Search results for "vision."
showing 10 items of 4900 documents
Fuzzy-logic-based approach for identifying objects of interest in the PRIDE framework
2008
On-road autonomous vehicle navigation requires real-time motion planning in the presence of static and moving objects. Based on sensed data of the environment and the current traffic situation, an autonomous vehicle has to plan a path by predicting the future location of objects of interest. In this context, an object of interest is a moving or stationary object in the environment that has a reasonable probability of intersecting the path of the autonomous vehicle within a predetermined time frame. This paper investigates the identification of objects of interest within the PRIDE (PRediction In Dynamic Environments) framework. PRIDE is a multi-resolutional, hierarchical framework that predi…
Improving color correction across camera and illumination changes by contextual sample selection
2012
International audience; In many tasks of machine vision applications, it is important that recorded colors remain constant, in the real world scene, even under changes of the illuminants and the cameras. Contrary to the human vision system, a machine vision system exhibits inadequate adaptability to the variation of lighting conditions. Automatic white bal- ance control available in commercial cameras is not sufficient to pro- vide reproducible color classification. We address this problem of color constancy on a large image database acquired with varying digi- tal cameras and lighting conditions. A device-independent color repre- sentation may be obtained by applying a chromatic adaptation…
Mathematical Morphology for Color Images: An Image-Dependent Approach
2012
This paper proposes one possibility to generalize the morphological operations (particularly, dilation, erosion, opening, and closing) to color images. First, properties of a desirable generalization are stated and a brief review is done on former approaches. Then, the method is explained, which is based on a total ordering of the colors in an image induced by its color histogram; this is valid for just one image and may present problems in smoothly coloured images. To solve these drawbacks a refinement consisting of smoothing the histogram and using a joint histogram of several images is presented. Results of applying the so-defined morphological operations on several sets of images are sh…
Multichannel single-output color pattern recognition by use of a joint-transform correlator.
1996
A novel method for performing color image recognition by the use of the coherent joint-transform correlator is introduced. The input plane of the proposed method is a spatial rearrangement of the separation into color channels of both the color input scene and the color target. This input plane is gray scaled and monochromatic, thus it can be displayed by the use of amplitude spatial light modulators to achieve real-time operation. The system provides a single output-plane result of the optical coherent addition of the separate channels’ correlation outputs. At the output plane no electronic postprocessing is needed, and the detection decision is achieved simply by the application of thresh…
Multi-channel chromatic transformations for nonlinear color pattern recognition
2002
We present a new approach for color pattern recognition based on multi-channel nonlinear correlations. High discrimination capability is obtained in comparison with common linear multi-channel detection methods. We apply the nonlinear morphological correlation to different color channel decompositions as RGB and ATD channels. Moreover, in order to improve the discrimination we have introduced a new color transformation. When a high selectivity is required, the combination of the nonlinear correlation and the new color decomposition yields to detect the object using just a single channel. Simulation results are provided.
A Gamut Preserving Color Image Quantization
2007
International audience; We propose a new approach for color image quantization which preserves the shape of the color gamut of the studied image. Quantization consists to find a set of color representative of the color distribution of the image. We are looking here for an optimal LUT (look up table) which contains information on the image's gamut and on the color distribution of this image. The main motivation of this work is to control the reproduction of color images on different output devices in order to have the same color feeling, coupling intrinsic informations on the image gamut and output device calibration. We have developped a color quantization algorithm based on an image depend…
A Combinatorial Color Edge Detector
2004
In this paper, we present an edge detection approach in color image using neighborhood hypergraph. The edge structure is detected by a structural model. The Color Image Neighborhood Hypergraph (CINH) representation is first computed, then the hyperedges of CINH are classified into noise or edge based on hypergraph properties. To evaluate the algorithm performance, experiments were carried out on synthetic and real color images corrupted by alpha-stable noise. The results show that the proposed edge detector finds the edges properly from color images.
Semantic and topological classification of images in magnetically guided capsule endoscopy
2012
International audience; Magnetically-guided capsule endoscopy (MGCE) is a nascent technology with the goal to allow the steering of a capsule endoscope inside a water filled stomach through an external magnetic field. We developed a classification cascade for MGCE images with groups images in semantic and topological categories. Results can be used in a post-procedure review or as a starting point for algorithms classifying pathologies. The first semantic classification step discards over-/under-exposed images as well as images with a large amount of debris. The second topological classification step groups images with respect to their position in the upper gastrointestinal tract (mouth, es…
Color and Flow Based Superpixels for 3D Geometry Respecting Meshing
2014
We present an adaptive weight based superpixel segmentation method for the goal of creating mesh representation that respects the 3D scene structure. We propose a new fusion framework which employs both dense optical flow and color images to compute the probability of boundaries. The main contribution of this work is that we introduce a new color and optical flow pixel-wise weighting model that takes into account the non-linear error distribution of the depth estimation from optical flow. Experiments show that our method is better than the other state-of-art methods in terms of smaller error in the final produced mesh.
Karhunen-Loe`ve transform applied to region-based segmentation of color aerial images
2001
The use of the Karhunen-Loeve transform (KLT) for region- based segmentation of aerial images by color and textural attributes is presented. Our aerial images are shown to be homogeneous color im- ages within the Karhunen-Loeve color representation space, which means they can be represented more easily and the region-based seg- mentation algorithms can be optimized. For texture analysis, the KLT is the basis of the local linear transform (LLT) and allows structural infor- mation about textures to be represented in an optimal and condensed manner. The LLT provides a system of textural analysis in the form of an adapted filter bank. We end the paper by presenting a method for merg- ing textur…