The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper tackles the risk estimation problem from a new perspective: a framework is proposed for reasoning about traffic situations and collision risk at a semantic level, while classic approaches typically reason at a trajectory level. Risk is assessed by estimating the intentions of drivers and detecting conflicts between them, rather than by predicting the future trajectories of the vehicles...
In this paper, we propose a novel feature extraction scheme for fingertip writing recognition in the air for egocentric viewpoint. The inherent challenges in the egocentric vision e.g. rapid camera motion and object's appearance and disappearance in scene may cause the fingertip to be detected in non-uniformly time separated frames. Most existing approaches do not consider this missing temporal information...
This paper describes an approach to predict the human motion. Instead of using a simple motion model as widely used, we take advantages of the environmental context, including the shape and structure, for predicting the human movement. First, we characterize the environment using a graph representation. Subsequently, we acquire the human trajectory tendency on each environment and build a probabilistic...
In this paper, we propose a unified approach to teach and iteratively refine both end-effector and null-space movements. Hence, the robot can be taught to make use of all its degrees-of-freedom (DoF) to adapt its behavior to new dynamic scenarios. In order to achieve this goal we propose an incremental learning approach in a framework of kinesthetic teaching based on a multi-priority kinematic controller,...
Recent efforts in the field of intervention-autonomous underwater vehicles (I-AUVs) have started to show promising results in simple manipulation tasks. However, there is still a long way to go to reach the complexity of the tasks carried out by ROV pilots. This paper proposes an intervention framework based on parametric Learning by Demonstration (p-LbD) techniques in order to acquire multiple strategies...
We are looking to perform anomaly detection in video streams, within the fastest time possible, and without the need to hand-engineer features to suit for particular scenes. In any scene captured by surveillance camera, there could be single or multiple persons (agents) and activities ongoing concurrently, with or without human-object and/or human-human interactions. These characteristics lead to...
We propose a methodology for learning and using a multiple-goal probabilistic motion model within a particle filter-based target tracking on video streams. In a set of training video sequences, we first extract the locations (coined as “goals”) where the pedestrians either leave the scene or often change directions. Then, we learn one motion prior model per detected goal. Each of these models is learned...
Robots that interact with humans must learn to not only adapt to different human partners but also to new interactions. Such a form of learning can be achieved by demonstrations and imitation. A recently introduced method to learn interactions from demonstrations is the framework of Interaction Primitives. While this framework is limited to represent and generalize a single interaction pattern, in...
To enable safe and efficient human-robot collaboration in shared workspaces, it is important for the robot to predict how a human will move when performing a task. While predicting human motion for tasks not known a priori is very challenging, we argue that single-arm reaching motions for known tasks in collaborative settings (which are especially relevant for manufacturing) are indeed predictable...
Target motion analysis (TMA) for a rectilinear source movement (RSM) has been intensively studied in the last ten years. But difficulties still exist, especially when source heading or speed changes are within the same time as the conventional TMA convergence time. This paper is concerned with a new method of batch TMA for maneuvering sources using a non-linear least-squares fit between the whole...
Monitoring the dynamical behavior of receptors and lig-ands via single-molecule fluorescence microscopy allows quantifying the interactions between these two subcellular structures at a very high spatial and temporal resolution. We have developed a probabilistic approach to determine the positions of receptors and ligands over time in two-channel image sequences of small protein complexes and single...
To solve the acoustic-to-articulatory inversion problem, this paper proposes a deep bidirectional long short term memory recurrent neural network and a deep recurrent mixture density network. The articulatory parameters of the current frame may have correlations with the acoustic features many frames before or after. The traditional pre-designed fixed-length context window may be either insufficient...
In this paper we propose synchronization rules between acoustic and visual laughter synthesis systems. This work follows up our previous studies on acoustics laughter synthesis and visual laughter synthesis. The need of synchronization rules comes from the constraint that in laughter, HMM-based synthesis of laughter cannot be performed using a unified system where common transcriptions may be used...
Classification of moving objects for video surveillance applications still remains a challenging problem due to the video inherently changing conditions such as lighting or resolution. This paper proposes a new approach for vehicle/pedestrian object classification based on the learning of a static kNN classifier, a dynamic Hidden Markov Model (HMM)-based classifier, and the definition of a fusion...
This paper proposes a novel parameter generation algorithm for high-quality speech generation in Hidden Markov Model (HMM)-based speech synthesis. One of the biggest issues causing significant quality degradation is the over-smoothing effect often observed in generated parameter trajectories. Global Variance (GV) is known as a feature well correlated with the over-smoothing effect and a metric on...
This paper presents a new approach to cross-lingual voice transformation in HMM-based TTS with only the recordings from two monolingual speakers in different languages (e.g. Mandarin and English). We aim to synthesize one speaker's speech in the other language. We regard the spectral space of any speaker to be composed of universal elementary units (i.e. tied-states) of speech in different languages...
Particle filtering - perhaps more properly named Sequential Monte Carlo - approaches have a strong potential for signal and image processing applications. A problem of great practical significance in this field, which remains largely unsolved as of today, is the estimation of fixed model parameters based on the output of sequential simulations. In this contribution, we investigate maximum likelihood...
In this paper, we present a Sign Language Tutoring Demonstrator, which is capable of teaching the basics of the sign language interactively. Instead of a passive learner, by incorporating a simple sign language recognizer to the system, the learner would be able to practice the signs and have feedbacks according to the similarity of the performed gesture to the actual gesture model.
In this paper, we present an approach for automatic clustering of multi-dimensional dynamic trajectories corresponding to speech data that is based on Trajectory Clustering (TC). TC uses the Expectation Maximization algorithm (EM) for clustering with the mixtures of Multiple Linear Regression model. Since the initial values of the model parameters are critical to the clustering performance, a successive...
This paper presents a framework to recognize the symbols drawn in air using bare hand motion. The work marks a step towards development of non-tactile interfaces requiring no physical means for writing or drawing. To overcome the limitations of traditional two dimensional camera based acquisition, a preliminary step in gesture recognition, depth based sensor is used to acquire trajectory signals....
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.