Wood is an essential component of rivers and plays a significant role in ecology and morphology. ... more Wood is an essential component of rivers and plays a significant role in ecology and morphology. It can be also considered as a risk factor in rivers due to its influence on erosion and flooding. Quantifying and characterizing wood fluxes in rivers during floods would improve our understanding of the key processes but is hindered by technical challenges. Among various techniques for monitoring wood in rivers, streamside videography is a powerful approach to quantify different characteristics of wood in rivers, but past research has employed a manual approach that has many limitations. In this work, we introduce new software for the automatic detection of wood pieces in rivers. We apply different image analysis techniques such as static and dynamic masks, object tracking, and object characterization to minimize false positive and missed detections. To assess the software performance, results are compared with manual detections of wood from the same videos, which was a time-consuming process. Key parameters that affect detection are assessed including surface reflections, lighting conditions, flow discharge, wood position relative to the camera, and the length of wood pieces. Preliminary results had a 36% rate of false positive detection, primarily due to light reflection and water waves, but post-processing reduced this rate to 15%. The missed detection rate was 71% of piece numbers in the preliminary result, but post processing reduced this error to only 6.5% of piece numbers, and 13.5% of volume. The high precision of the software shows that it can be used to massively increase the quantity of wood flux data in rivers around the world, potentially in real time. The significant impact of postprocessing indicates that it is necessary to train the software in various situations (location, timespan, weather conditions) to ensure reliable results. Manual wood detections and annotations for this work took more than one human-month of labor. In comparison, the presented software coupled with an appropriate post processing step performed the same task in real time (55 hr) on a standard desktop computer.
In order to identify the species of a tree, the different organs that are the leaves, the bark, t... more In order to identify the species of a tree, the different organs that are the leaves, the bark, the flowers and the fruits, are inspected by botanists. So as to develop an algorithm that identifies automatically the species, we need to extract these objects of interest from their complex natural environment. In this article, we focus on the segmentation of flowers and fruits and we present a new method of segmentation based on an active contour algorithm using two probability maps. The first map is constructed via the dual camera that we can find on the back of the latest smartphones. The second map is made with the help of a multilayer perceptron (MLP). The combination of these two maps to drive the evolution of the object contour allows an efficient segmentation of the organ from a natural background.
The adoption of self-driving cars will certainly revolutionize our lives, even though they may ta... more The adoption of self-driving cars will certainly revolutionize our lives, even though they may take more time to become fully autonomous than initially predicted. The first vehicles are already present in certain cities of the world, as part of experimental robot-taxi services. However, most existing studies focus on the navigation part of such vehicles. We currently miss methods, datasets, and studies to assess the in-cabin human component of the adoption of such technology in real-world conditions. This paper proposes an experimental framework to study the activities of occupants of self-driving cars using a multidisciplinary approach (computer vision associated with human and social sciences), particularly non-driving related activities. The framework is composed of an experimentation scenario, and a data acquisition module. We seek firstly to capture real-world data about the usage of the vehicle in the nearest possible, real-world conditions, and secondly to create a dataset containing in-cabin human activities to foster the development and evaluation of computer vision algorithms. The acquisition module records multiple views of the front seats of the vehicle (Intel RGB-D and GoPro cameras); in addition to survey data about the internal states and attitudes of participants towards this type of vehicle before, during, and after the experimentation. We evaluated the proposed framework with the realization of real-world experimentation with 30 participants (1 hour each) to study the acceptance of SDCs of SAE level 4.
Discrete Geometry constitutes one of the great families of methods dedicated to the automated ana... more Discrete Geometry constitutes one of the great families of methods dedicated to the automated analysis of shapes in 2D and 3D digital images. Images are generally organized on a regular grid, called discrete data, for which the discrete geometry is a complete geometrical paradigm (discrete objects—points, straight lines…—and associated algorithmic).The main conference on this topic, the International Conference on Discrete Geometry for Computer Imagery (DGCI), was held in Lyon, France, April 16–18, 2008, for the 14th edition. DGCI 2008 attracted researchers from all around the world. Thereby, 76 papers were submitted, from 24 different countries and five continents. Once reviewed, 45 papers were accepted for publication. This special issue includes contributions which are significantly revised and extended versions of papers selected from the best presented at the 14th DGCI. These papers which were accepted after two extra review cycles address topics relevant to the Pattern Recognition community.DGCI 2008 was supported by the International Association for Pattern Recognition (IAPR), and is the main conference associated with the Technical Committee 18 on Discrete Geometry of the IAPR. We also thank our sponsoring institutions for providing the financial support essential for a successful event. We sincerely want to thank the authors who contributed to this special issue, the referees for their useful reviews in a short period of time and for contributing to improve the paper quality. We are very grateful to the chief editor of Pattern Recognition who gives us the opportunity to publish papers from discrete geometry topics.We enjoyed making the 14th DGCI a success and working on this special issue. We hope you will enjoy reading the selected papers.
Revue D Epidemiologie Et De Sante Publique, Jul 1, 2018
HAL is a multidisciplinary open access archive for the deposit and dissemination of scientific re... more HAL is a multidisciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.
For everyone, the identification of tree is a difficult task. The main organ of the plant used ge... more For everyone, the identification of tree is a difficult task. The main organ of the plant used generally to identify a tree is the leaf. However, due to the large variability of the shapes of leaves, it is difficult to obtain good recognition results. Moreover, sometimes the bark is a very distinctive feature and we think it may be possible to improve the recognition rate by considering it. The main purpose of this article is to investigate how we can combine the features extracted respectively from the leaf and the bark images to recognize the tree the photos come from. An important point is the consideration of the confusion matrix that can be constructed between several species, when the form of a leaf or the shape of a bark is common to a number of tree species. So, we present various strategies of fusion including belief functions and compare them on a public database of 72 species of trees and shrubs, which can be find in metropolitan France.
In the frame of a tree species identifying mobile application, designed for a wide scope of users... more In the frame of a tree species identifying mobile application, designed for a wide scope of users, and with didactic purposes, we developed a method based on the computation of explicit leaf shape descriptors inspired by the criteria used in botany. This paper focuses on the characterization of the leaf contour, the extraction of its properties, and its description using botanical terms. Contour properties are investigated using the Curvature-Scale Space representation, the potential teeth explicitly extracted and described, and the margin classified into a set of inferred shape classes. Results are presented for both margin shape characterization, and leaf classification over nearly 80 tree species.
Object detection in a dynamic background is a challenging task in many computer vision applicatio... more Object detection in a dynamic background is a challenging task in many computer vision applications. In some situations, the motion of objects can be predicted thanks to its regularity (e.g., vehicle motion, pedestrian motion). In this article, we propose to model such motion knowledge and to use it as additional information to help in foreground detection. The inclusion of object motion information provides a measure for distinguishing moving objects from a background that has similar sizes and brightness levels. This information is obtained by applying statistical methods on data obtained during the training period. When available, prior knowledge can be incorporated into the foreground detection process to improve robustness and to decrease false detection. We apply this framework to moving object detection in rivers, one of the situations in which classic background subtraction algorithms fail. Our experiments show that the incorporation of prior motion data into background subtraction improves object detection.
Introduction 1 2 Analytic study of circles on the grid, bundles of discrete parabolas 11 3 Constr... more Introduction 1 2 Analytic study of circles on the grid, bundles of discrete parabolas 11 3 Construction of the floor parabolas with a cellular automaton 38 4 Construction of the floor circles 52 5 Ceiling parabolas and circles 55 6 Pitteway's and arithmetical circles 62 7 Conclusion 72 * This research has been done while the author was member of LIP, Ecole Normale Supérieure of Lyon.
With the definition of discrete lines introduced by Réveillès [REV91], there has been a wide rang... more With the definition of discrete lines introduced by Réveillès [REV91], there has been a wide range of research in discrete geometry and more precisely on the study of discrete lines. By the use of the linear time segment recognition algorithm of Debled and Réveillès [DR94], Vialard [VIA96a] has proposed a O(l) algorithm for computing the tangent in one point of a discrete curve where l is the average length of the tangent. By applying her algorithm to n points of a discrete curve, the complexity becomes O(n.l). This paper proposes a new approach for computing the tangent. It is based on a precise study of the tangent evolution along a discrete curve. The resulting algorithm has a O(n) complexity and is thus optimal. Some applications in curvature computation and a tombstones contours study are also presented.
Wood is an essential component of rivers and plays a significant role in ecology and morphology. ... more Wood is an essential component of rivers and plays a significant role in ecology and morphology. It can be also considered as a risk factor in rivers due to its influence on erosion and flooding. Quantifying and characterizing wood fluxes in rivers during floods would improve our understanding of the key processes but is hindered by technical challenges. Among various techniques for monitoring wood in rivers, streamside videography is a powerful approach to quantify different characteristics of wood in rivers, but past research has employed a manual approach that has many limitations. In this work, we introduce new software for the automatic detection of wood pieces in rivers. We apply different image analysis techniques such as static and dynamic masks, object tracking, and object characterization to minimize false positive and missed detections. To assess the software performance, results are compared with manual detections of wood from the same videos, which was a time-consuming process. Key parameters that affect detection are assessed including surface reflections, lighting conditions, flow discharge, wood position relative to the camera, and the length of wood pieces. Preliminary results had a 36% rate of false positive detection, primarily due to light reflection and water waves, but post-processing reduced this rate to 15%. The missed detection rate was 71% of piece numbers in the preliminary result, but post processing reduced this error to only 6.5% of piece numbers, and 13.5% of volume. The high precision of the software shows that it can be used to massively increase the quantity of wood flux data in rivers around the world, potentially in real time. The significant impact of postprocessing indicates that it is necessary to train the software in various situations (location, timespan, weather conditions) to ensure reliable results. Manual wood detections and annotations for this work took more than one human-month of labor. In comparison, the presented software coupled with an appropriate post processing step performed the same task in real time (55 hr) on a standard desktop computer.
In order to identify the species of a tree, the different organs that are the leaves, the bark, t... more In order to identify the species of a tree, the different organs that are the leaves, the bark, the flowers and the fruits, are inspected by botanists. So as to develop an algorithm that identifies automatically the species, we need to extract these objects of interest from their complex natural environment. In this article, we focus on the segmentation of flowers and fruits and we present a new method of segmentation based on an active contour algorithm using two probability maps. The first map is constructed via the dual camera that we can find on the back of the latest smartphones. The second map is made with the help of a multilayer perceptron (MLP). The combination of these two maps to drive the evolution of the object contour allows an efficient segmentation of the organ from a natural background.
The adoption of self-driving cars will certainly revolutionize our lives, even though they may ta... more The adoption of self-driving cars will certainly revolutionize our lives, even though they may take more time to become fully autonomous than initially predicted. The first vehicles are already present in certain cities of the world, as part of experimental robot-taxi services. However, most existing studies focus on the navigation part of such vehicles. We currently miss methods, datasets, and studies to assess the in-cabin human component of the adoption of such technology in real-world conditions. This paper proposes an experimental framework to study the activities of occupants of self-driving cars using a multidisciplinary approach (computer vision associated with human and social sciences), particularly non-driving related activities. The framework is composed of an experimentation scenario, and a data acquisition module. We seek firstly to capture real-world data about the usage of the vehicle in the nearest possible, real-world conditions, and secondly to create a dataset containing in-cabin human activities to foster the development and evaluation of computer vision algorithms. The acquisition module records multiple views of the front seats of the vehicle (Intel RGB-D and GoPro cameras); in addition to survey data about the internal states and attitudes of participants towards this type of vehicle before, during, and after the experimentation. We evaluated the proposed framework with the realization of real-world experimentation with 30 participants (1 hour each) to study the acceptance of SDCs of SAE level 4.
Discrete Geometry constitutes one of the great families of methods dedicated to the automated ana... more Discrete Geometry constitutes one of the great families of methods dedicated to the automated analysis of shapes in 2D and 3D digital images. Images are generally organized on a regular grid, called discrete data, for which the discrete geometry is a complete geometrical paradigm (discrete objects—points, straight lines…—and associated algorithmic).The main conference on this topic, the International Conference on Discrete Geometry for Computer Imagery (DGCI), was held in Lyon, France, April 16–18, 2008, for the 14th edition. DGCI 2008 attracted researchers from all around the world. Thereby, 76 papers were submitted, from 24 different countries and five continents. Once reviewed, 45 papers were accepted for publication. This special issue includes contributions which are significantly revised and extended versions of papers selected from the best presented at the 14th DGCI. These papers which were accepted after two extra review cycles address topics relevant to the Pattern Recognition community.DGCI 2008 was supported by the International Association for Pattern Recognition (IAPR), and is the main conference associated with the Technical Committee 18 on Discrete Geometry of the IAPR. We also thank our sponsoring institutions for providing the financial support essential for a successful event. We sincerely want to thank the authors who contributed to this special issue, the referees for their useful reviews in a short period of time and for contributing to improve the paper quality. We are very grateful to the chief editor of Pattern Recognition who gives us the opportunity to publish papers from discrete geometry topics.We enjoyed making the 14th DGCI a success and working on this special issue. We hope you will enjoy reading the selected papers.
Revue D Epidemiologie Et De Sante Publique, Jul 1, 2018
HAL is a multidisciplinary open access archive for the deposit and dissemination of scientific re... more HAL is a multidisciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.
For everyone, the identification of tree is a difficult task. The main organ of the plant used ge... more For everyone, the identification of tree is a difficult task. The main organ of the plant used generally to identify a tree is the leaf. However, due to the large variability of the shapes of leaves, it is difficult to obtain good recognition results. Moreover, sometimes the bark is a very distinctive feature and we think it may be possible to improve the recognition rate by considering it. The main purpose of this article is to investigate how we can combine the features extracted respectively from the leaf and the bark images to recognize the tree the photos come from. An important point is the consideration of the confusion matrix that can be constructed between several species, when the form of a leaf or the shape of a bark is common to a number of tree species. So, we present various strategies of fusion including belief functions and compare them on a public database of 72 species of trees and shrubs, which can be find in metropolitan France.
In the frame of a tree species identifying mobile application, designed for a wide scope of users... more In the frame of a tree species identifying mobile application, designed for a wide scope of users, and with didactic purposes, we developed a method based on the computation of explicit leaf shape descriptors inspired by the criteria used in botany. This paper focuses on the characterization of the leaf contour, the extraction of its properties, and its description using botanical terms. Contour properties are investigated using the Curvature-Scale Space representation, the potential teeth explicitly extracted and described, and the margin classified into a set of inferred shape classes. Results are presented for both margin shape characterization, and leaf classification over nearly 80 tree species.
Object detection in a dynamic background is a challenging task in many computer vision applicatio... more Object detection in a dynamic background is a challenging task in many computer vision applications. In some situations, the motion of objects can be predicted thanks to its regularity (e.g., vehicle motion, pedestrian motion). In this article, we propose to model such motion knowledge and to use it as additional information to help in foreground detection. The inclusion of object motion information provides a measure for distinguishing moving objects from a background that has similar sizes and brightness levels. This information is obtained by applying statistical methods on data obtained during the training period. When available, prior knowledge can be incorporated into the foreground detection process to improve robustness and to decrease false detection. We apply this framework to moving object detection in rivers, one of the situations in which classic background subtraction algorithms fail. Our experiments show that the incorporation of prior motion data into background subtraction improves object detection.
Introduction 1 2 Analytic study of circles on the grid, bundles of discrete parabolas 11 3 Constr... more Introduction 1 2 Analytic study of circles on the grid, bundles of discrete parabolas 11 3 Construction of the floor parabolas with a cellular automaton 38 4 Construction of the floor circles 52 5 Ceiling parabolas and circles 55 6 Pitteway's and arithmetical circles 62 7 Conclusion 72 * This research has been done while the author was member of LIP, Ecole Normale Supérieure of Lyon.
With the definition of discrete lines introduced by Réveillès [REV91], there has been a wide rang... more With the definition of discrete lines introduced by Réveillès [REV91], there has been a wide range of research in discrete geometry and more precisely on the study of discrete lines. By the use of the linear time segment recognition algorithm of Debled and Réveillès [DR94], Vialard [VIA96a] has proposed a O(l) algorithm for computing the tangent in one point of a discrete curve where l is the average length of the tangent. By applying her algorithm to n points of a discrete curve, the complexity becomes O(n.l). This paper proposes a new approach for computing the tangent. It is based on a precise study of the tangent evolution along a discrete curve. The resulting algorithm has a O(n) complexity and is thus optimal. Some applications in curvature computation and a tombstones contours study are also presented.
Uploads
Papers by Laure Tougne