Brian P. Clarkson. Recognizing user's context from wearable sensors. Technical Report 519, Vision and Modeling Group, MIT Media Lab, January 2000. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Framing through Peripheral Perception - Clarkson, Pentland (2000) (Correct)
....many types of observable context not just location. We are less interested in obtaining high precision and recall rates than we are in obtaining appropriate model structures for doing higher order tasks like clustering and prediction on a user s day to day activities. Full details are in [6]. A. Experimental Setup A wearable computer was constructed for the purposes of labeling a stream of audio visual features with tags such as Entering Office, or Leaving Kitchen as the wearer went through his day. The features we obtained from a wearable video camera and a wearable microphone are ....
....Setup A wearable computer was constructed for the purposes of labeling a stream of audio visual features with tags such as Entering Office, or Leaving Kitchen as the wearer went through his day. The features we obtained from a wearable video camera and a wearable microphone are listed in [6]. The camera was 1 x 1 x pinhole CCD mounted to the chest strap. The microphone was an omni directional boundary microphone, also mounted to the chest strap. We collected the audio visual features at 1Hz. The features together describe a 24 dimensional feature space in which HMMs were trained ....
[Article contains additional citation context not shown here]
Clarkson, B., K. Mase, and A. Pentland, Recognizing User's Context from Wearable Sensor's: Baseline System. Vismod Technical Report #519, 2000.
Finding Location Using Omnidirectional Video on a.. - Rungsarityotin, Starner (2000) (5 citations) (Correct)
....video trajectories through a laboratory space with 75 accuracy. Clarkson and Pentland [5] use HMM s with both audio and visual features from body mounted cameras and microphones for unspecified classification of locations such as grocery stores and stairways. Continuing this work, Clarkson et al. [4] use ergodic HMM s to detect the entering and leaving of an office, kitchen, and communal areas with approximately 94 accuracy. Unlike these previous systems which identify discrete events, our system will concentrate on identifying continuous paths through an environment. In computer vision, ....
B. Clarkson, K. Mase, and A. Pentland. Recognizing user's context from wearable sensors: Baseline system. Technical Report 519, MIT Media Laboratory, 20Ames St., Cambridge, MA, March 2000.
The Memory Glasses: Towards a Wearable, Context Aware.. - DeVaul, Clarkson.. Self-citation (Clarkson) (Correct)
....the sensor data from camera and microphone, and the label stream from the user or software agents. The goal of the classi er is to extract meaningful features from the sensor data and use these features to detect the events that the user has labeled. The classi er is based on work done by Clarkson [3, 2]. The system overview is as follows: 1. Extract basic features from the sensors at approximately 5Hz. We calculate all spatial moments up to order 2 from the images, 10 equally spaced frequency coecients from 50Hz to 8000Hz from the audio, including measurements of auditory volume and the amount ....
Brian P. Clarkson. Recognizing user's context from wearable sensors. Technical Report 519, Vision and Modeling Group, MIT Media Lab, January 2000.
Exploration of Perceptual Computing for Smart-Its - Antifakos (2001) (Correct)
No context found.
B. Clarkson, K. Mase, and A. Pentland. Recognizing user's context from wearable sensors: Baseline system. Technical Report 519, MIT Media Laboratory, March 2000.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC