Search results for "Signal and image processing"
showing 10 items of 454 documents
Unsupervised Eye Blink Artifact Identification in Electroencephalogram
2018
International audience; The most prominent type of artifact contaminating electroencephalogram (EEG) signals is the eye blink (EB) artifact. Hence, EB artifact detection is one of the most crucial pre-processing step in EEG signal processing before this artifact can be removed. In this work, an approach that identifies EB artifacts without human supervision and automated varying threshold setting is proposed and evaluated. The algorithm functions on the basis of correlation between two EEG electrodes, Fp1 and Fp2, followed by EB artifact threshold determination utilizing the amplitude displacement from the mean. The proposed approach is validated and evaluated in terms of accuracy and error…
Conception d'architectures compactes pour la détection spatiotemporelle d'actions en temps réel
2022
This thesis tackles the spatiotemporal action detection problem from an online, efficient, and real-time processing point of view. In the last decade, the explosive growth of video content has driven a broad range of application demands for automating human action understanding. Aside from accurate detection, vast sensing scenarios in the real-world also mandate incremental, instantaneous processing of scenes under restricted computational budgets. However, current research and related detection frameworks are incapable of simultaneously fulfilling the above criteria. The main challenge lies in their heavy architectural designs and detection pipelines to extract pertinent spatial and tempor…
Exploiting deep learning algorithms and satellite image time series for deforestation prediction
2022
In recent years, we have witnessed the emergence of Deep Learning (DL) methods, which have led to enormous progress in various fields such as automotive driving, computer vision, medicine, finances, and remote sensing data analysis. The success of these machine learning methods is due to the ever-increasing availability of large amounts of information and the computational power of computers. In the field of remote sensing, we now have considerable volumes of satellite images thanks to the large number of Earth Observation (EO) satellites orbiting the planet. With the revisit time of satellites over an area becoming shorter and shorter, it will probably soon be possible to obtain daily imag…
Real-time micro-expression analysis by artificial vision
2022
Human-computer interaction technologies focus more and more on the human being, whether it is on his identity, or on his physical and mental state. Significant progress has been made in the last few decades. However, the study of thoughts and emotions is still an underdeveloped field, but one that has begun to gain considerable interest. In this field, the analysis of facial expressions is the preferred treatment.Unlike a macro-expression, which is visible to the eye, a micro-expression is a type of involuntary facial expression that is extremely rapid and of very low intensity. The computer vision scientific community has been studying ways to automatically recognize micro-expressions usin…
Simulation of Future Geostationary Ocean Color Images
2012
The objective of this work is to simulate global images that would be provided by a theoretical ocean color sensor on a geostationary orbit at longitude 0, in order to assess the range of radiance value data reaching the sensor throughout the day for 20 spectral bands similar to those of the Ocean and Land Color Imager (OLCI). The secondary objective is to assess the illumination and viewing geometries that result in sunglint. For this purpose, we combined a radiative transfer model for ocean waters (Hydrolight) and a radiative transfer model for atmosphere (MODTRAN) to construct the simulated radiance images at the sea surface and at the Top-Of-Atmosphere (TOA). Bio-optical data from GlobC…
Comparative study of three satellite image time-series decomposition methods for vegetation change detection
2018
International audience; Satellite image time-series (SITS) methods have contributed notably to detection of global change over the last decades, for instance by tracking vegetation changes. Compared with multi-temporal change detection methods, temporally highly resolved SITS methods provide more information in a single analysis, for instance on the type and consistency of change. In particular, SITS decomposition methods show a great potential in extracting various components from non-stationary time series, which allows for an improved interpretation of the temporal variability. Even though many case studies have applied SITS decomposition methods, a systematic comparison of common algori…
Machine Learning VS Transfer Learning - Smart Camera Implementation for Face Authentication
2018
The aim of this paper is to highlight differences between classical machine learning and transfer learning applied to low cost real-time face authentication. Furthermore, in an access control context, the size of biometric data should be minimized so it can be stored on a remote personal media. These constraints have led us to compare only lightest versions of these algorithms. Transfer learning applied on Mobilenet v1 raises to 85% of accuracy, for a 457Ko model, with 3680s and 1.43s for training and prediction tasks. In comparison, the fastest integrated method (Random Forest) shows accuracy up to 90% for a 7,9Ko model, with a fifth of a second to be trained and a hundred of microseconds …
Automatic cell nuclei counting: a protocol to acquire images and to compare results between color and multispectral images
2013
International audience; High-throughput screening in histology and analysis need a necessary automatic cell or nucleus counting. Current methods and systems based on grayscale or color images give results with counting errors. We suggest to use multispectral imaging (with more than three bands) rather than color one for nucleus counting. A traditional acquisition chains uses a source of white light and a CCD camera in addition to the optical microscope. To pass to a multispectral acquisition, we use a Programmable Light Source (PLS) in the place of the white light source. This PLS is capable of generating different wavelengths in the visible spectrum. So, one color image and four multispect…
Memristors in Nonlinear Network : Application to Information (Signal and Image) Processing
2021
Memristor is a two-terminal nonlinear dynamic electronic device. Typically, it is a passive nano-device whose conductivity is controlled by the flux, time-integral of the voltage across its terminals, or by the charge, time-integral of the current flowing through it, and it presents interesting features for versatile applications. This thesis considers memristor use as a neighborhood connection for 2D cellular nonlinear or neural network (CNN), essentially for information (image and signal) processing and electronic prosthesis. We develop a model of the memristor based 2D cellular nonlinear networks CNNs compatible to image applications by incorporating memristor in the adjacent neighborhoo…
A sensor-data-based denoising framework for hyperspectral images
2015
Many denoising approaches extend image processing to a hyperspectral cube structure, but do not take into account a sensor model nor the format of the recording. We propose a denoising framework for hyperspectral images that uses sensor data to convert an acquisition to a representation facilitating the noise-estimation, namely the photon-corrected image. This photon corrected image format accounts for the most common noise contributions and is spatially proportional to spectral radiance values. The subsequent denoising is based on an extended variational denoising model, which is suited for a Poisson distributed noise. A spatially and spectrally adaptive total variation regularisation term…