Laurent Bonnaud - Academia.edu (original) (raw)
Papers by Laurent Bonnaud
Proceedings Icip International Conference on Image Processing, Oct 1, 2006
ABSTRACT A method for detecting people in video streams is presented for the context of a front v... more ABSTRACT A method for detecting people in video streams is presented for the context of a front view monocular camera. This paper describes the proposed human model, which combines skin color and foreground probability maps by defining the spatial relationships that exist between them. The detection is performed with a Monte Carlo simulation for the defined Bayesian framework, in order to estimate the model parameters. The detected people are then associated with signatures, that are compared between consecutive frames in order to achieve tracking. Promising results are obtained for the detection and matching of multiple people, as presented for a transportation vehicle application
Proceedings of the 7th Ieee International Conference on Computer and Information Technology, Oct 16, 2007
ABSTRACT This paper presents an approach to optical blur estimation in images based on the measur... more ABSTRACT This paper presents an approach to optical blur estimation in images based on the measuring of the spread of edges. Two measures based on this approach are proposed. The first measure defines a model of amplified Gaussian with background for the profile of edges. The second measure is an approximation that does not require the extraction of profiles at edges. Both measures do not depend on the content or illumination of the image, making them suitable for dynamic videos. The behaviour of the proposed measures is finally presented in the context of dynamic videos from a surveillance camera embedded in a transportation vehicle.
Wec, 2005
Counting people from a video stream in a noisy environment is a challenging task. This project ai... more Counting people from a video stream in a noisy environment is a challenging task. This project aims at developing a counting system for transport vehicles, integrated in a video surveillance product. This article presents a method for the detection and tracking of multiple faces in a video by using a model of first and second order local moments. An iterative process is used to estimate the position and shape of multiple faces in images, and to track them. the trajectories are then processed to count people entering and leaving the vehicle.
DI-fusion, le D��p��t institutionnel num��rique de l'ULB, est l'outil de r��f��rencemen... more DI-fusion, le D��p��t institutionnel num��rique de l'ULB, est l'outil de r��f��rencementde la production scientifique de l'ULB.L'interface de recherche DI-fusion permet de consulter les publications des chercheurs de l'ULB et les th��ses qui y ont ��t�� d��fendues.
Personal and Ubiquitous Computing, 2009
This paper presents a driver simulator, which takes into account the information about the user&#... more This paper presents a driver simulator, which takes into account the information about the user's state of mind (level of attention, fatigue state, stress state). The user's state of mind analysis is based on video data and biological signals. Facial movements such as eyes blinking, yawning, head rotations, etc., are detected on video data: they are used in order to evaluate the fatigue and the attention level of the driver. The user's electrocardiogram and galvanic skin response are recorded and analyzed in order to ...
Journal on Multimodal User Interfaces, 2007
In this paper we focus on the software design of a multimodal driving simulator that is based on ... more In this paper we focus on the software design of a multimodal driving simulator that is based on both multimodal driver's focus of attention detection as well as driver's fatigue state detection and prediction. Capturing and interpreting the driver's focus of attention and fatigue state is based on video data (e.g., facial expression, head movement, eye tracking). While the input multimodal interface relies on passive modalities only (also called attentive user interface), the output multimodal user interface includes several active output modalities for presenting alert messages including graphics and text on a mini-screen and in the windshield, sounds, speech and vibration (vibration wheel). Active input modalities are added in the meta-User Interface to let the user dynamically select the output modalities. The driving simulator is used as a case study for studying its software architecture based on multimodal signal processing and multimodal interaction components considering two software platforms, OpenInterface and ICARE.
Abstract—This paper deals with visual servoing for a pan,and tilt camera,embedded,in a drone. Vid... more Abstract—This paper deals with visual servoing for a pan,and tilt camera,embedded,in a drone. Video is transmitted,to the ground where images are processed on a PC, and turret controls are sent back,to the drone. The objective is to track any,fixed object on the ground,without,knowledge,about shape or texture and,to keep,it centered,in the image. In order to achieve this task an algorithm,that combines,feature-based
Enformatika Conferences, 2005
Counting people from a video stream in a noisy environ- ment is a challenging task. This project ... more Counting people from a video stream in a noisy environ- ment is a challenging task. This project aims at developing a counting system for transport vehicles, integrated in a video surveillance product. This article presents a method for the detection and tracking of multiple faces in a video by using a model of first and second order local moments. An
This paper presents a system that can automatically recognize four different static human body po... more This paper presents a system that can automatically recognize four different static human body postures for video surveillance applications. The considered postures are standing, sitting, squatting, and lying. The data come from the persons 2D segmentation and from their face localization. It consists in distance measurements relative to a reference posture (standing, arms stretched horizontally). The recognition is based on data fusion using the belief theory, because this theory allows the modelling of imprecision and uncertainty. The efficiency and the limits of the recognition system are highlighted thanks to the processing of several thousands of frames. A considered application is the monitoring of elder people in hospitals or at home. This system allows real-time processing.
This paper introduces a video object segmentation algorithm developed in the context of the Europ... more This paper introduces a video object segmentation algorithm developed in the context of the European project Art.live1 where constraints on the quality of segmentation and the processing rate (at least 10 images/second) are required. In order to obtain a fine segmentation (no blocking effect, boundaries precision, temporal stability without flickering), the segmentation process is based on Markov Random Field (MRF) modelling which involves consecutive frame difference and a reference image in a unified way. Temporal changes of the luminance are predominant when the reference image is not yet available whereas the reference image prevails for low textured moving objects or for objects which stop moving for a while. The increased processing rate comes from the substitution of some Markovian iterations with morphological operations
Cet article décrit une tâche d'asservissement visuel pour une caméra commandable en pan et ti... more Cet article décrit une tâche d'asservissement visuel pour une caméra commandable en pan et tilt embarquée dans un drone. La tâche se résume à garder un objet sélectionné par l'utilisateur au centre de l'image quelques soient les mouvements du drone. Afin de réaliser cette tâche nous proposons un algorithme de suivi de primitives utilisant un système de prédiction basé sur l'analyse du mouvement global dans l'image. Cet algorithme permet une bonne robustesse aux très fortes perturbations dues à la transmission vidéo et fonctionne à une cadence proche de la cadence vidéo. La commande du système est basée sur une loi de commande à double boucle, qui assure une convergence rapide vers la position désirée. L'expérimentation en conditions réelles montre l'efficacité du système proposé.
Enformatika Conferences, 2005
This paper presents various classifiers results from a syste m that can automatically recognize f... more This paper presents various classifiers results from a syste m that can automatically recognize four different static human body postures in video sequences. The considered postures are standing, sitting, squatting, and lying. The three classifiers considered are a na¨ ive one and two base d on the belief theory. The belief theory-based classifiers use either a cla ssic or restricted
The context of this work is a European projectart.live1 which aims at mixing real and virtual wor... more The context of this work is a European projectart.live1 which aims at mixing real and virtual worlds for multime- dia applications. This paper focuses on an algorithm for the detection and tracking of face and both hands of segmented pe r- sons standing in front of a camera. The first step consists in t he detection of skin pixels based
Proceedings. IEEE Conference on Advanced Video and Signal Based Surveillance, 2005., 2005
Abstract This paper presents a system that can automatically rec- ognize four different static hu... more Abstract This paper presents a system that can automatically rec- ognize four different static human,body postures for video surveillance applications. The considered postures are standing, sitting, squatting, and lying. The data come from the persons 2D segmentation and from their face localiza- tion. It consists in distance measurements,relative to a ref- erence posture (standing, arms stretched horizontally). The recognition is
6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004., 2004
Several results show the efficiency of this method. This algorithm allows real time processing.
Machine Vision Applications, 2007
This paper deals with visual servoing for a pan and tilt camera embedded in a drone. Video is tra... more This paper deals with visual servoing for a pan and tilt camera embedded in a drone. Video is transmitted to the ground where images are processed on a PC, and turret controls are sent back to the drone. The objective is to track any fixed object on the ground without knowledge about shape or texture and to keep it centered in the image. In order to achieve this task an algorithm that combines feature-based and global motion estimation is proposed. This algorithm provides a good robustness to very strong video transmission noise and works at a frame rate close to 25 fps. The control of the system is based on a double closed loop, which achieves a fast convergence to the desired position. Experimentation in real conditions shows the effectiveness of the proposed scheme.
Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205), 2001
This paper introduces a video object segmentation algorithm developed in the context of the Europ... more This paper introduces a video object segmentation algorithm developed in the context of the European project Art.live 1 where constraints on the quality of segmentation and the processing rate (at least 10 images/second) are required. In order to obtain a fine segmentation (no blocking effect, boundaries precision, temporal stability without flickering), the segmentation process is based on Markov Random Field (MRF) modelling which involves consecutive frame difference and a reference image in a unified way. Temporal changes of the luminance are predominant when the reference image is not yet available whereas the reference image prevails for low textured moving objects or for objects which stop moving for a while.
Visual Information Processing XII, 2003
ABSTRACT In this paper, we present a new method to compress the information in an image, called M... more ABSTRACT In this paper, we present a new method to compress the information in an image, called MeshEZW. The proposed approach is based on the finite elements method, a mesh construction and a zerotree method. The zerotree method is an adaptive of the EZW algorithm with two new symbols for increasing the performance. These steps allow a progressive representation of the image by the automatic construction of a bitstream. The mesh structure is adapted to the image compression domain and is defined to allow video comrpession. The coder is described and some preliminary results are discussed.
ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005., 2005
Our project is to design algorithms to count people in vehicles such as buses from surveillance c... more Our project is to design algorithms to count people in vehicles such as buses from surveillance cameras' video streams. This article presents a method of detection and tracking of multiple faces in a video by using a model of first and second order local moments. The three essential steps of our system are the skin color modeling, the probabilistic shape model and bayesian decision, and the tracking. An iterative processus estimates the position and shape of multiple faces in images, and tracks them. Tracking updates an object history including all spatial and temporal information about this object. Location and size of these tracking object are predicted by constant speed motion analysis and learned trajectories. Results on office and buses video are promising.
Proceedings Icip International Conference on Image Processing, Oct 1, 2006
ABSTRACT A method for detecting people in video streams is presented for the context of a front v... more ABSTRACT A method for detecting people in video streams is presented for the context of a front view monocular camera. This paper describes the proposed human model, which combines skin color and foreground probability maps by defining the spatial relationships that exist between them. The detection is performed with a Monte Carlo simulation for the defined Bayesian framework, in order to estimate the model parameters. The detected people are then associated with signatures, that are compared between consecutive frames in order to achieve tracking. Promising results are obtained for the detection and matching of multiple people, as presented for a transportation vehicle application
Proceedings of the 7th Ieee International Conference on Computer and Information Technology, Oct 16, 2007
ABSTRACT This paper presents an approach to optical blur estimation in images based on the measur... more ABSTRACT This paper presents an approach to optical blur estimation in images based on the measuring of the spread of edges. Two measures based on this approach are proposed. The first measure defines a model of amplified Gaussian with background for the profile of edges. The second measure is an approximation that does not require the extraction of profiles at edges. Both measures do not depend on the content or illumination of the image, making them suitable for dynamic videos. The behaviour of the proposed measures is finally presented in the context of dynamic videos from a surveillance camera embedded in a transportation vehicle.
Wec, 2005
Counting people from a video stream in a noisy environment is a challenging task. This project ai... more Counting people from a video stream in a noisy environment is a challenging task. This project aims at developing a counting system for transport vehicles, integrated in a video surveillance product. This article presents a method for the detection and tracking of multiple faces in a video by using a model of first and second order local moments. An iterative process is used to estimate the position and shape of multiple faces in images, and to track them. the trajectories are then processed to count people entering and leaving the vehicle.
DI-fusion, le D��p��t institutionnel num��rique de l'ULB, est l'outil de r��f��rencemen... more DI-fusion, le D��p��t institutionnel num��rique de l'ULB, est l'outil de r��f��rencementde la production scientifique de l'ULB.L'interface de recherche DI-fusion permet de consulter les publications des chercheurs de l'ULB et les th��ses qui y ont ��t�� d��fendues.
Personal and Ubiquitous Computing, 2009
This paper presents a driver simulator, which takes into account the information about the user&#... more This paper presents a driver simulator, which takes into account the information about the user's state of mind (level of attention, fatigue state, stress state). The user's state of mind analysis is based on video data and biological signals. Facial movements such as eyes blinking, yawning, head rotations, etc., are detected on video data: they are used in order to evaluate the fatigue and the attention level of the driver. The user's electrocardiogram and galvanic skin response are recorded and analyzed in order to ...
Journal on Multimodal User Interfaces, 2007
In this paper we focus on the software design of a multimodal driving simulator that is based on ... more In this paper we focus on the software design of a multimodal driving simulator that is based on both multimodal driver's focus of attention detection as well as driver's fatigue state detection and prediction. Capturing and interpreting the driver's focus of attention and fatigue state is based on video data (e.g., facial expression, head movement, eye tracking). While the input multimodal interface relies on passive modalities only (also called attentive user interface), the output multimodal user interface includes several active output modalities for presenting alert messages including graphics and text on a mini-screen and in the windshield, sounds, speech and vibration (vibration wheel). Active input modalities are added in the meta-User Interface to let the user dynamically select the output modalities. The driving simulator is used as a case study for studying its software architecture based on multimodal signal processing and multimodal interaction components considering two software platforms, OpenInterface and ICARE.
Abstract—This paper deals with visual servoing for a pan,and tilt camera,embedded,in a drone. Vid... more Abstract—This paper deals with visual servoing for a pan,and tilt camera,embedded,in a drone. Video is transmitted,to the ground where images are processed on a PC, and turret controls are sent back,to the drone. The objective is to track any,fixed object on the ground,without,knowledge,about shape or texture and,to keep,it centered,in the image. In order to achieve this task an algorithm,that combines,feature-based
Enformatika Conferences, 2005
Counting people from a video stream in a noisy environ- ment is a challenging task. This project ... more Counting people from a video stream in a noisy environ- ment is a challenging task. This project aims at developing a counting system for transport vehicles, integrated in a video surveillance product. This article presents a method for the detection and tracking of multiple faces in a video by using a model of first and second order local moments. An
This paper presents a system that can automatically recognize four different static human body po... more This paper presents a system that can automatically recognize four different static human body postures for video surveillance applications. The considered postures are standing, sitting, squatting, and lying. The data come from the persons 2D segmentation and from their face localization. It consists in distance measurements relative to a reference posture (standing, arms stretched horizontally). The recognition is based on data fusion using the belief theory, because this theory allows the modelling of imprecision and uncertainty. The efficiency and the limits of the recognition system are highlighted thanks to the processing of several thousands of frames. A considered application is the monitoring of elder people in hospitals or at home. This system allows real-time processing.
This paper introduces a video object segmentation algorithm developed in the context of the Europ... more This paper introduces a video object segmentation algorithm developed in the context of the European project Art.live1 where constraints on the quality of segmentation and the processing rate (at least 10 images/second) are required. In order to obtain a fine segmentation (no blocking effect, boundaries precision, temporal stability without flickering), the segmentation process is based on Markov Random Field (MRF) modelling which involves consecutive frame difference and a reference image in a unified way. Temporal changes of the luminance are predominant when the reference image is not yet available whereas the reference image prevails for low textured moving objects or for objects which stop moving for a while. The increased processing rate comes from the substitution of some Markovian iterations with morphological operations
Cet article décrit une tâche d'asservissement visuel pour une caméra commandable en pan et ti... more Cet article décrit une tâche d'asservissement visuel pour une caméra commandable en pan et tilt embarquée dans un drone. La tâche se résume à garder un objet sélectionné par l'utilisateur au centre de l'image quelques soient les mouvements du drone. Afin de réaliser cette tâche nous proposons un algorithme de suivi de primitives utilisant un système de prédiction basé sur l'analyse du mouvement global dans l'image. Cet algorithme permet une bonne robustesse aux très fortes perturbations dues à la transmission vidéo et fonctionne à une cadence proche de la cadence vidéo. La commande du système est basée sur une loi de commande à double boucle, qui assure une convergence rapide vers la position désirée. L'expérimentation en conditions réelles montre l'efficacité du système proposé.
Enformatika Conferences, 2005
This paper presents various classifiers results from a syste m that can automatically recognize f... more This paper presents various classifiers results from a syste m that can automatically recognize four different static human body postures in video sequences. The considered postures are standing, sitting, squatting, and lying. The three classifiers considered are a na¨ ive one and two base d on the belief theory. The belief theory-based classifiers use either a cla ssic or restricted
The context of this work is a European projectart.live1 which aims at mixing real and virtual wor... more The context of this work is a European projectart.live1 which aims at mixing real and virtual worlds for multime- dia applications. This paper focuses on an algorithm for the detection and tracking of face and both hands of segmented pe r- sons standing in front of a camera. The first step consists in t he detection of skin pixels based
Proceedings. IEEE Conference on Advanced Video and Signal Based Surveillance, 2005., 2005
Abstract This paper presents a system that can automatically rec- ognize four different static hu... more Abstract This paper presents a system that can automatically rec- ognize four different static human,body postures for video surveillance applications. The considered postures are standing, sitting, squatting, and lying. The data come from the persons 2D segmentation and from their face localiza- tion. It consists in distance measurements,relative to a ref- erence posture (standing, arms stretched horizontally). The recognition is
6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004., 2004
Several results show the efficiency of this method. This algorithm allows real time processing.
Machine Vision Applications, 2007
This paper deals with visual servoing for a pan and tilt camera embedded in a drone. Video is tra... more This paper deals with visual servoing for a pan and tilt camera embedded in a drone. Video is transmitted to the ground where images are processed on a PC, and turret controls are sent back to the drone. The objective is to track any fixed object on the ground without knowledge about shape or texture and to keep it centered in the image. In order to achieve this task an algorithm that combines feature-based and global motion estimation is proposed. This algorithm provides a good robustness to very strong video transmission noise and works at a frame rate close to 25 fps. The control of the system is based on a double closed loop, which achieves a fast convergence to the desired position. Experimentation in real conditions shows the effectiveness of the proposed scheme.
Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205), 2001
This paper introduces a video object segmentation algorithm developed in the context of the Europ... more This paper introduces a video object segmentation algorithm developed in the context of the European project Art.live 1 where constraints on the quality of segmentation and the processing rate (at least 10 images/second) are required. In order to obtain a fine segmentation (no blocking effect, boundaries precision, temporal stability without flickering), the segmentation process is based on Markov Random Field (MRF) modelling which involves consecutive frame difference and a reference image in a unified way. Temporal changes of the luminance are predominant when the reference image is not yet available whereas the reference image prevails for low textured moving objects or for objects which stop moving for a while.
Visual Information Processing XII, 2003
ABSTRACT In this paper, we present a new method to compress the information in an image, called M... more ABSTRACT In this paper, we present a new method to compress the information in an image, called MeshEZW. The proposed approach is based on the finite elements method, a mesh construction and a zerotree method. The zerotree method is an adaptive of the EZW algorithm with two new symbols for increasing the performance. These steps allow a progressive representation of the image by the automatic construction of a bitstream. The mesh structure is adapted to the image compression domain and is defined to allow video comrpession. The coder is described and some preliminary results are discussed.
ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005., 2005
Our project is to design algorithms to count people in vehicles such as buses from surveillance c... more Our project is to design algorithms to count people in vehicles such as buses from surveillance cameras' video streams. This article presents a method of detection and tracking of multiple faces in a video by using a model of first and second order local moments. The three essential steps of our system are the skin color modeling, the probabilistic shape model and bayesian decision, and the tracking. An iterative processus estimates the position and shape of multiple faces in images, and tracks them. Tracking updates an object history including all spatial and temporal information about this object. Location and size of these tracking object are predicted by constant speed motion analysis and learned trajectories. Results on office and buses video are promising.