Abdelaziz Ouamri

Blind spatial unmixing of multispectral images: New methods combining sparse component analysis, clustering and non-negativity constraints

Remote sensing has become an unavoidable tool for better managing our environment, generally by realizing maps of land cover using classification techniques. Traditional classification techniques assign only one class (e.g., water, soil, grass) to each pixel of remote sensing images. However, the area covered by one pixel contains more than one surface component and results in the mixture of these surface components. In such situations, classical classification is not acceptable for many major applications, such as environmental monitoring, agriculture, mineral exploration and mining, etc. Most methods proposed for treating this problem have been developed for hyperspectral images. On the contrary, there are very few automatic techniques suited to multispectral images. In this paper, we propose new unsupervised spatial methods (called 2D-Corr-NLS and 2D-Corr-NMF) in order to unmix each pixel of a multispectral image for better recognizing the surface components constituting the observed scene. These methods are related to the blind source separation (BSS) problem, and are based on sparse component analysis (SCA), clustering and non-negativity constraints. Our approach consists in first identifying the mixing matrix involved in this BSS problem, by using the first stage of a spatial correlation-based SCA method with very limited source sparsity constraints, combined with clustering. Non-negative least squares (NLS) or non-negative matrix factorization (NMF) methods are then used to extract spatial sources. An important advantage of our proposed methods is their applicability to the possibly globally underdetermined, but locally (over)determined BSS model in multispectral remote sensing images. Experiments based on realistic synthetic mixtures and real multispectral images collected by the Landsat ETM+ and the Formosat-2 sensors are performed to evaluate the performance of the proposed approach. We also show that our methods significantly outperform the sequential maximum angle convex cone (SMACC) method.

Improvement of remote sensing multispectral image classification by using Independent Component Analysis

This paper deals with the application of Independent Component Analysis (ICA) as a solution to Blind Source Separation (BSS), in order to pre-process remote sensing multispectral images before we classify them. We analyze the structure of the considered data, and especially show that each recorded image corresponding to a spectral band may be seen as an observation consisting of a mixture (linear combination) of source images. The latter images correspond to the abundances of the pure elements (endmembers) in the pixels. Using BSS methods, one can hope to reduce the mixing effect in these observations, which then allows better recognition of the classes constituting the observed scene. Based on this approach, we create new images (i.e. at least partly separated images) by using ICA, starting from HRV SPOT images. These images are then used as inputs of a supervised classifier integrating textural information. The separated image classification results show a clear improvement compared to classification of initial images. This show the contribution of ICA as an attractive pre-processing for classification of multispectral remote sensing imagery.

A new spatial sparsity-based method for extracting endmember spectra from hyperspectral data with some pure pixels

Remote sensing hyperspectral sensors typically collect data in contiguous narrow bands (up to several hundred bands) in the electromagnetic spectrum. In hyperspectral imagery, pixels are often linear mixtures of pure materials (endmembers) contained in the observed scene. In this paper, we propose a new unsupervised spatial method (called 2D-VM) for endmember spectra extraction from data to be collected by future higher spatial resolution hyperspectral sensors, which will allow the existence of some pure pixels. This method is related to the Blind Mixture Identification (BMI) problem, and is based on Sparse Component Analysis (SCA). It extracts the endmember spectra by using a spatial variance-based SCA method, which detects a few pure-pixel zones. Experiments based on synthetic but realistic data are performed to compare the performance of the proposed approach and of methods from the literature. We show that our approach outperforms all other methods.

New Efficient Schemes for Adaptive Selection of the Update Time in the IMMJPDAF

The paper addresses the problem of adaptive manoeuvring targets tracking in clutter with a phased array radar. The tracking algorithm is based on the combination of the interacting multiple models (IMM) algorithm and the joint probabilistic data association filter (JPDAF), the resulting algorithm is named IMMJPDAF algorithm. Moreover, the phased array radar is a multifunction radar with the capability to select adaptively the sampling time interval; consequently, the tracking performance is improved. First, a complete comparative study between the IMMJPDAF algorithm and the multirate IMMJPDAF (MRIMMJPDAF) algorithm for tracking close manoeuvring targets with varying amounts of clutter density is presented. Then a description is made of the integration of a new fast method into the IMMJPDAF algorithm to adaptively select the next update time according to the targets motions. We call the resulting algorithm, the fast adaptive IMMJPDAF (FAIMMJPDAF) algorithm. Furthermore, an enhancement of the tracking accuracy in the FAIMMJPDAF algorithm is made by also taking into account the separation distance between targets in the selection of the next update time. The performance of the proposed algorithm, named improved fast adaptive IMMJPDAF (IFAIMMJPDAF) algorithm is assessed via Monte Carlo Simulations and compared with that of four algorithms that use an adaptive selection of the update time: FAIMMJPDAF algorithm, the adaptive IMMJPDAF that uses a modified version of the van Keuk criterion (MAIMMJPDAF), the adaptive IMMJPDAF that uses the original van Keuk method (AIMMJPDAF), and the IMMJPDAF (CIMMJPDAF) that uses a constant update time.

Hyperspectral data multi-sharpening based on linear-quadratic nonnegative matrix factorization

In this paper, we propose a new multi-sharpening approach for improving the spatial resolution of hyperspectral data. This approach, based on the linear-quadratic spectral unmixing concept, uses a linear-quadratic nonnegative matrix factorization multiplicative algorithm. Our method first consists in unmixing the low spatial resolution hyperspectral data and high spatial resolution multispectral data. The obtained high resolution spectral and spatial parts of information are then recombined, according to the linear-quadratic mixing model, in order to obtain unobservable multi-sharpened high spatial resolution hyperspectral data. Experiments, based on realistic synthetic and real data, are carried out to evaluate the performance of the proposed approach and of linear nonnegative matrix factorization-based approaches from the literature. We show that our proposed approach significantly outperforms the used literature methods.

Nose tip localization on a three dimensional face across pose, expressions and occlusions variations in a Riemannian context

Nose tip localization is an important step for registration, preprocessing and recognition of 3D face data. In this paper, we propose a new approach for the nose tip detection that is robust to pose and expression variations and in presence of occlusions. From a rotated 3D face, we extract facial curves that are matched to a profile curve model. An optimal matching using the Riemannian geometry, based on the Elastic Shape Analysis is performed to obtain the accurate nose tip. The proposed method requires no training and can locate the nose tip in less than 6 seconds. Experiments are performed on the Bosphorus database. Quantitative analysis and comparison with the ground truth locations are provided. The results confirm that our approach achieves 97.68% with error no larger than 12 mm and 98.19% within 20 mm.

Modified nonnegative matrix factorization for endmember spectra extraction from highly mixed hyperspectral images combined with multispectral data

In this paper, a new approach is proposed for linear endmember spectra extraction from a highly mixed hyperspectral image combined with high spatial resolution multispectral data containing pure pixels. This new approach, which is applied to unmix the considered hyperspectral image, is based on a modified version of nonnegative matrix factorization (NMF) coupled with nonnegative least squares (NLS). The multispectral data are used to initialize the hyperspectral NMF algorithm and to constrain it during matrix updates. Experiments based on synthetic and real data are performed to evaluate the performance of the proposed approach and to compare it with five methods from the literature only applied to the hyperspectral data. The obtained performance shows the superiority of the proposed approach as compared with all other methods. Also, the impact, on the proposed method, of spectral variability between hyperspectral and multispectral data is evaluated, and the obtained results show the robustness of the proposed method to this variability.

Real time Hough transform based track initiators in clutter

In both military and civilian surveillance systems such as Air Traffic Control (ATC) systems, tracking targets in clutter using radar involves dealing with a number of challenges, all related to real time decision and data fusion theories. A major challenge is to detect the real targets through the received measurements in real time and to activate the tracking process.This paper deals with real time automatic initiation of tracks in clutter. Among the proposed solutions in the literature to handle this problem, the conventional Hough transforms (HT) and the Modified Hough Transforms (MHT) have been shown to be effective as track initiator techniques in dense clutter. However, these techniques are computationally intensive. Inasmuch as the tracking of targets is a real time application, we propose in this work, to modify both the Hough transforms (HT) and the Modified Hough Transforms (MHT) so that they can work in real time in adverse environments. The resulting techniques are called Real Time HT (RTHT) and Real Time MHT (RTMHT). Monte Carlo simulations are used to assess the performance of the proposed techniques.

Moving Objects Localization by Local Regions Based Level Set: Application on Urban Traffic

In this paper, a novel method for locating multiple moving objects in a video sequences captured by a stationary camera is proposed. In order to determine the precise location of the objects in an image, a new local regions based level set model is carried out. The whole process consists of two main parts: the global detection and the fine localization. During the global detection, the presence or absence of an object in an image is determined by the Mixture of Gaussians method. For the fine localization, we propose to reformulate global energies by utilizing little squared windows centered on each point over a thin band surrounding the zero level set, hence the object contour can be reshaped into small local interior and exterior regions that lead to compute a family of adaptive local energies, which enables us to well localize the moving objects. Moreover, we propose to adapt the smoothness of the contours, and the accuracy of the objects’ perimeter of different shapes with an automatic stopping criterion. The proposed method has been tested on different real urban traffic videos, and the experiment results demonstrate that our algorithm can locate effectively and accurately the moving objects; optimize the results of the localized objects and also decrease the computations load.

Vision based system for driver drowsiness detection

Drowsiness of drivers is amongst the significant causes of road accidents. Every year, it increases the amounts of deaths and fatalities injuries globally. In this paper, a module for Advanced Driver Assistance System (ADAS) is presented to reduce the number of accidents due to drivers fatigue and hence increase the transportation safety; this system deals with automatic driver drowsiness detection based on visual information and Artificial Intelligence. We proposed an algorithm to locate, track, and analyze both the drivers face and eyes to measure PERCLOS, a scientifically supported measure of drowsiness associated with slow eye closure.