Patent
Gesture detection and recognition
Sebastian Nowozin,Pushmeet Kohli,Jamie Shotton +2 more
- 04 Mar 2011
108
TL;DR: A gesture detection and recognition technique is described in this article, in which a sequence of data items relating to the motion of a gesturing user is received, and a selected set of items from the sequence are tested against pre-learned threshold values, to determine a probability of the sequence representing a certain gesture.
read more
Abstract: A gesture detection and recognition technique is described. In one example, a sequence of data items relating to the motion of a gesturing user is received. A selected set of data items from the sequence are tested against pre-learned threshold values, to determine a probability of the sequence representing a certain gesture. If the probability is greater than a predetermined value, then the gesture is detected, and an action taken. In examples, the tests are performed by a trained decision tree classifier. In another example, the sequence of data items can be compared to pre-learned templates, and the similarity between them determined. If the similarity for a template exceeds a threshold, a likelihood value associated with a future time for a gesture associated with that template is updated. Then, when the future time is reached, the gesture is detected if the likelihood value is greater than a predefined value.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Patent
Telemetry system with tracking receiver devices
James Proud
- 14 Aug 2013
TL;DR: In this article, a wireless power transmission system includes, a transmit antenna which in operation produces a wireless field, an amplifier coupled to the transmit antenna, a load sensing circuit coupled with the amplifier, and a controller coupled with an ID circuitry.
191
Patent
Trajectory detection and feedback system for tennis
Alan W. Marty,Thomas A. Edwards +1 more
- 18 Jan 2013
TL;DR: In this paper, a system for capturing and analyzing a trajectory of a tennis ball or other object associated with a play of a game of tennis and providing feedback is described, which may be configured to provide immediate feedback that may be utilized by a player to improve their performance as well as provide entertainment value above and beyond what is normally associated with the play of tennis.
154
Patent
Gaming device with rotatably placed cameras
Jeffrey Roger Stafford,Todd Tokubo +1 more
- 10 Mar 2015
TL;DR: In this paper, a method to identify positions of fingers of a hand is described, which includes capturing images of a first hand using a plurality of cameras that are part of a wearable device and sending the stream of captured image data to a computing device that is interfaced with the HMD.
98
Patent
System using wearable device with unique user ID and telemetry system
James Proud
- 21 Jun 2013
TL;DR: In this paper, a system for using telemetry data based on a user habit information includes one or more sensors coupled to a wearable device that has a unique user ID, and acquires user information selected from of at least one of, a user's activities, behaviors and habit information.
91
Patent
Telemetry system with wireless power receiver and monitoring devices
James Proud
- 01 Aug 2013
TL;DR: In this paper, a wireless power receiver includes a rectifier coupled to an antenna which is configured to receive a wireless signal and convert the wireless power signal to a direct current input signal.
90
References
Learning realistic human actions from movies
Ivan Laptev,Marcin Marszalek,Cordelia Schmid,B. Rozenfeld +3 more
- 23 Jun 2008
TL;DR: A new method for video classification that builds upon and extends several recent ideas including local space-time features,space-time pyramids and multi-channel non-linear SVMs is presented and shown to improve state-of-the-art results on the standard KTH action dataset.
Coupled hidden Markov models for complex action recognition
Matthew Brand,Nuria Oliver,Alex Pentland +2 more
- 17 Jun 1997
TL;DR: Algorithms for coupling and training hidden Markov models (HMMs) to model interacting processes, and demonstrate their superiority to conventional HMMs in a vision task classifying two-handed actions are presented.
1.2K
Real-time American Sign Language recognition from video using hidden Markov models
Thad Starner,Alex Pentland +1 more
- 21 Nov 1995
TL;DR: A real-time HMM-based system for recognizing sentence level American Sign Language (ASL) which attains a word accuracy of 99.2% without explicitly modeling the fingers.
Conditional models for contextual human motion recognition
TL;DR: Algorithms for recognizing human motion in monocular video sequences, based on discriminative conditional random field (CRF) and maximum entropy Markov models (MEMM) are presented, which outperform HMMs in classifying not only diverse human activities like walking, jumping.
384
Patent
Methods and apparatus for targeted sound detection and characterization
Xiadong Mao,Richard Marks,Gary M. Zalewski +2 more
- 04 May 2006
TL;DR: In this paper, a sound capture unit is configured to identify one or more sound sources and generate data capable of being analyzed to determine a listening zone at which to process sound to the substantial exclusion of sounds outside the listening zone.
352