Search results for "GEP"
showing 10 items of 1017 documents
Multi-illumination single-holographic-exposure lensless Fresnel (MISHELF) microscopy using 4 channels
2021
MISHELF microscopy is generalized by considering 4 illumination/detection channels while retaining single-shot working principle, twin image mitigation and noise averaging. Proof of principle validation is included considering a resolution test target.
CNN-based People Detection in Voxel Space using Intensity Measurements and Point Cluster Flattening
2021
In this paper real-time people detection is demonstrated in a relatively large indoor industrial robot cell as well as in an outdoor environment. Six depth sensors mounted at the ceiling are used to generate a merged point cloud of the cell. The merged point cloud is segmented into clusters and flattened into gray-scale 2D images in the xy and xz planes. These images are then used as input to a classifier based on convolutional neural networks (CNNs). The final output is the 3D position (x,y,z) and bounding box representing the human. The system is able to detect and track multiple humans in real-time, both indoors and outdoors. The positional accuracy of the proposed method has been verifi…
Based on Compton Camera
2016
Compton Cameras have been proposed as an alternative to SPECT imaging with Gamma Camera, mainly due to factors such as the electronic collimation, which allows a bigger field of view and provides further information from the acquired events if compared to devices with mechanical collimation. By contrast, this involves a higher amount of data to be processed. In medical devices this leads to waiting times that are generally higher than desirable by the health-care professionals. In this work we have assessed the reconstruction of Compton images by making use of iterative and non-iterative techniques, and also evaluated its performances as a SPECT imaging technique.
Compressive single-pixel multispectral Stokes polarimeter
2014
We present a single-pixel system that performs polarimetric multispectral imaging with the aid of compressive sensing techniques. We experimentally obtain the full Stokes spatial distribution of a scene for different spectral channels.
The on-board calibration system of the X-ray Imaging Polarimetry Explorer (XIPE)
2016
The calibration system for XIPE is aimed at providing a way to check and correct possible variations of performance of the Gas Pixel Detector during the three years of operation in orbit (plus two years of possible extended operation), while facilitating the observation of the celestial sources. This will be performed by using a filter wheel with a large heritage having a set of positions for the calibration and the observation systems. In particular, it will allow for correcting possible gain variation, for measuring the modulation factor using a polarized source, for removing non interesting bright sources in the field of view and for observing very bright celestial sources. The on-board …
Color Image Segmentation: The Hypergraph Framework
2006
International audience; Color Image Segmentation: The Hypergraph Framework
Eye movements when reading sentences with handwritten words.
2016
The examination of how we read handwritten words (i.e., the original form of writing) has typically been disregarded in the literature on reading. Previous research using word recognition tasks has shown that lexical effects (e.g., the word-frequency effect) are magnified when reading difficult handwritten words. To examine this issue in a more ecological scenario, we registered the participants’ eye movements when reading handwritten sentences that varied in the degree of legibility (i.e., sentences composed of words in easy vs. difficult handwritten style). For comparison purposes, we included a condition with printed sentences. Results showed a larger reading cost for sentences with dif…
Removal of streaking artefact in the images of the Pierre Auger Observatory infra-red cameras
2011
In this paper the problem of removing concentric semi-circular stripe artefacts induced by the operating hardware of the infra red cameras of the Pierre Auger Observatory, is tackled. The method builds on top of a recent algorithm for the removal of artefacts, which presents a robust filter, obtained as a combination of Wavelet and Fourier analysis, capable of eliminating horizontal and vertical stripes in images, while trying to preserve structural features and quantitative values of the image. The method requires several parameters which have been tuned by an exhaustive test on a large set of images. The results show that the method is capable to satisfactorily remove the stripe artefacts.
Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks
2016
This paper proposes Markovian Generative Adversarial Networks (MGANs), a method for training generative networks for efficient texture synthesis. While deep neural network approaches have recently demonstrated remarkable results in terms of synthesis quality, they still come at considerable computational costs (minutes of run-time for low-res images). Our paper addresses this efficiency issue. Instead of a numerical deconvolution in previous work, we precompute a feed-forward, strided convolutional network that captures the feature statistics of Markovian patches and is able to directly generate outputs of arbitrary dimensions. Such network can directly decode brown noise to realistic textu…
Leveraging Uncertainty Estimates to Improve Segmentation Performance in Cardiac MR
2021
In medical image segmentation, several studies have used Bayesian neural networks to segment and quantify the uncertainty of the images. These studies show that there might be an increased epistemic uncertainty in areas where there are semantically and visually challenging pixels. The uncertain areas of the image can be of a great interest as they can possibly indicate the regions of incorrect segmentation. To leverage the uncertainty information, we propose a segmentation model that incorporates the uncertainty into its learning process. Firstly, we generate the uncertainty estimate (sample variance) using Monte-Carlo dropout during training. Then we incorporate it into the loss function t…