neural Networks (DCNN) for dense image labeling tasks (e.g. multi-class semantic segmentation) given their capacity to learn rich features. In this paper, we propose a dense image labeling approach based on DCNNs coupled with a support vector classifier. We employ the cl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-Time Human Motion Capture with Multiple Depth Cameras

    Publication Year: 2016, Page(s):24 - 31
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (984 KB) | HTML iconHTML

    Commonly used human motion capture systems require intrusive attachment of markers that are visually tracked with multiple cameras. In this work we present an efficient and inexpensive solution to markerless motion capture using only a few Kinect sensors. Unlike the previous work on 3d pose estimation using a single depth camera, we relax constraints on the camera location and do not assume a co-o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust Non-saliency Guided Watermarking

    Publication Year: 2016, Page(s):32 - 36
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (894 KB) | HTML iconHTML

    A non-saliency guided watermarking approach is introduced where the watermark is embedded in natural images based on three measures, namely, non-saliency, heterogeneity and brightness. The three measures aim to exploit the main characteristics of the human visual system (HVS) for the purpose of embedding watermarks in images. The proposed method has the following advantages: (1) increasing the imp... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sensor Planning for 3D Visual Search with Task Constraints

    Publication Year: 2016, Page(s):37 - 44
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (591 KB) | HTML iconHTML

    Visual search is a fundamental problem in autonomous robotics. Traditionally, visual search is formulated as an optimization problem in which the sequence of actions ischosen based on immediate efficiency. In this paper we examine the effects of the task constraint in the form of maximum allowable cost on action selection in search. We propose three algorithms, namely Greedy Search with Constraint... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Obstacle Detection for Image-Guided Surface Water Navigation

    Publication Year: 2016, Page(s):45 - 52
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1156 KB) | HTML iconHTML

    Maritime safety is an issue of concern when operating a small to medium sized sailboat, and the appearance of hazards in the navigational route like floating logs can lead to a severe collision if undetected. As a precautionary measure to prevent such a collision with a log, a 2D vision-based detection system algorithm presented to detect these floating hazards. We take a combined approach involvi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Indoor Place Recognition System for Localization of Mobile Robots

    Publication Year: 2016, Page(s):53 - 60
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (345 KB) | HTML iconHTML

    In this paper we present a method for robots to do visual place recognition and categorization. The robot learns from experience and then recognizes previously observed places in known environments and categorizes previously unseen places in new environments. This system has been practically tested with a novel dataset developed by us to validate the theoretical results of the proposed system. A H... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Depth Texture Synthesis for Realistic Architectural Modeling

    Publication Year: 2016, Page(s):61 - 68
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5340 KB) | HTML iconHTML

    Large scenes such as building facades and other architectural constructions often contain repeating elements like identical windows, brick patterns, etc. In this paper, we present a novel approach that improves the resolution and geometry of 3D meshes of large scenes with such repeating elements. By leveraging structure from motion reconstruction and an off-the-shelf depth sensor, our approach cap... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dense and Occlusion-Robust Multi-view Stereo for Unstructured Videos

    Publication Year: 2016, Page(s):69 - 76
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (15133 KB) | HTML iconHTML

    We present an efficient multi-view stereo system for dense reconstruction of homogeneous areas from videos with arbitrary camera trajectories. Most techniques have difficulties in recovering textureless areas, weak robustness for occlusion, and low efficiency on the massive redundant data provided by densely sampled frames. Our key idea is to use the measurable depth at object edges to recover the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Aligning 3D Local Data of Leapfrog Locations along Elongated Structures

    Publication Year: 2016, Page(s):77 - 84
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (941 KB) | HTML iconHTML

    This paper presents a registration approach to tackle the problem of rigid alignment of local data acquired from leapfrog locations along elongated structures such as pipelines or other types of pipes. As cylindrical geometry does not have enough constraints for alignment, classical registration algorithms fail to converge since a sliding effect can occur between the views to be aligned. We propos... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.