Search results for "ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION"
showing 10 items of 982 documents
Attention-Based Landmark Selection in Autonomous Robotics
2007
This paper describes a robotic architecture that uses visual attention mechanisms for autonomous navigation in unknown indoor environments. A foveation mechanism based on a bottom-up attention system allows the robot to autonomously select landmarks, defined as salient points in the camera images. Landmarks are memorized in a behavioral fashion by coupling sensing and acting to achieve a representation that is view and scale independent. Selected landmarks are stored in a topological map. During the navigation a top-down mechanism controls the attention system to achieve robot localization. Experiments and results show that our system is robust to noise and odometric errors, being at the sa…
Attention-based environment perception in autonomous robotics
2007
This paper describes a robotic architecture that uses visual attention mechanisms for autonomous navigation in unknown indoor environments. A foveation mechanism based on classical bottom-up gaze shifts allows the robot to autonomously select landmarks, defined as salient points in the camera images. Landmarks are memorized in a behavioral fashion, coupling sensing and acting to achieve a representation view and scale independent. Selected landmarks are stored in a topological map; during the navigation a top-down mechanism controls the attention system to achieve robot localization. Experiments and results show that our system is robust to noise and odometric errors, being at the same time…
MultiSlice human organ extraction based on GVF
2008
Segmentation techniques based on active contours algorithm are widely used in medical imaging. Unfortunately, they require a lot of parameters to be used and this can rep- resent an issue for those physicians with not much informatics skills. This paper proposes a software tool which allows to segment multiple slice can differ organ extraction setting a small number of parameters. Moreover, the tool offers the functionality to perform a multiple segmentation the same time, so that an entire volume composed by hundreds slices can be segmented.
Chapter 11: Affect and Mathematical Modeling Assessment: A Case Study on Engineering Students’ Experience of Challenge and Flow During a Compulsory M…
2019
This chapter describes a study on engineering students’ affect while working on the Tracker Project Task, a group assessment task that asks students (1) to use digital tools (the camera in their smart phones and free tracker software) to capture the movement of an object, (2) to mathematically model that movement, and (3) to create a poster reporting on the video analysis of the movement.
Shaded-Mask Filtering for Extended Depth-of-Field Microscopy
2013
This paper proposes a new spatial filtering approach for increasing the depth-of-field (DOF) of imaging systems, which is very useful for obtaining sharp images for a wide range of axial positions of the object. Many different techniques have been reported to increase the depth of field. However the main advantage in our method is its simplicity, since we propose the use of purely absorbing beam-shaping elements, which allows a high focal depth with a minimum modification of the optical architecture. In the filter design, we have used the analogy between the axial behavior of a system with spherical aberration and the transverse impulse response of a 1D defocused system. This allowed us the…
Single-channel polychromatic pattern recognition by the use of a joint-transform correlator.
2010
We present a single-channel system for color image recognition that is based on a joint-transform correlator setup. The color images are encoded as phase and amplitude functions, inspired from the Munsell color representation. A real-time implementation of the new codification method can be achieved by the use of a spatial light modulator operating in phase-only modulation mode. We determine the optimal codification for a linear color-phase code. Its performance is compared with a conventional multichannel correlator by means of computer simulations. Experimental results are also presented.
Super Resolution Methods Implementing Diffractive Masks Having a Certain Degree of Periodicity
2011
This section presents an approach that provides super resolved imaging at the center of the field of view and yet allows to see the remaining of the original field of view with original resolution. This operation resembles optical zooming while the zoomed and the nonzoomed images are obtained simultaneously. This is obtained by taking a single snap-shot and using a single imaging lens. The technique utilizes a special static/still coding element and a postprocessing algorithmic, without any mechanical movements.
Salient Pixels and Dimensionality Reduction for Display of Multi/Hyperspectral Images
2012
International audience; Dimensionality Reduction (DR) of spectral images is a common approach to different purposes such as visualization, noise removal or compression. Most methods such as PCA or band selection use either the entire population of pixels or a uniformly sampled subset in order to compute a projection matrix. By doing so, spatial information is not accurately handled and all the objects contained in the scene are given the same emphasis. Nonetheless, it is possible to focus the DR on the separation of specific Objects of Interest (OoI), simply by neglecting all the others. In PCA for instance, instead of using the variance of the scene in each spectral channel, we show that i…
Salient Spin Images: A Descriptor for 3D Object Recognition
2018
In the last decades a wide range of algorithms have been devoted to recognize 3D free-from objects under real conditions such as occlusions, clutters, rotation, scale and translation. Spin image is one of these algorithms known to be robust to rotation, translation, occlusions up to 70% and clutters up to 60%, but still suffer from scaling, resolution changes and it is time consuming. In this paper we present a novel approach based on spin images, called salient spin images (SSI). This method enhances spin images algorithm based on its limits. Particularly, it decreases significantly the complexity of the algorithm using DoG detector, it shows a higher performance due to the relevant locali…
Periodic Orthogonal Wavelets and Wavelet Packets
2018
In this chapter, we discuss how to derive versatile families of periodic discrete-time orthogonal wavelets and wavelet packets from discrete and discrete-time splines outlined in Chap. 3. These wavelets and wavelet packets, although not having compact supports, are well localized in the time domain. They can have any number of discrete vanishing moments. Their DFT spectra tend to have a rectangular shape when the spline order grows and provide a collection of refined splits of the Nyquist frequency band. The wavelet and wavelet packet transforms are implemented in a fast way using the FFT.