“…As features, they use simply the number of pixels corresponding to the human pose and apply a vector-quantization. Rigoll et al [8] proposed to recognize gestures from low-resolution grey-scale images using continuous HMMs. To compute a 7-dimensional feature vector, they describe the region corresponding to the moving body parts using statistics such as image moments.…”
Section: Related Workmentioning
confidence: 99%
“…In contrast to previous approaches relying on monocular data (e.g., [7], [8], [9]), our system works under realistic settings such as varying and difficult lighting conditions, multiple people, and cluttered background. On a notebook computer, we achieve a frame rate of 20 fps and are able to spot gestures as well as to recognize them, i.e., our system distinguishes between previously learned gestures and irrelevant or unconscious movements.…”
Abstract-Robotic assistants designed to coexist and communicate with humans in the real world should be able to interact with them in an intuitive way. This requires that the robots are able to recognize typical gestures performed by humans such as head shaking/nodding, hand waving, or pointing. In this paper, we present a system that is able to spot and recognize complex, parameterized gestures from monocular image sequences. To represent people, we locate their faces and hands using trained classifiers and track them over time. We use few, expressive features extracted out of this compact representation as input to hidden Markov models (HMMs). First, we segment gestures into distinct phases and train HMMs for each phase separately. Then, we construct composed HMMs, which consist of the individual phase-HMMs. Once a specific phase is recognized, we estimate the parameter of the current gesture, e.g., the target of a pointing gesture. As we demonstrate in the experiments, our method is able to robustly locate and track hands, despite of the fact that they can take a large number of substantially different shapes. Based on this, our system is able to reliably spot and recognize a variety of complex, parameterized gestures.
“…As features, they use simply the number of pixels corresponding to the human pose and apply a vector-quantization. Rigoll et al [8] proposed to recognize gestures from low-resolution grey-scale images using continuous HMMs. To compute a 7-dimensional feature vector, they describe the region corresponding to the moving body parts using statistics such as image moments.…”
Section: Related Workmentioning
confidence: 99%
“…In contrast to previous approaches relying on monocular data (e.g., [7], [8], [9]), our system works under realistic settings such as varying and difficult lighting conditions, multiple people, and cluttered background. On a notebook computer, we achieve a frame rate of 20 fps and are able to spot gestures as well as to recognize them, i.e., our system distinguishes between previously learned gestures and irrelevant or unconscious movements.…”
Abstract-Robotic assistants designed to coexist and communicate with humans in the real world should be able to interact with them in an intuitive way. This requires that the robots are able to recognize typical gestures performed by humans such as head shaking/nodding, hand waving, or pointing. In this paper, we present a system that is able to spot and recognize complex, parameterized gestures from monocular image sequences. To represent people, we locate their faces and hands using trained classifiers and track them over time. We use few, expressive features extracted out of this compact representation as input to hidden Markov models (HMMs). First, we segment gestures into distinct phases and train HMMs for each phase separately. Then, we construct composed HMMs, which consist of the individual phase-HMMs. Once a specific phase is recognized, we estimate the parameter of the current gesture, e.g., the target of a pointing gesture. As we demonstrate in the experiments, our method is able to robustly locate and track hands, despite of the fact that they can take a large number of substantially different shapes. Based on this, our system is able to reliably spot and recognize a variety of complex, parameterized gestures.
“…al. [Rigoll, 1997] used HMMbased approach for real-time gesture recognition. In their work, features are extracted from the differences between two consecutive images and target image is always assumed to be in the center of the input images.…”
“…[9], systems for the graphical recognition of traces left on tablet devices [10] etc. Among several methods for gesture recognition, there are methods based on fuzzy logic and fuzzy sets, methods based on neural networks, hybrid neuro-fuzzy methods [11], fuzzy rule [12] and finite state machine [13] based methods, methods based on hidden Markov models [14] etc. In particular, considering methods for sign language recognition, some literature can be found related to fuzzy methods, such as, for example, fuzzy decision trees [15] and neuro-fuzzy systems [16].…”
Abstract. This paper introduces a fuzzy rule-based method for the recognition of hand gestures acquired from a data glove, with an application to the recognition of some sample hand gestures of LIBRAS, the Brazilian Sign Language. The method uses the set of angles of finger joints for the classification of hand configurations, and classifications of segments of hand gestures for recognizing gestures. The segmentation of gestures is based on the concept of monotonic gesture segment, sequences of hand configurations in which the variations of the angles of the finger joints have the same sign (non-increasing or non-decreasing). Each gesture is characterized by its list of monotonic segments. The set of all lists of segments of a given set of gestures determine a set of finite automata, which are able to recognize every such gesture.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.