About
66
Publications
27,427
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
813
Citations
Introduction
D. Vivet currently works at the Department of Electronics, Optronics and Signal, Institut Supérieur de l'Aéronautique et de l'Espace (ISAE). Damien does research in Electrical Engineering, Transportation Engineering and Perception. Their current projects are 'AVISé' and 'STAR'.
Additional affiliations
December 2015 - present
September 2013 - December 2015
September 2012 - August 2013
Le Laboratoire d'Informatique, du Traitement de l'Information et des Systèmes (LITIS Rouen)
Position
- ATER
Education
September 2007 - August 2008
September 2005 - August 2008
CUST
Field of study
- Electrical Engineering
September 2003 - August 2005
Institut Universitaire de Technologie de Montpellier 2
Field of study
- Sensor Technologies and Measurements
Publications
Publications (66)
Planetary defense efforts rely on estimates of the mechanical properties of asteroids, which are difficult to constrain accurately from Earth. The mechanical properties of asteroid material are also important in the interpretation of the Double Asteroid Redirection Test (DART) impact. Here we perform a detailed morphological analysis of the surface...
The bearing capacity - the ability of a surface to support applied loads - is an important parameter for understanding and predicting the response of a surface. Previous work has inferred the bearing capacity and trafficability of specific regions of the Moon using orbital imagery and measurements of the boulder tracks visible on its surface. Here,...
Urban environments are undergoing significant transformations, with pedestrian areas emerging as complex hubs of diverse mobility modes. This shift demands a more nuanced approach to urban planning and navigation technologies, highlighting the limitations of traditional, road-centric datasets in capturing the detailed dynamics of pedestrian spaces....
Visual navigation has achieved significant maturity in recent decades. Indirect methods relying on sparse feature extraction, have become a standard for state estimation. However, these techniques are not frequently utilized as inputs for path planning due to the sparse nature of their maps. To address this limitation, this paper introduces a metho...
Multi-object tracking (MOT) is one of the most essential and challenging tasks in computer vision (CV). Unlike object detectors, MOT systems nowadays are more complicated and consist of several neural network models. Thus, the balance between the system performance and the runtime is crucial for online scenarios. While some of the works contribute...
In this paper, we propose an innovative solution: indirect bi-monocular visual odometry with a non-recovering field of view in order to make the most effective use of available camera pixels. Leveraging sliding-window optimization techniques, we aim to overcome the inherent difficulties in accurately estimating scale in displacement and environment...
Multi-object tracking (MOT) is a critical task in various domains, such as traffic analysis, surveillance, and autonomous vehicles. The joint-detection-and-tracking paradigm has been extensively researched, which appears to be faster, more convenient for training and deploying over the classic tracking-by-detection paradigm while achieving state-of...
We propose a modular bi-monocular indirect approach adapted to every camera model while keeping the processing load as low as possible. This paper presents an experimental study in a self illuminated cave environment. We focus on keypoint /descriptor pairs, feature association modalities and camera models.
This work addressed the problem of miscalibration or decalibration of mobile stereo/bi-monocular camera setups. We especially focused on the context of autonomous vehicles. In real-world conditions, any optical system is subject to various mechanical stresses, caused by vibration, rough handling, collisions, or even thermal expansion. Such mechanic...
This paper addresses the problem of monocular Simultaneous Localization And Mapping on Lie groups using fiducial patterns. For that purpose, we propose a reformulation of the classical camera model as a model on matrix Lie groups. Thus, we define an original-state vector containing the camera pose and the set of transformations from the world frame...
This letter addresses the robust state estimation problem for mismatched nonlinear dynamic systems. In this context, we are interested in nonlinear filters able to provide consistent estimates while mitigating the impact of possible modeling errors. We focus on the cubature Kalman filter (CKF) and its square-root form (SCKF), being the most promisi...
This paper addresses the problem of monocular Simultaneous Localisation And Mapping on Lie groups using fiducial patterns. For that purpose, we propose to reformulate the classical camera model as a model on matrix Lie groups. We thus define an original vector state containing the camera pose and the set of transformations from the world frame to e...
The technological advancement of sensors and computational power has opened a new chapter in machine learning for robotics applications, especially in image classification, segmentation, object detection, and self-driving cars. One of the challenges among these applications is improving the systems perception reliability and accuracy through sensor...
Existing methods for video instance segmentation (VIS) mostly rely on two strategies: (1) building a sophisticated post-processing to associate frame level segmentation results and (2) modeling a video clip as a 3D spatial-temporal volume with a limit of resolution and length due to memory constraints. In this work, we propose a frame-to-frame meth...
It is well known that the standard state estimation technique performance is particularly sensitive to perfect system knowledge, where the underlying assumptions are: (i) Process and measurement functions and parameters are known, (ii) inputs are known, and (iii) noise statistics are known. These are rather strong assumptions in real-life applicati...
A fusion of LiDAR and cameras have been widely used in many robotics applications such as classification, segmentation, object detection, and autonomous driving. It is essential that the LiDAR sensor can measure distances accurately, which is a good complement to the cameras. Hence, calibrating sensors before deployment is a mandatory step. The mai...
A fusion of LiDAR and cameras have been widely used in many robotics applications such as classification, segmentation, object detection, and autonomous driving. It is essential that the LiDAR sensor can measure distances accurately, which is a good complement to the cameras. Hence, calibrating sensors before deployment is a mandatory step. The con...
The existing methods for video object detection mainly depend on two-stage image object detectors. The fact that two-stage detectors are generally slow makes it difficult to apply in real-time scenarios. Moreover, adapting directly existing methods to a one-stage detector is inefficient or infeasible. In this work, we introduce a method based on a...
Standard state estimation techniques, ranging from the linear Kalman filter (KF) to nonlinear extended KF (EKF), sigma‐point or particle filters, assume a perfectly known system model, that is, process and measurement functions and system noise statistics (both the distribution and its parameters). This is a strong assumption which may not hold in...
Current navigation systems use multi-sensor data to improve the localization accuracy, but often without certitude on the quality of those measurements in certain situations. The context detection will enable us to build an adaptive navigation system to improve the precision and the robustness of its localization solution by anticipating possible d...
Autonomous navigation requires both a precise and robust mapping and localization solution. In this context, Simultaneous Localization and Mapping (SLAM) is a very well-suited solution. SLAM is used for many applications including mobile robotics, self-driving cars, unmanned aerial vehicles, or autonomous underwater vehicles. In these domains, both...
This article introduces a new class of recursive linearly constrained minimum variance estimators (LCMVEs) that provides additional robustness to modeling errors. To achieve that robustness, a set of non-stationary linear constraints are added to the standard LCMVE that allow for a closed form solution that becomes appealing in sequential implement...
The increased autonomy of robots is directly linked to their capability to perceive their environment. Simultaneous Localization and Mapping (SLAM) techniques, which associate perception and movement, are particularly interesting because they provide advanced autonomy to vehicles in the field of Intelligent Transportation Systems (ITS). Such ITS ar...
Nous présentons dans cet article une nouvelle méthode de détection d’événements rares basée sur l’analyse des mouvements saillants dans une scène. La méthode vise à localiser automatiquement toutes les régions d’une scène où se déroulent des événements rares. Un événement rare s’oppose aux événements fréquents en ce sens qu’on y intégre tout événem...
This paper presents a new method for the detection of rares events in video. It is based on the visual saliency and on the detection and local description of points of interest. The point-of-interest filtering is carried out using the saliency score, allowing only those with visual importance to be considered. A model of normal events is learned th...
In this work, we investigated the abnormal events detection in video using visual saliency for Spatio-temporal interest point selection, combined with the Latent Dirichlet Allocation for event modeling. The point-of-interest filtering is carried out using the saliency score, allowing only those with visual importance to be considered. A model of no...
In this paper, we propose a framework in order to automatically extract the 3D pose of an individual from a single silhouette image obtained with a classical low-cost camera without any depth information. By pose, we mean the configuration of human bones in order to reconstruct a 3D skeleton representing the 3D posture of the detected human. Our ap...
This work focuses on the problem of automatically extracting human 3D poses from a single 2D image. By pose we mean the configuration of human bones in order to reconstruct a 3D skeleton representing the 3D posture of the detected human. This problem is highly non-linear in nature and confounds standard regression techniques. Our approach combines...
The purpose of this paper is to develop a wrapper Random Forest-based feature selection method and to study the performance on emotion recognition of different selected feature sets. A large bank of Gabor filters is used to extract the face appearance. A feature selection is then applied on the wide feature set based on feature importance score com...
According to a new market research report, Electronic Access Control System is expected to reach $16.3 billion by 2017. Vision based biometric authentication systems have received much attention with increasing demands for long distance surveillance applications and access control to the security area. Such visual application is mainly focused on f...
Les autorités publiques et les gestionnaires de la route ont fait de la sécurité des deux roues mobiles (2RM) une priorité. En 2012, les chiffres officiels montrent que le trafic des 2RM représente 2% du trafic global mais 30% des accidents mortels. Cette étude montre que les risques encourus par les 2RM sont 24 fois plus élevés que pour les autres...
The safety of Powered Two Wheelers (PTWs) is an issue of concern for public authorities and road administrators around the world. In 2011, the official figures show that the PTW is estimated to represent only 2% of the total traffic but represents 30% of the deaths on the roads in France. The ambiguity in the values is due to the fact that the PTWs...
Powered Two Wheelers (PTWs) represent only 2% of the traffic, but 30% of all deaths on the road. European governments have made this particular point a priority for road safety. The present study overcomes the lack of PTW traffic-analyser systems in real traffic conditions. We propose a detection technique based on a single 2D lidar sensor. This sy...
This paper presents a fast method to estimate the probability of occupancy of a space point from a huge set of 3D rays represented in a common reference. These data can come from any range finding sensor such as : Lidar, Kinect or Velodyne. The key idea is to consider that the occupancy of a space 3D point is linked to 1) the number of 3D point bel...
Rotating radar sensors are perception systems rarely used in mobile robotics. This paper is concerned with the use of a mobile ground-based panoramic radar sensor which is able to deliver both distance and velocity of multiple targets in its surrounding. The consequence of using such a sensor in high speed robotics is the appearance of both geometr...
Abstract This paper is concerned with robotic applications using a ground‐based radar sensor for
simultaneous localization and mapping problems. In mobile robotics, radar technology is interesting because of its long range and the robustness of radar waves to atmospheric conditions, making these sensors well‐suited for extended outdoor robotic app...
Résumé— Le projet IMPALA s'effectue dans le cadre d'une collaboration scientifique entre deux structures de recherche et un industriel : le LASMEA, le Cemagref et THALES. Il porte sur l'utilisation d'un radar panoramique hyperfréquence pour des applications de localisation et de cartographie simultanées en milieu extérieur (connu sous l'acronyme an...
This paper describes a full 6D localization algorithm based on probabilistic motion field. The motion field is obtained by an adaptation of the video compression algorithm known as Block-Matching which provides a sparse optical flow. Such a technique is very fast and allows real time applications. Image is decomposed in a grid of rectangular blocks...
The use of a rotating range sensor in high speed robotics creates distortions in the collected data. Such an effect is, in the majority of studies, ignored or considered as a noise and then corrected, based on proprioceptive sensors or localization systems. In this study we consider that distortion contains the information about the vehicle's displ...
The use of a rotating range sensor in high speed robotics creates distortions in the collected data. Such an effect is, in the majority of studies, ignored or considered as noise and then corrected, based on proprioceptive sensors or localization systems. In this study we consider that distortion contains the information about the vehicle's displac...
The detection and tracking of moving objects (DATMO) in an outdoor environment from a mobile robot are difficult tasks because of the wide variety of dynamic objects. A reliable discrimination of mobile and static detections without any prior knowledge is often conditioned by a good position estimation obtained using Global Positionning System/Diff...
Résumé L'utilisation d'un capteur télémétrique tournant en robo-tique mobile à haute vitesse implique l'apparition de dis-torsions sur les données collectées. Un tel effet est, dans la majorité des études, ignoré ou considéré comme un bruit et, de ce fait, corrigé en utilisant des capteurs propriocep-tifs ou des systèmes de localisation. Dans cet a...
Le projet IMPALA rattaché à l’appel à projets PSIROB 2006 de l’Agence Nationale de la Recherche réunit deux structures de recherche et un industriel : IRSTEA, le LASMEA et THALES Optronique. L’objectif du projet est d’évaluer l’apport du radar comme solution alternative aux moyens de perception en robotique mobile d’extérieur. Cet article illustre...
In outdoor robotic context, notion of perception and localization is essential for an autonomous navigation of a mobile robot. The objectives of this PhD are multiple and tend to develop a simultaneous localization and mapping approach in a dynamic outdoor environment with detection and tracking of moving objects (SLAMMOT) with a unique exterocepti...
This paper is concerned with the Simultaneous Localization And Mapping (SLAM) application with a mobile robot moving in a structured environment using data obtained from rotating sensors such as radars or lasers. A line-based EKF-SLAM (EKF stands for Extended Kalman Filter) algorithm is presented, which is able to deal with data that cannot be cons...
Résumé Cet article concerne la cartographie d'un environnement d'extérieur à partir d'un robot mobile muni de capteurs. Le robot cherche en simultané à se localiser dans le milieu qu'il explore. Le monde visité est initialement considéré comme statique mais le challenge à relever est d'être en mesure de cartographier et de se localiser tout en iden...
Questions
Question (1)
I have motion capture information in bvh format, for my application I need to obtain all the joints coordinates in a 3D frame. Is there any parser to directly obtain from all the OFFSET and MOTION information such information ?