2017 IEEE International Conference on Image Processing (ICIP)

17-20 Sept. 2017

Filter Results

Displaying Results 1 - 25 of 934
  • [Front cover]

    Publication Year: 2017, Page(s): 1
    Request permission for reuse | PDF file iconPDF (115 KB)
    Freely Available from IEEE
  • [Title page]

    Publication Year: 2017, Page(s): 1
    Request permission for reuse | PDF file iconPDF (112 KB)
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2017, Page(s):ii - iii
    Request permission for reuse | PDF file iconPDF (137 KB)
    Freely Available from IEEE
  • ICIP 2017 organizing committee

    Publication Year: 2017, Page(s): iv
    Request permission for reuse | PDF file iconPDF (125 KB)
    Freely Available from IEEE
  • Technical Program Committee

    Publication Year: 2017, Page(s):v - xvi
    Request permission for reuse | PDF file iconPDF (156 KB)
    Freely Available from IEEE
  • General chair's welcome

    Publication Year: 2017, Page(s):xvii - xix
    Request permission for reuse | PDF file iconPDF (143 KB)
    Freely Available from IEEE
  • Technical program chairs' overview

    Publication Year: 2017, Page(s):xx - xxii
    Request permission for reuse | PDF file iconPDF (139 KB) | HTML iconHTML
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2017, Page(s):xxiii - xcv
    Request permission for reuse | PDF file iconPDF (368 KB)
    Freely Available from IEEE
  • Intra prediction using fully connected network for video coding

    Publication Year: 2017, Page(s):1 - 5
    Cited by:  Papers (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (855 KB) | HTML iconHTML

    Traditional intra prediction methods exploit some fixed rules to generate prediction, which might not be adaptive enough to handle complicated contents. In this paper, we investigate applying deep neural network to improve the state-of-the-art intra prediction. Considering the characteristics of block-based video coding framework, we propose a fully connected network for intra prediction where all... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel angle-restricted test zone search algorithm for performance improvement of HEVC

    Publication Year: 2017, Page(s):6 - 10
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (194 KB) | HTML iconHTML

    High Efficiency Video Coding (HEVC) is the latest video encoding standard and has approximately 50% bit-rate saving compared to its predecessor. However, the motion estimation (ME) is considerably complicated by the incorporation of varieties of partitioning modes and a quad-tree based coding structure, and also by increasing the basic coding unit size by a factor of 16. Motion estimation is the m... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Chroma adjustment for HDR video

    Publication Year: 2017, Page(s):11 - 15
    Cited by:  Papers (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (253 KB) | HTML iconHTML

    This paper describes a pre-processing method for HDR video on linear RGB data before converting to a Y'CbCr 4:2:0 representation. The method targets the luminance artifacts that can arise in saturated colors after compression when PQ Y'CbCr 4:2:0 NCL is used. After processing, the resulting Y'CbCr 4:2:0 representation is also more compressible, leading to objective BD rate results of -2.4%. Subjec... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Probabilistic graphical model based fast HEVC inter prediction

    Publication Year: 2017, Page(s):16 - 20
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (666 KB) | HTML iconHTML

    The High Efficiency Video Coding (HEVC) standard achieves 50% improvement in coding efficiency compared with H.264/ AVC by introducing many more video encoding tools achieving different coding performance and complexity tradeoffs [1]. Various techniques have been proposed to reduce the complexity of HEVC encoding. In this paper, an effective Bayesian network based complexity reduction framework fo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Motion compensation using critically sampled DWT subbands for low-bitrate video coding

    Publication Year: 2017, Page(s):21 - 25
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (726 KB) | HTML iconHTML

    In this paper, we propose a novel motion estimation/motion compensation (ME/MC) method for wavelet-based (i.e. in-band) motion compensated temporal filtering (MCTF), with application to low-bitrate video coding. Unlike the conventional in-band MCTF algorithms, which require redundancy to overcome the shift-variance problem of critically sampled (i.e. complete) discrete wavelet transforms (DWT), we... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-modal/multi-scale convolutional neural network based in-loop filter design for next generation video codec

    Publication Year: 2017, Page(s):26 - 30
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (972 KB) | HTML iconHTML

    In this paper, we propose a novel in-loop filter design for video compression. Our approach aims to replace existing deblocking filter and SAO (Sample Adaptive Offset) of HEVC standard with multi-modal/multi-scale convolutional neural network (MMS-net). The proposed CNN architecture consists of two sub-networks of different scales. An input image is down-sampled first and restored through the lowe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Block-wise lensless compressive camera

    Publication Year: 2017, Page(s):31 - 35
    Cited by:  Papers (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1444 KB) | HTML iconHTML

    The existing lensless compressive camera (L<sup>2</sup>C<sup>2</sup>) [1] suffers from low capture rates, resulting in low resolution images when acquired over a short time. In this work, we propose a new regime to mitigate these drawbacks. We replace the global-based compressive sensing used in the existing L<sup>2</sup>C<sup>2</sup> by the local bl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust plane-based calibration for linear cameras

    Publication Year: 2017, Page(s):36 - 40
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (157 KB) | HTML iconHTML

    A linear, or 1D, camera is a type of camera that sweeps a linear sensor array over the scene, rather than capturing the scene using a single impression on a 2D sensor array. They are often used in satellite imagery, industrial inspection, or hyperspectral imaging. In satellite imaging calibration is often done through a collection of ground points for which the 3D locations are known. In other app... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Enhancement of phase detection for autofocus

    Publication Year: 2017, Page(s):41 - 45
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1933 KB) | HTML iconHTML

    Phase detection autofocus (PDAF) is a technique that uses sensors on left and right pixels to determine the relative position between the object and the focal plane. When an image is out of focus, a shift between the assembled left and right pixels is resulted, which can be used to determine the lens movement during the autofocus process. However, the presence of noise and blur often affects the a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Exponential coordinates based rotation stabilization for panoramic videos

    Publication Year: 2017, Page(s):46 - 50
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (774 KB) | HTML iconHTML

    We propose a practical algorithm for stabilizing panoramic video. We represent a stabilizing rotation by using exponential coordinates and compute the stabilizing rotation for all video frames by smoothing the shaky trajectories of visual features on the panoramic video images. Analytic derivatives of the optimization objective function involving stabilizing rotation matrices are formulated and th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 360-degree video stitching for dual-fisheye lens cameras based on rigid moving least squares

    Publication Year: 2017, Page(s):51 - 55
    Cited by:  Papers (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1347 KB) | HTML iconHTML

    Dual-fisheye lens cameras are becoming popular for 360-degree video capture, especially for User-generated content (UGC), since they are affordable and portable. Images generated by the dual-fisheye cameras have limited overlap and hence require non-conventional stitching techniques to produce high-quality 360×180-degree panoramas. This paper introduces a novel method to align these images using i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Data driven coded aperture design for depth recovery

    Publication Year: 2017, Page(s):56 - 60
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (362 KB) | HTML iconHTML

    Inserting a patterned occluder at the aperture of a camera lens has been shown to improve the recovery of depth map and all-focus image compared to a fully open aperture. However, design of the aperture pattern plays a very critical role. Previous approaches for designing aperture codes make simple assumptions on image distributions to obtain metrics for evaluating aperture codes. However, real im... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient cloud detection in remote sensing images using edge-aware segmentation network and easy-to-hard training strategy

    Publication Year: 2017, Page(s):61 - 65
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (825 KB) | HTML iconHTML

    Detecting cloud regions in remote sensing image (RSI) is very challenging yet of great importance to meteorological forecasting and other RSI-related applications. Technically, this task is typically implemented as a pixel-level segmentation. However, traditional methods based on handcrafted or low-level cloud features often fail to achieve satisfactory performances from images with bright non-clo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust ellipse detection via arc segmentation and classification

    Publication Year: 2017, Page(s):66 - 70
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1182 KB) | HTML iconHTML

    In this paper, we propose a novel ellipse detection algorithm for synthetic and real images. Existing ellipse detection methods are too slow when used with limited hardware resources. The proposed method demonstrates the capability of detecting ellipses with an excellent accuracy at an acceptable speed level in three public datasets. The excellent performance is attributed to the novel combination... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A directed graph approach to active contours

    Publication Year: 2017, Page(s):71 - 75
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (452 KB) | HTML iconHTML

    Active contours based on level sets are popular segmentation algorithms but their local optimization approach makes their results to depend on initialization, especially for edge-based formulations. In this paper we present a novel energy minimization method based on directed graph optimization that minimizes the same type of active contour energy function without the need of an initialization. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Circle detection by arc-support line segments

    Publication Year: 2017, Page(s):76 - 80
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1075 KB) | HTML iconHTML

    Circle detection is fundamental in both object detection and high accuracy localization in visual control systems. We propose a novel method for circle detection by analysing and refining arc-support line segments. The key idea is to use line segment detector to extract the arc-support line segments which are likely to make up the circle, instead of all line segments. Each couple of line segments ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image segmentation using contour, surface, and depth cues

    Publication Year: 2017, Page(s):81 - 85
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (748 KB) | HTML iconHTML

    We target at solving the problem of automatic image segmentation. Although 1D contour and 2D surface cues have been widely utilized in existing work, 3D depth information of an image, a necessary cue according to human visual perception, is however overlooked in automatic image segmentation. In this paper, we study how to fully utilize 1D contour, 2D surface, and 3D depth cues for image segmentati... View full abstract»

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