Search results for "Convolution"

Convolution operators with a fundamental solution of finite order

1995

Emergency Analysis: Multitask Learning with Deep Convolutional Neural Networks for Fire Emergency Scene Parsing

2021

In this paper, we introduce a novel application of using scene semantic image segmentation for fire emergency situation analysis. To analyse a fire emergency scene, we propose to use deep convolutional image segmentation networks to identify and classify objects in a scene based on their build material and their vulnerability to catch fire. We introduce our own fire emergency scene segmentation dataset for this purpose. It consists of real world images with objects annotated on the basis of their build material. We use state-of-the-art segmentation models: DeepLabv3, DeepLabv3+, PSPNet, FCN, SegNet and UNet to compare and evaluate their performance on the fire emergency scene parsing task. …

Mixed Circular Convolutions and Zak Transforms

2014

In this chapter the notion of mixed circular convolution is introduced. The polynomial and discrete periodic splines defined on uniform grids are special cases of such convolutions. The so-called Zak transforms provide tools to handle mixed circular convolutions

Genetic Normalized Convolution

2011

Normalized convolution techniques operate on very few samples of a given digital signal and add missing information, trough spatial interpolation. From a practical viewpoint, they make use of data really available and approximate the assumed values of the missing information. The quality of the final result is generally better than that obtained by traditional filling methods as, for example, bilinear or bicubic interpolations. Usually, the position of the samples is assumed to be random and due to transmission errors of the signal. Vice versa, we want to apply normalized convolution to compress data. In this case, we need to arrange a higher density of samples in proximity of zones which c…

Charge reconstruction in large-area photomultipliers

2018

Large-area PhotoMultiplier Tubes (PMT) allow to efficiently instrument Liquid Scintillator (LS) neutrino detectors, where large target masses are pivotal to compensate for neutrinos' extremely elusive nature. Depending on the detector light yield, several scintillation photons stemming from the same neutrino interaction are likely to hit a single PMT in a few tens/hundreds of nanoseconds, resulting in several photoelectrons (PEs) to pile-up at the PMT anode. In such scenario, the signal generated by each PE is entangled to the others, and an accurate PMT charge reconstruction becomes challenging. This manuscript describes an experimental method able to address the PMT charge reconstruction …

Skin-remitted photon path lengths: experimental study

2020

Skin-remitted picosecond laser pulses were detected at four input-output fiber distances in the spectral range 560-800 nm. After deconvolution procedures, distributions and mean values of the remitted photon path lengths in forearm skin were analyzed.

Fingerprint classification based on deep learning approaches: Experimental findings and comparisons

2021

Biometric classification plays a key role in fingerprint characterization, especially in the identification process. In fact, reducing the number of comparisons in biometric recognition systems is essential when dealing with large-scale databases. The classification of fingerprints aims to achieve this target by splitting fingerprints into different categories. The general approach of fingerprint classification requires pre-processing techniques that are usually computationally expensive. Deep Learning is emerging as the leading field that has been successfully applied to many areas, such as image processing. This work shows the performance of pre-trained Convolutional Neural Networks (CNNs…

Remitted photon path lengths in human skin: in-vivo measurement data

2020

The remitted photon path lengths in human skin can be estimated by modelling; however, there are very few experimental data available to validate the simulations. This study exploited the photon time of flight method where picosecond laser pulses at seven wavelength bands in the spectral range 560-800 nm were launched into in-vivo forearm skin of 10 volunteers via an optical fiber. The pulses of back-scattered light were detected via another optical fiber placed at variable distance (1, 8, 12, 16 or 20 mm) from the input fiber, with subsequent analysis of their shapes for all 35 spectral-spatial combinations. Using a deconvolution algorithm, the distribution functions of remitted photon arr…

Deconvolving the Beam in Small Angular Scale CMB Experiments

2000

This paper is concerned with experiments which measure CMB anisotropies on small angular scales. A certain coverage, a beam structure and a level of uncorrelated noise define each experiment. We focus our atention on the reversion of the beam average. In each experiment, we look for the best pixelization for reversion, namely, for the pixelization that -after reversion- leads to good maps containing right spectra for the most wide range of angular scales. Squared pixels having different sizes "smaller" than the beam radius are considered. For a given size, the following question arises: How well can we assign a temperature to each pixel? Various mathematical methods are used to show that, i…

The analysis of dielectric relaxation phenomena with the inverse Fourier transformation

1993

Abstract A method to determine the distribution of relaxation times directly from dielectric loss spectra is presented. The method is based upon a deconvolution procedure: the Fourier transform of the loss factor is divided by sech( π 2 f ) and then, via an inverse Fourier transformation, transformed into the time domain. Limitations and possible improvements of the method are discussed. It is shown that the present method is able to reveal local relaxation processes not perceptible in the loss factor spectrum. With stimulated noise-free data, the resolution of the method is one third of a decade on a logarithmic relaxation timescale.