Search results for "VISION"
showing 10 items of 5066 documents
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…
The iterative object symmetry transform
2005
This paper introduces a new operator named the Iterated Object Transform that is computed by combining the Object Symmetry Transform with the morphological operator erosion. This new operator has been applied on both binary and gray levels images showing the ability to grasp the internal structure of a digital object. We present some experiments on real images in face analysis.
Saliency Based Aesthetic Cut of Digital Images
2013
Aesthetic cut of photos is a process well known to professional photographers. It consists of cutting the original photo to remove less relevant parts close to the borders leaving in this way the interesting subjects in a position that is perceived by the observer as more pleasant. In this paper we propose a saliency based technique to automatically perform aesthetic cut in images. We use a standard method to estimate the saliency map and propose some post processing on the map to make it more suitable for our scope. We then apply a greedy algorithm to determine the cut (i.e. the most important part of the original image) both in the cases of free and fixed aspect ratio. Experimental result…
Splitting criterion for hierarchical motion estimation based on perceptual coding
1998
A new entropy-constrained motion estimation scheme using variable-size block matching is proposed. It is known that fixed-size block matching as used in most video codec standards is improved by using a multiresolution or multigrid approach. In this work, it is shown that further improvement is possible in terms of both the final bit rate achieved and the robustness of the predicted motion field if perceptual coding is taken into account in the motion estimation phase. The proposed scheme is compared against other variable- and fixed-size block matching algorithms.
Diversity in search strategies for ensemble feature selection
2005
Ensembles of learnt models constitute one of the main current directions in machine learning and data mining. Ensembles allow us to achieve higher accuracy, which is often not achievable with single models. It was shown theoretically and experimentally that in order for an ensemble to be effective, it should consist of base classifiers that have diversity in their predictions. One technique, which proved to be effective for constructing an ensemble of diverse base classifiers, is the use of different feature subsets, or so-called ensemble feature selection. Many ensemble feature selection strategies incorporate diversity as an objective in the search for the best collection of feature subse…
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…
Plenoptic image watermarking to preserve copyright
2017
Common camera loses a huge amount of information obtainable from scene as it does not record the value of individual rays passing a point and it merely keeps the summation of intensities of all the rays passing a point. Plenoptic images can be exploited to provide a 3D representation of the scene and watermarking such images can be helpful to protect the ownership of these images. In this paper we propose a method for watermarking the plenoptic images to achieve this aim. The performance of the proposed method is validated by experimental results and a compromise is held between imperceptibility and robustness.
Remote Sensing Geometric Corrections
2016
This article reviews the different aspects of geometrical processing of remote sensing data, discussing error sources and methods to determine the transformation from the image acquisition geometry to the output cartographic product. Resampling methods are discussed to transform the input image to the output geometry. Several practical examples of remote sensing platforms are discussed, including satellite cases and airborne sensors. Validation of the resulting geometrical processed products is also discussed. Spatial mosaicking techniques and multitemporal composites used to produce multisource integrated products and advanced applications are finally considered, keeping a perspective on t…
Dynamics of Vertebral Column Observed by Stereovision and Recurrent Neural Network Model
2005
A new non-invasive method for investigation of movement of selected points on the vertebral column is presented. The registration of position of points marked on patient's body is performed by 4 infrared cameras. This experiment enables to reconstruct 3-dimensional trajectories of displacement of marked points. We introduce recurrent neural networks as formal nonlinear dynamical models of each point trajectory. These models are based only on experimental data and are set up of minimal number of parameters. Therefore they are suitable for pattern recognition problems.
Electromagnetic spectrum and color vision
2004
In most of occasions the maps, drawings and printed images are elaborated thinking that the observer will visualize them with illuminants like the light of the day. With these illuminants, for example the CIE D/sub 65/, we can distinguish the great quantity of colors that it is capable the human eye. But if the illuminant has a very different spectrum than the light of day, for example the light of acetylene, the number of colors that we are able to distinguish can decrease drastically.