Search results for "Computer Science::Computer Vision and Pattern Recognition"
showing 10 items of 193 documents
Spatially variant dimensionality reduction for the visualization of multi/hyperspectral images
2011
International audience; In this paper, we introduce a new approach for color visu- alization of multi/hyperspectral images. Unlike traditional methods, we propose to operate a local analysis instead of considering that all the pixels are part of the same population. It takes a segmentation map as an input and then achieves a dimensionality reduction adaptively inside each class of pixels. Moreover, in order to avoid unappealing discon- tinuities between regions, we propose to make use of a set of distance transform maps to weigh the mapping applied to each pixel with regard to its relative location with classes' centroids. Results on two hyperspec- tral datasets illustrate the efficiency of…
A nonlinear oscillators network devoted to image processing
2004
A contrast enhancement and image inverting tool using a lattice of uncoupled nonlinear oscillators is proposed. We show theoretically and numerically that the gray scale picture contrast is strongly enhanced even if this one is initially very small. An image inversion can be also obtained in real time with the same Cellular Nonlinear Network (CNN) without reconfiguration of the network. A possible electronic implementation of this CNN is finally discussed.
AN APPROACH TO CORRECTING IMAGE DISTORTION BY SELF CALIBRATION STEREOSCOPIC SCENE FROM MULTIPLE VIEWS
2012
International audience; An important step in the analysis and interpretation of video scenes for recognizing scenario is the aberration corrections introduced during the image acquisition in order to provide and correct real image data. This paper presents an approach on distortion correction based on stereoscopic self calibration from images sequences by using a multi-camera system of vision (network cameras). This approach for correcting image distortion brings an elegant and robust technique with good accuracy. Without any knowledge of shooting conditions, the camera's parameters will be estimated. For this, the image key points of interest are extracted from different overlapping views …
Wavelet Decomposition in Laplacian Pyramid for Image Fusion
2016
International audience; The aim of image fusion is to combine information from the set of images to get a single image which contains a more accurate description than any individual source image. While the scene contains objects in different focus due to the limited depth-of-focus of optical lenses in camera then by using image fusion technique we can get an image which has better focus across all area. In this paper, a multifocus image fusion method using combination Laplacian pyramid and wavelet decomposition is proposed. The fusion process contains the following steps: first, the multifocus images are decomposed using Laplacian pyramid into several levels of pyramid. Then at each level o…
On Keyframe Positioning for Pose Graphs Applied to Visual SLAM
2013
International audience; In this work, a new method is introduced for localization and keyframe identification to solve a Simultaneous Localization and Mapping (SLAM) problem. The proposed approach is based on a dense spherical acquisition system that synthesizes spherical intensity and depth images at arbitrary locations. The images are related by a graph of 6 degrees-of-freedom (DOF) poses which are estimated through spherical registration. A direct image-based method is provided to estimate pose by using both depth and color information simultaneously. A new keyframe identification method is proposed to build the map of the environment by using the covariance matrix between raletive 6 DOF…
Multi-Scale Feature Extraction for Vehicle Detection Using Phis-Lbp
2018
International audience; Multi-resolutionobjectdetectionfacesseveraldrawbacksincludingitshighdimensionalityproducedby a richer image representation in different channels or scales. In this paper, we propose a robust and lightweight multi-resolution method for vehicle detection using local binary patterns (LBP) as channel feature. Algorithm acceleration is done using LBP histograms instead of multi-scale feature maps and by extrapolating nearby scales to avoid computing each scale. We produce a feature descriptor capable of reaching a similar precision to other computationally more complex algorithms but reducing its size from 10 to 800 times. Finally, experiments show that our method can obt…
Motion estimation and reconstruction of piecewise planar scenes from two views
2010
The task of recovering the camera motion relative to the environment (motion estimation) is fundamental to many computer vision applications. We present an algorithm for reconstruction of piece-wise planar scenes from only two views and based on minimum line correspondences. We first recover camera rotation by matching vanishing points based on the methods already exist in the literature and then recover the camera translation by searching among a family of hypothesized planes passing through one line. Unlike algorithms based on line segments, the presented algorithm does not require an overlap between two line segments or more than one line correspondence across more than two views to reco…
Robustness of texture parameters for color texture analysis
2006
This article proposes to deal with noisy and variable size color textures. It also proposes to deal with quantization methods and to see how such methods change final results. The method we use to analyze the robustness of the textures consists of an auto-classification of modified textures. Texture parameters are computed for a set of original texture samples and stored into a database. Such a database is created for each quantization method. Textures from the set of original samples are then modified, eventually quantized and classified according to classes determined from a precomputed database. A classification is considered incorrect if the original texture is not retrieved. This metho…
Noise Robustness Analysis of Point Cloud Descriptors
2013
In this paper, we investigate the effect of noise on 3D point cloud descriptors. Various types of point cloud descriptors have been introduced in the recent years due to advances in computing power, which makes processing point cloud data more feasible. Most of these descriptors describe the orientation difference between pairs of 3D points in the object and represent these differences in a histogram. Earlier studies dealt with the performances of different point cloud descriptors; however, no study has ever discussed the effect of noise on the descriptors performances. This paper presents a comparison of performance for nine different local and global descriptors amidst 10 varying levels o…
GHOST: GRADIENT HISTOGRAM OF SPECTRAL TEXTURE
2021
International audience; A gradient-based texture feature for hyperspectral image is formulated with straightforward application to grayscale and color images. Processed in full band, GHOST is expressed as a four-dimensional probability density distribution encompassing joint metrological assessment of spectral and spatial properties. Its performance is close to Opponent Band Local Binary Pattern (OBLBP) in HyTexiLa texture classification (91 %-99 % accuracy) with feature size 0.2 % of OBLBP's.