Sylvie Chambon

Ecole Nationale Supérieure d’Electrotechnique, d’Electronique, d’Informatique, d’Hydraulique et des Télécommunications | INP ENSEEIHT · Département Informatique et mathématiques appliquées

The determination of precise skin lesion boundaries in dermoscopic images using automated methods faces many challenges, most importantly, the presence of hair, inconspicuous lesion edges and low contrast in dermoscopic images, and variability in the color, texture and shapes of skin lesions. Existing deep learning-based skin lesion segmentation al...

Abstract Herein, the problem of vehicle re‐identification using distance comparison of images in CNN latent spaces is addressed. First, the impact of the distance metrics, comparing performances obtained with different metrics is studied: the minimal Euclidean distance (MED), the minimal cosine distance (MCD) and the residue of the sparse coding re...

Rapid and accurate detection of COVID-19 is a crucial step to control the virus. For this purpose, the authors designed a web-based COVID-19 detector using efficient dual attention networks, called ‘EDANet’. The EDANet architecture is based on inverted residual structures to reduce the model complexity and dual attention mechanism with position and...

This column describes the release of the Toulouse Campus Surveillance Dataset (ToCaDa). It consists of 25 synchronized videos (with audio) of two scenes recorded from different viewpoints of the campus. An extensive manual annotation comprises all moving objects and their corresponding bounding boxes, as well as audio events. The annotation was per...

Estimating a depth map and, at the same time, predicting the 3D pose of an object from a single 2D color image is a very challenging task. Depth estimation is typically performed through stereo vision by following several time-consuming stages, such as epipolar geometry, rectification and matching. Alternatively, when stereo vision is not useful or...

Wearable cameras are become more popular in recent years for capturing the unscripted moments of the first-person that help to analyze the users lifestyle. In this work, we aim to recognize the places related to food in egocentric images during a day to identify the daily food patterns of the first-person. Thus, this system can assist to improve th...

This paper addresses the problem of vehicle re-identification using distance comparison of images in CNN latent spaces. First, we study the impact of the distance metrics, comparing performances obtained with different metrics: the minimal Euclidean distance (MED), the minimal cosine distance (MCD), and the residue of the sparse coding reconstructi...

Determining the precise boundaries of skin lesions in dermoscopic images needs to cope with many challenges, such as the presence of hair, inconspicuous lesion edges, low contrast, and the variability in colour, texture, and shapes of these lesions. Recent developed skin lesion segmentation algorithms based on deep learning are computationally expe...

Circular markers are planar markers which offer great performances for detection and pose estimation. For an uncalibrated camera with rectangular pixels, the images of at least two coplanar circles in one view are generally required to recover the circle poses. Unfortunately, detecting more than one ellipse in the image is tricky and time-consuming...

21st Scandinavian Conference, SCIA 2019, Norrköping, Sweden, June 11–13, 2019, Proceedings

Computing a skeleton for a discretized boundary typically produces a noisy output, with a skeletal branch produced for each boundary pixel. A simplification step often follows to reduce these noisy branches. As a result, generating a clean skeleton is usually a 2-step process. In this article, we propose a skeletonization process that produces a cl...

This paper proposes a new gait representation that encodes the dynamics of a gait period through a 2D array of 17-bin histograms. Every histogram models the co-occurrence of optical flow states at every pixel of the normalized template that bounds the silhouette of a target subject. Five flow states (up, down, left, right, null) are considered. The...

Registering a single intensity image to a 3D geometric model represented by a set of depth images is still a challenge. Since depth images represent only the shape of the objects, in turn, the intensity image is relative to viewpoint, texture and lighting condition. Thus, it is essential to firstly bring 2D and 3D representations to common features...

Computing a skeleton for a discretized boundary typically produces a noisy output, with a skeletal branch produced for each boundary pixel. A simplification step often follows to reduce these noisy branches. As a result, generating a clean skeleton is usually a 2-step process. In this article, we propose a skeletonization process that produces a cl...

This paper aims at developing an automatic algorithm for moth recognition from trap images in real-world conditions. This method uses our previous work for detection [1] and introduces an adapted classification step. More precisely, SVM classifier is trained with a multi-scale descriptor, Histogram Of Curviness Saliency (HCS). This descriptor is ro...

This paper aims at developing an automatic algorithm for moth recognition from trap images in real-world conditions. This method uses our previous work for detection [1] and introduces an adapted classification step. More precisely, SVM classifier is trained with a multi-scale descriptor, Histogram Of Curviness Saliency (HCS). This descriptor is ro...

In surveillance applications, humans and vehicles are the most important common elements studied. In consequence, detecting and matching a person or a car that appears on several videos is a key problem. Many algorithms have been introduced and nowadays, a major relative problem is to evaluate precisely and to compare these algorithms, in reference...

Circular markers are planar markers which offer great performances for detection and pose estimation. For an uncalibrated camera with an unknown focal length, at least the images of at least two coplanar circles are generally required to recover their poses. Unfortunately, detecting more than one ellipse in the image must be tricky and time-consumi...

In the context of 2D/3D registration, this paper introduces an approach that allows to match features detected in two different modalities: photographs and 3D models, by using a common 2D reprensentation. More precisely, 2D images are matched with a set of depth images, representing the 3D model. After introducing the concept of curvilinear salienc...

Insect detection is one of the most challenging problems of biometric image processing. This study focuses on developing a method to detect both individual insects and touching insects from trap images in extreme conditions. This method is able to combine recent approaches on contour-based and region-based segmentation. More precisely, the two cont...

We present a novel approach to reconstruct a 3D object from images corresponding to two different viewpoints: we estimate the skeleton of the object instead of its surface. The originality of the method is to be able to reconstruct a complete tubular 3D object from only two input images. Unlike classical reconstruction methods like multiview stereo...

This paper proposes a new algorithm for crack detection based on the selection of minimal paths. It takes account of both photometric and geometric characteristics and requires few information a priori. It is validated on synthetic and real images.

This paper proposes a new algorithm for automatic crack detection from pavement images. It heavily relies on the localization of minimal paths within each image, a path being a series of neighbouring pixels with low intensities. The originality of the approach is about the manner to select the set of minimal paths and the two post-processing steps...

In the context of semantic segmentation of urban scenes, the calibrated multi-views and the flatness assumption are commonly used to estimate a warped image based on the homography estimation. In order to classify planar and non-planar areas, we propose an evaluation protocol that compares several Image Quality Assessments (IQA) between a reference...

Superpixel segmentation is widely used in the preprocessing step of many applications. Most of existing methods are based on a photometric criterion combined to the position of the pixels. In the same way as the Simple Linear Iterative Clustering (SLIC) method, based on k-means segmentation, a new algorithm is introduced. The main contribution lies...

Nous présentons dans cet article une méthode de segmentation en superpixels appliquée à des images de scènes urbaines. Ces images proviennent de sé-quences acquises au moyen d'un système de carto-graphie mobile qui assure des prises de vue géo-référencées et redondantes spatio-temporellement. Notre objectif est d'obtenir une segmentation sé-mantiqu...

From image processing to artificial vision. Cognitive advances SUMMARY : Cognitive Issues in Automatic Audiovisual Content Indexing (Philippe Joly) Assistive Technologies for the Visually Impaired Persons (Christophe Jouffrais) Imaging Devices Developed by the 21st Century COE Group in Shizuoka University. An Introduction to Nanovision (Hidenori...

Seed propagation-based stereo matching can help to reduce ambiguity occuring when a pixel from one image has different putative correspondents in the other one due to difficult areas (repetitive patterns, homogeneous areas, occlusions and depth discontinuities). They rely on previously computed matches (seeds) to reduce the size of the search area,...

The state of roads is continuously degrading due to meteorological conditions, ground movements, and traffic, leading to the formation of defects, such as grabbing, holes, and cracks. In this article, a method to automatically distinguish images of road surfaces with defects from road surfaces without defects is presented. This method, based on sup...

In the context of computer vision, matching can be done with similarity measures. This paper presents the classification of these measures into five families. In addition, 18 measures based on robust statistics, previously proposed in order to deal with the problem of occlusions, are studied and compared to the state of the art. A new evaluation pr...

A new algorithm of automatic extraction of thin structures in textured images is introduced, and, more specifi- cally, is applied to detection of road cracks. The method is based on two steps: the first one consists in detecting points of interest inside the thin structure whereas the second step connects the points with a geodesic contour process....

Dans le cadre de la mise en correspondance dense de pixels, nous étudions la fusion de différentes mesures de corrélation. En s'appuyant sur les travaux précédents, nous utilisons les mesures les plus représentatives parmi 5 familles de mesures : corrélation croisée, mesures classiques, similarité de gradients, statistiques non-paramétriques et sta...

In the field of noninvasive sensing techniques for civil infrastructures monitoring, this paper addresses the problem of crack detection, in the surface of the French national roads, by automatic analysis of optical images. The first contribution is a state of the art of the image-processing tools applied to civil engineering. The second contributi...

This paper presents a region-based stereo matching algorithm which uses a new method to select the final disparity: a random process computes for each pixel different approximations of its disparity relying on a surface model with different image segmentations and each found disparity gets a vote. At last, the final disparity is selected by estimat...

The automatic detection of road cracks is important in a lot of countries to quantify the quality of road surfaces and to determine the national roads that have to be improved. Many methods have been proposed to automat-ically detect the defects of road surface and, in particular, cracks: with tools of mathematical morphology, neuron networks or mu...

Dans la contexte de l'extraction de structure fine, ce papier présente une nouvelle méthode s'appuyant sur une segmentation multi-résolution appliquée au cas des images routières. Une méthode initialement développée pour la détection de membranes biologiques faiblement contrastées a été adaptée aux cas de la détection de fissures dans des images. E...

Extracting the defects of the road pavement in images is difficult and, mos t of the time, one image is used alone. The difficulties of this task are: illumination changes, objects on the ro ad, artefacts due to the dynamic acquisition. In this work, we try to solve some of these problems by using acquisitions from different points of view. In cons...

The Thin-Plate Spline warp has been shown to be a very effective parameterized model of the optic flow field between images of various types of deformable surfaces, such as a paper sheet being bent. Recent work has also used such warps for images of a smooth and rigid surface. Standard Thin-Plate Spline warps are however not rigid, in the sense tha...

In the context of fine structure extraction, lots of methods have been introduced, and, particularly in pavement crack detection. We can distinguish approaches based on a threshold, employing mathematical morphology tools or neuron networks and, more recently, techniques with transformations, like wavelet decomposition. The goal of this paper is to...

Résumé La mise en correspondance de pixels est une étape impor-tante de la reconstruction 3D. Parmi les méthodes exis-tantes, nous nous intéressons plus particulièrement à celles par propagation de germes qui s'appuient sur un ensemble d'appariements fiables (germes). Le principe utilisé pour la propagation est que le correspondant d'un voisin d'un...

Diagnosis and therapy planning in oncology applications often rely on the joint exploitation of two complementary imaging modalities, namely Computerized Tomography (CT) and Positron Emission Tomography (PET). While recent technical advances in combined CT/PET scanners enable 3D CT and PET data of the thoracic region to be obtained with the patient...

Nous nous plaçons dans le cadre du recalage 3D entre images tomodensitométriques (TDM), acquises à deux instants du cycle respiratoire, et images de tomographie par émission de positons (TEP), en imagerie thoracique. Pour garantir des déformations physiologiquement réalistes, nous proposons une nouvelle approche qui permet d'introduire un modèle de...

In the context of thoracic CT-PET volume registration, we present a novel method to incorporate a breathing model in a non-linear registration procedure, guaranteeing physiologically plausible deforma- tions. The approach also accounts for the rigid motions of lung tumors during breathing. We performed a set of registration experiments on one healt...

This paper deals with the problem of non-linear landmark-based registration of CT (at two different instants of the breathing cycle, intermediate expirations) and PET images of thoracic regions. We propose a general method to introduce a breathing model in a registration procedure in order to simulate the instant in the breathing cycle most similar...

Thin-plate spline warps have been shown to be very effective as a parameterized model of the optic flow field between images of various deforming surfaces. Examples include a sheet of paper being manually handled. Recent work has used such warps for images of smooth rigid surfaces. Standard thin-plate spline warps are not rigid, in the sense that t...

In the context of thoracic CT-PET volume registration, we present a novel method to incorporate a breathing model in a non-linear registration procedure, guaranteeing physiologically plausible deformations. The approach also accounts for the rigid motions of lung tumors during breathing. We performed a set of registration experiments on one healthy...

In binocular stereovision, the accuracy of the 3D reconstruction depends on the accuracy of matching results. Consequently, matching is an important task. Our first goal is to present a state of the art of matching methods. We define a generic and complete algorithm based on essential components to describe most of the matching methods. Occlusions...

This work deals with stereo-vision and more precisely matching of pixels using correlation measures. Matching is an important task in computer vision, the accuracy of the three-dimensional reconstruction depending on the accuracy of the matching. The problems of matching are: intensity distortions, noises, untextured areas, foreshortening and occlu...

Abstract In the context of computer vision, stereo matching can be done us- ing correlation,measures. Few papers,deal with color correlation- based,matching,so the underlying,problem,of this paper,is about how,it can be adapted,to color images. The goals of this work,are to help,choosing,a color space and,to generalize the correlation measures,to c...

In the context of computer vision, matching can be done using correlation measures. This paper presents new algorithms that use two correlation measures: the zero mean normalised cross-correlation, ZNCC, and the smooth median absolute deviation, SMAD. While ZNCC is efficient in non-occluded areas and non-robust near occlusions, SMAD is non-efficien...

In the context of computer vision, matching can be done using correlation measures. This paper presents the classification of forty measures into five families. In addition, sixteen new measures based on robust statistics are presented to deal with the problem of occlusions. An evaluation protocol is proposed (eight criteria, three pairs of real an...