Nous proposons une methode de transfert d'apprentissage de type transductif basee sur un filt... more Nous proposons une methode de transfert d'apprentissage de type transductif basee sur un filtre sequentiel de Monte Carlo pour la specialisation d'un classifieur generique vers un domaine cible donne. Nous presentons une application de cette methode pour specialiser un detecteur de pietons generique a une scene de trafic routier. Les performances enregistrees du detecteur specialise sur des donnees reelles avec un seul faux positif par image, depassent celles du detecteur generique de plus de 40%.
Depuis les années 2000, un progrès significatif est enregistré dans les travaux de recherche qui ... more Depuis les années 2000, un progrès significatif est enregistré dans les travaux de recherche qui proposent l’apprentissage de détecteurs d’objets sur des grandes bases de données étiquetées manuellement et disponibles publiquement. Cependant, lorsqu’un détecteur générique d’objets est appliqué sur des images issues d’une scène spécifique les performances de détection diminuent considérablement. Cette diminution peut être expliquée par les différences entre les échantillons de test et ceux d’apprentissage au niveau des points de vues prises par la(les) caméra(s), de la résolution, de l’éclairage et du fond des images. De plus, l’évolution de la capacité de stockage des systèmes informatiques, la démocratisation de la "vidéo-surveillance" et le développement d’outils d’analyse automatique des données vidéos encouragent la recherche dans le domaine du trafic routier. Les buts ultimes sont l’évaluation des demandes de gestion du trafic actuelles et futures, le développement de...
Abstract Generally, the performance of a generic detector decreases significantly when it is test... more Abstract Generally, the performance of a generic detector decreases significantly when it is tested on a specific scene due to the large variation between the source training dataset and the samples from the target scene. To solve this problem, we propose a new formalism of transfer learning based on the theory of a Sequential Monte Carlo (SMC) filter to automatically specialize a scene-specific Faster R-CNN detector. The suggested framework uses different strategies based on the SMC filter steps to approximate iteratively the target distribution as a set of samples in order to specialize the Faster R-CNN detector towards a target scene. Moreover, we put forward a likelihood function that combines spatio-temporal information extracted from the target video sequence and the confidence-score given by the output layer of the Faster R-CNN, to favor the selection of target samples associated with the right label. The effectiveness of the suggested framework is demonstrated through experiments on several public traffic datasets. Compared with the state-of-the-art specialization frameworks, the proposed framework presents encouraging results for both single and multi-traffic object detections.
EURASIP Journal on Image and Video Processing, 2016
Transfer learning approaches have shown interesting results by using knowledge from source domain... more Transfer learning approaches have shown interesting results by using knowledge from source domains to learn a specialized classifier/detector for a target domain containing unlabeled data or only a few labeled samples. In this paper, we present a new transductive transfer learning framework based on a sequential Monte Carlo filter to specialize a generic classifier towards a specific scene. The proposed framework utilizes different strategies and approximates iteratively the hidden target distribution as a set of samples in order to learn a specialized classifier. These training samples are selected from both source and target domains according to their weight importance, which indicates that they belong to the target distribution. The resulting classifier is applied to pedestrian and car detection on several challenging traffic scenes. The experiments have demonstrated that our solution improves and outperforms several state of the art's specialization algorithms on public datasets.
2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2016
The performance of the learning-based detector depends much on its training dataset and decreases... more The performance of the learning-based detector depends much on its training dataset and decreases rapidly when it is tested on a new scene. The reason is that in the large variations between the source training dataset and target scene. To solve this problem, we propose a novel approach to automatically specialize a generic detector to specific scene by utilizing the sequential Monte Carlo filter and the Faster R-CNN deep model. The main idea is to consider the Faster R-CNN as a function that generates realizations from the probability distribution of the object to be detected in the target sequence. Our contribution is to approximate this target probability distribution with a set of samples and an associated specialized Faster R-CNN estimated in a sequential Bayesian filter framework. The resulting algorithm is compared to the state of the art scene specialization methods on several challenging datasets, the results are very promising.
Depuis les annees 2000, un progres significatif est enregistre dans les travaux de recherche qui ... more Depuis les annees 2000, un progres significatif est enregistre dans les travaux de recherche qui proposent l’apprentissage de detecteurs d’objets sur des grandes bases de donnees etiquetees manuellement et disponibles publiquement. Cependant, lorsqu’un detecteur generique d’objets est applique sur des images issues d’une scene specifique les performances de detection diminuent considerablement. Cette diminution peut etre expliquee par les differences entre les echantillons de test et ceux d’apprentissage au niveau des points de vues prises par la(les) camera(s), de la resolution, de l’eclairage et du fond des images.De plus, l’evolution de la capacite de stockage des systemes informatiques, la democratisation de la "video-surveillance" et le developpement d’outils d’analyse automatique des donnees videos encouragent la recherche dans le domaine du trafic routier. Les buts ultimes sont l’evaluation des demandes de gestion du trafic actuelles et futures, le developpement des...
EURASIP Journal on Image and Video Processing, 2016
Transfer learning approaches have shown interesting results by using knowledge from source domain... more Transfer learning approaches have shown interesting results by using knowledge from source domains to learn a specialized classifier/detector for a target domain containing unlabeled data or only a few labeled samples. In this paper, we present a new transductive transfer learning framework based on a sequential Monte Carlo filter to specialize a generic classifier towards a specific scene. The proposed framework utilizes different strategies and approximates iteratively the hidden target distribution as a set of samples in order to learn a specialized classifier. These training samples are selected from both source and target domains according to their weight importance, which indicates that they belong to the target distribution. The resulting classifier is applied to pedestrian and car detection on several challenging traffic scenes. The experiments have demonstrated that our solution improves and outperforms several state of the art's specialization algorithms on public datasets.
Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2016
In this paper, we tackle the problem of domain adaptation to perform object-classification and de... more In this paper, we tackle the problem of domain adaptation to perform object-classification and detection tasks in video surveillance starting by a generic trained detector. Precisely, we put forward a new transductive transfer learning framework based on a sequential Monte Carlo filter to specialize a generic classifier towards a specific scene. The proposed algorithm approximates iteratively the target distribution as a set of samples (selected from both source and target domains) which feed the learning step of a specialized classifier. The output classifier is applied to pedestrian detection into a traffic scene. We have demonstrated by many experiments, on the CUHK Square Dataset and the MIT Traffic Dataset, that the performance of the specialized classifier outperforms the generic classifier and that the suggested algorithm presents encouraging results.
10Th International Multi Conferences on Systems Signals Devices 2013, 2013
This paper presents a solution capable of recognizing the facial expressions performed by a perso... more This paper presents a solution capable of recognizing the facial expressions performed by a person's face and mapping them to a 3D face virtual model and RGB data captured from Microsoft's Kinect solution starts by detecting the face and segmenting its regions, then, it identifies the actual expression using EigenFace metrics on the RGB images and reconstructs the face from the filtered Depth data. A new dataset relative to subjects is introduced for learning purposes. It cont images and point clouds for the different facial expressions performed. The algorithm seeks and displays automatically the seven state of the art expressions including surprise, fear, disgust, anger, joy, sadness and the neutral appearance. As result our system shows a morphing sequence between of 3D face avatar models.
Nous proposons une methode de transfert d'apprentissage de type transductif basee sur un filt... more Nous proposons une methode de transfert d'apprentissage de type transductif basee sur un filtre sequentiel de Monte Carlo pour la specialisation d'un classifieur generique vers un domaine cible donne. Nous presentons une application de cette methode pour specialiser un detecteur de pietons generique a une scene de trafic routier. Les performances enregistrees du detecteur specialise sur des donnees reelles avec un seul faux positif par image, depassent celles du detecteur generique de plus de 40%.
Depuis les années 2000, un progrès significatif est enregistré dans les travaux de recherche qui ... more Depuis les années 2000, un progrès significatif est enregistré dans les travaux de recherche qui proposent l’apprentissage de détecteurs d’objets sur des grandes bases de données étiquetées manuellement et disponibles publiquement. Cependant, lorsqu’un détecteur générique d’objets est appliqué sur des images issues d’une scène spécifique les performances de détection diminuent considérablement. Cette diminution peut être expliquée par les différences entre les échantillons de test et ceux d’apprentissage au niveau des points de vues prises par la(les) caméra(s), de la résolution, de l’éclairage et du fond des images. De plus, l’évolution de la capacité de stockage des systèmes informatiques, la démocratisation de la "vidéo-surveillance" et le développement d’outils d’analyse automatique des données vidéos encouragent la recherche dans le domaine du trafic routier. Les buts ultimes sont l’évaluation des demandes de gestion du trafic actuelles et futures, le développement de...
Abstract Generally, the performance of a generic detector decreases significantly when it is test... more Abstract Generally, the performance of a generic detector decreases significantly when it is tested on a specific scene due to the large variation between the source training dataset and the samples from the target scene. To solve this problem, we propose a new formalism of transfer learning based on the theory of a Sequential Monte Carlo (SMC) filter to automatically specialize a scene-specific Faster R-CNN detector. The suggested framework uses different strategies based on the SMC filter steps to approximate iteratively the target distribution as a set of samples in order to specialize the Faster R-CNN detector towards a target scene. Moreover, we put forward a likelihood function that combines spatio-temporal information extracted from the target video sequence and the confidence-score given by the output layer of the Faster R-CNN, to favor the selection of target samples associated with the right label. The effectiveness of the suggested framework is demonstrated through experiments on several public traffic datasets. Compared with the state-of-the-art specialization frameworks, the proposed framework presents encouraging results for both single and multi-traffic object detections.
EURASIP Journal on Image and Video Processing, 2016
Transfer learning approaches have shown interesting results by using knowledge from source domain... more Transfer learning approaches have shown interesting results by using knowledge from source domains to learn a specialized classifier/detector for a target domain containing unlabeled data or only a few labeled samples. In this paper, we present a new transductive transfer learning framework based on a sequential Monte Carlo filter to specialize a generic classifier towards a specific scene. The proposed framework utilizes different strategies and approximates iteratively the hidden target distribution as a set of samples in order to learn a specialized classifier. These training samples are selected from both source and target domains according to their weight importance, which indicates that they belong to the target distribution. The resulting classifier is applied to pedestrian and car detection on several challenging traffic scenes. The experiments have demonstrated that our solution improves and outperforms several state of the art's specialization algorithms on public datasets.
2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2016
The performance of the learning-based detector depends much on its training dataset and decreases... more The performance of the learning-based detector depends much on its training dataset and decreases rapidly when it is tested on a new scene. The reason is that in the large variations between the source training dataset and target scene. To solve this problem, we propose a novel approach to automatically specialize a generic detector to specific scene by utilizing the sequential Monte Carlo filter and the Faster R-CNN deep model. The main idea is to consider the Faster R-CNN as a function that generates realizations from the probability distribution of the object to be detected in the target sequence. Our contribution is to approximate this target probability distribution with a set of samples and an associated specialized Faster R-CNN estimated in a sequential Bayesian filter framework. The resulting algorithm is compared to the state of the art scene specialization methods on several challenging datasets, the results are very promising.
Depuis les annees 2000, un progres significatif est enregistre dans les travaux de recherche qui ... more Depuis les annees 2000, un progres significatif est enregistre dans les travaux de recherche qui proposent l’apprentissage de detecteurs d’objets sur des grandes bases de donnees etiquetees manuellement et disponibles publiquement. Cependant, lorsqu’un detecteur generique d’objets est applique sur des images issues d’une scene specifique les performances de detection diminuent considerablement. Cette diminution peut etre expliquee par les differences entre les echantillons de test et ceux d’apprentissage au niveau des points de vues prises par la(les) camera(s), de la resolution, de l’eclairage et du fond des images.De plus, l’evolution de la capacite de stockage des systemes informatiques, la democratisation de la "video-surveillance" et le developpement d’outils d’analyse automatique des donnees videos encouragent la recherche dans le domaine du trafic routier. Les buts ultimes sont l’evaluation des demandes de gestion du trafic actuelles et futures, le developpement des...
EURASIP Journal on Image and Video Processing, 2016
Transfer learning approaches have shown interesting results by using knowledge from source domain... more Transfer learning approaches have shown interesting results by using knowledge from source domains to learn a specialized classifier/detector for a target domain containing unlabeled data or only a few labeled samples. In this paper, we present a new transductive transfer learning framework based on a sequential Monte Carlo filter to specialize a generic classifier towards a specific scene. The proposed framework utilizes different strategies and approximates iteratively the hidden target distribution as a set of samples in order to learn a specialized classifier. These training samples are selected from both source and target domains according to their weight importance, which indicates that they belong to the target distribution. The resulting classifier is applied to pedestrian and car detection on several challenging traffic scenes. The experiments have demonstrated that our solution improves and outperforms several state of the art's specialization algorithms on public datasets.
Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2016
In this paper, we tackle the problem of domain adaptation to perform object-classification and de... more In this paper, we tackle the problem of domain adaptation to perform object-classification and detection tasks in video surveillance starting by a generic trained detector. Precisely, we put forward a new transductive transfer learning framework based on a sequential Monte Carlo filter to specialize a generic classifier towards a specific scene. The proposed algorithm approximates iteratively the target distribution as a set of samples (selected from both source and target domains) which feed the learning step of a specialized classifier. The output classifier is applied to pedestrian detection into a traffic scene. We have demonstrated by many experiments, on the CUHK Square Dataset and the MIT Traffic Dataset, that the performance of the specialized classifier outperforms the generic classifier and that the suggested algorithm presents encouraging results.
10Th International Multi Conferences on Systems Signals Devices 2013, 2013
This paper presents a solution capable of recognizing the facial expressions performed by a perso... more This paper presents a solution capable of recognizing the facial expressions performed by a person's face and mapping them to a 3D face virtual model and RGB data captured from Microsoft's Kinect solution starts by detecting the face and segmenting its regions, then, it identifies the actual expression using EigenFace metrics on the RGB images and reconstructs the face from the filtered Depth data. A new dataset relative to subjects is introduced for learning purposes. It cont images and point clouds for the different facial expressions performed. The algorithm seeks and displays automatically the seven state of the art expressions including surprise, fear, disgust, anger, joy, sadness and the neutral appearance. As result our system shows a morphing sequence between of 3D face avatar models.
Uploads
Papers by houda Maâmatou