The Experts below are selected from a list of 88815 Experts worldwide ranked by ideXlab platform
T R Elmaraghi - One of the best experts on this subject based on the ideXlab platform.
-
robust online appearance models for visual tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003Co-Authors: Allan D Jepson, David J Fleet, T R ElmaraghiAbstract:We propose a framework for learning robust, adaptive, appearance models to be used for motion-based tracking of natural objects. The model adapts to slowly changing appearance, and it maintains a natural measure of the stability of the observed image structure during tracking. By identifying stable properties of appearance, we can weight them more heavily for motion estimation, while less stable properties can be proportionately downweighted. The appearance model involves a mixture of stable image structure, learned over long time courses, along with two-frame motion information and an outlier process. An online EM-algorithm is used to adapt the appearance model parameters over time. An implementation of this approach is developed for an appearance model based on the filter responses from a steerable pyramid. This model is used in a motion-based tracking algorithm to Provide Robustness in the face of image outliers, such as those caused by occlusions, while adapting to natural changes in appearance such as those due to facial expressions or variations in 3D pose.
-
robust online appearance models for visual tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003Co-Authors: Allan D Jepson, David J Fleet, T R ElmaraghiAbstract:We propose a framework for learning robust, adaptive, appearance models to be used for motion-based tracking of natural objects. The model adapts to slowly changing appearance, and it maintains a natural measure of the stability of the observed image structure during tracking. By identifying stable properties of appearance, we can weight them more heavily for motion estimation, while less stable properties can be proportionately downweighted. The appearance model involves a mixture of stable image structure, learned over long time courses, along with two-frame motion information and an outlier process. An online EM-algorithm is used to adapt the appearance model parameters over time. An implementation of this approach is developed for an appearance model based on the filter responses from a steerable pyramid. This model is used in a motion-based tracking algorithm to Provide Robustness in the face of image outliers, such as those caused by occlusions, while adapting to natural changes in appearance such as those due to facial expressions or variations in 3D pose.
-
robust online appearance models for visual tracking
Computer Vision and Pattern Recognition, 2001Co-Authors: Allan D Jepson, David J Fleet, T R ElmaraghiAbstract:We propose a framework for learning robust, adaptive appearance models to be used for motion-based tracking of natural objects. The approach involves a mixture of stable image structure, learned over long time courses, along with 2-frame motion information and an outlier process. An online EM-algorithm is used to adapt the appearance model parameters over time. An implementation of this approach is developed for an appearance model based on the filter responses from a steerable pyramid. This model is used in a motion-based tracking algorithm to Provide Robustness in the face of image outliers, such as those caused by occlusions. It also Provides the ability to adapt to natural changes in appearance, such as those due to facial expressions or variations in 3D pose. We show experimental results on a variety of natural image sequences of people moving within cluttered environments.
Ricardo J. Mantz - One of the best experts on this subject based on the ideXlab platform.
-
Harmonic series compensators in power systems: their control via sliding mode
IEEE Transactions on Control Systems and Technology, 2000Co-Authors: H. De Battista, Ricardo J. MantzAbstract:This paper deals with harmonic current compensation in power systems using shunt passive and series active filters. It is shown how constraints of the active filters can notoriously degrade the performance of the compensating system. The use of variable structure system theory is suggested for analysis and design of series active filters. Sliding mode control strategies to improve harmonic rejection are proposed, and active filters with different switching-ripple filters are considered. These control strategies Provide Robustness to active filter modeling errors and external disturbances.
Anindya Dutta - One of the best experts on this subject based on the ideXlab platform.
-
MicroRNAs Regulate and Provide Robustness to the Myogenic Transcriptional Network
Current opinion in pharmacology, 2012Co-Authors: Jeffrey Gagan, Bijan K. Dey, Anindya DuttaAbstract:The genetics of skeletal muscle lineage commitment are deceptively complicated. MyoD overexpression is sufficient to convert fibroblasts into skeletal muscle myotubes. In vivo, there are a number of different steps of differentiation that require a large network of transcription factors that control differentiation and homeostasis of skeletal muscle progenitors. Each transcription factor has been shown to have the ability to promote the next factor in the cascade, but the mechanisms regulating the transitions remain incomplete. Recently, microRNAs have been shown to be important for a large number of developmental and oncogenic processes. In this review, we will discuss recent advances in the understanding of how microRNA is critical for skeletal muscle development by interacting with protein-coding genes that had previously been shown to be important for myogenesis.
Allan D Jepson - One of the best experts on this subject based on the ideXlab platform.
-
robust online appearance models for visual tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003Co-Authors: Allan D Jepson, David J Fleet, T R ElmaraghiAbstract:We propose a framework for learning robust, adaptive, appearance models to be used for motion-based tracking of natural objects. The model adapts to slowly changing appearance, and it maintains a natural measure of the stability of the observed image structure during tracking. By identifying stable properties of appearance, we can weight them more heavily for motion estimation, while less stable properties can be proportionately downweighted. The appearance model involves a mixture of stable image structure, learned over long time courses, along with two-frame motion information and an outlier process. An online EM-algorithm is used to adapt the appearance model parameters over time. An implementation of this approach is developed for an appearance model based on the filter responses from a steerable pyramid. This model is used in a motion-based tracking algorithm to Provide Robustness in the face of image outliers, such as those caused by occlusions, while adapting to natural changes in appearance such as those due to facial expressions or variations in 3D pose.
-
robust online appearance models for visual tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003Co-Authors: Allan D Jepson, David J Fleet, T R ElmaraghiAbstract:We propose a framework for learning robust, adaptive, appearance models to be used for motion-based tracking of natural objects. The model adapts to slowly changing appearance, and it maintains a natural measure of the stability of the observed image structure during tracking. By identifying stable properties of appearance, we can weight them more heavily for motion estimation, while less stable properties can be proportionately downweighted. The appearance model involves a mixture of stable image structure, learned over long time courses, along with two-frame motion information and an outlier process. An online EM-algorithm is used to adapt the appearance model parameters over time. An implementation of this approach is developed for an appearance model based on the filter responses from a steerable pyramid. This model is used in a motion-based tracking algorithm to Provide Robustness in the face of image outliers, such as those caused by occlusions, while adapting to natural changes in appearance such as those due to facial expressions or variations in 3D pose.
-
robust online appearance models for visual tracking
Computer Vision and Pattern Recognition, 2001Co-Authors: Allan D Jepson, David J Fleet, T R ElmaraghiAbstract:We propose a framework for learning robust, adaptive appearance models to be used for motion-based tracking of natural objects. The approach involves a mixture of stable image structure, learned over long time courses, along with 2-frame motion information and an outlier process. An online EM-algorithm is used to adapt the appearance model parameters over time. An implementation of this approach is developed for an appearance model based on the filter responses from a steerable pyramid. This model is used in a motion-based tracking algorithm to Provide Robustness in the face of image outliers, such as those caused by occlusions. It also Provides the ability to adapt to natural changes in appearance, such as those due to facial expressions or variations in 3D pose. We show experimental results on a variety of natural image sequences of people moving within cluttered environments.
Krishna C Mohan - One of the best experts on this subject based on the ideXlab platform.
-
graph formulation of video activities for abnormal activity recognition
Pattern Recognition, 2017Co-Authors: Dinesh Singh, Krishna C MohanAbstract:Abnormal activity recognition is a challenging task in surveillance videos. In this paper, we propose an approach for abnormal activity recognition based on graph formulation of video activities and graph kernel support vector machine. The interaction of the entities in a video is formulated as a graph of geometric relations among space-time interest points. The vertices of the graph are spatio-temporal interest points and an edge represents the relation between appearance and dynamics around the interest points. Once the activity is represented using a graph, then for classification of the activities into normal or abnormal classes, we use binary support vector machine with graph kernel. These graph kernels Provide Robustness to slight topological deformations in comparing two graphs, which may occur due to the presence of noise in data. We demonstrate the efficacy of the proposed method on the publicly available standard datasets viz. UCSDped1, UCSDped2 and UMN. Our experiments demonstrate high rate of recognition and outperform the state-of-the-art algorithms. HighlightsAbnormal activity recognition in surveillance videos.Graph representation of video activity to incorporate geometric structures along with motion and appearance information.Classification of activity graphs using graph kernel SVM in order to detect local abnormal activities.Global abnormal activity recognition using bag-of-graphs (BoG).
