DOC PREVIEW
Stanford HPS 154 - The Camera Mouse Visual Tracking of Body Features

This preview shows page 1-2-3-24-25-26 out of 26 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 26 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 26 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 26 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 26 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 26 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 26 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 26 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

Resubmitted to the IEEE Transactions on Rehabilitation Engineering, June 19, 2001The Camera Mouse: Visual Tracking of Body Features to ProvideComputer Access For People with Severe DisabilitiesMargrit Betke∗James Gips and Peter FlemingComputer Science Department Computer Science DepartmentBoston University Boston College111 Cummington St 140 Commonwealth AveBoston, MA 02215 Chestnut Hill, MA 02467-3808AbstractThe “Camera Mouse” system has been developed to provide computer access for people with severe disabilities.The system tracks the computer user’s movements with a video camera and translates them into the movementsof the mouse pointer on the screen. Body features such as the tip of the user’s nose or finger can be tracked. Thevisual tracking algorithm is based on cropping an online template of the tracked feature from the current imageframe and testing where this template correlates in the subsequent frame. The location of the highest correlationis interpreted as the new location of the feature in the subsequent frame. Various body features are examined fortracking robustness and user convenience. A group of 20 people without disabilities tested the Camera Mouseand quickly learned how to use it to spell out messages or play games. Twelve people with severe cerebral palsyor traumatic brain injury have tried the system, nine of whom have shown success. They interacted with theirenvironment by spelling out messages and exploring the internet.∗Email: [email protected], http://www.cs.bu.edu/faculty/betke. The work was supported by the NSF equipment grant 9871219while the first author was at Boston College.11 IntroductionPeople who are quadriplegic and nonverbal, for example from cerebral palsy, traumatic brain injury, or stroke,often have great difficulties communicating their desires, thoughts, and needs. They use their limited voluntarymotions to communicate with family, friends, and other care providers. Some people can move their heads.Some can blink or wink voluntarily. Some can move their eyes or tongue. Assistive technology devices havebeen developed to help them use their voluntary movements to control computers. People with disabilitiescan then communicate through spelling or expression-building programs. This allows users to exhibit theirthoughts, emotions, and intellectual potential. Along with the increased ability to communicate, users withsevere disabilities can benefit from computer access in many other ways. They can acquire knowledge moreactively, partake in increased recreational activities, use the internet, and access computer-controlled technologiessuch as automated wheelchairs.Switch-based systems. Assistive technology systems that use switches to control a computer have been usedfor a considerable period and are still popular [22]. For entering text and other data into a computer, hitting theswitch initiates a scan through a matrix of letters, symbols, words, or phrases. Each matrix entry can be selectedwith a sequence of switch operations. Current research in this area focuses on dynamically adapting matrix rowand column scan delays in order to increase the individual user’s text entry rate without complicating the visualdisplay [27]. This is an important issue, since the inability to communicate at an effective rate is a serious barrierfor people with disabilities [28].Infrared systems. People with severe disabilities who retained the ability to rotate their heads have otherassistive technology options. For example, there are various commercial mouse alternatives. Some systems useinfrared emitters that are attached to the user’s glasses, head band, or cap, e.g., [17]. Other systems place thetransmitter over the monitor and use an infrared reflector that is attached to the user’s forehead or glasses,e.g., [2]. The user’s head movements control the mouse cursor on the screen. Mouse clicks are generated with aphysical switch or a software interface. Evans et al. recently described a head-mounted infrared-emitting controlsystem that is a “relative” pointing device and acts like a joystick rather than a mouse [8]. Chen et al. developed2a system that contains an infrared transmitter, mounted onto the user’s eyeglasses, a set of infrared receivingmodules that substitute the keys of a computer keyboard, and a tongue-touch panel to activate the infraredbeam [6]. Helmets, electrodes, goggles, and mouthsticks are uncomfortable to wear or use. Commercial head-mounted devices can often not be adjusted to fit a child’s head. Most importantly, some users, in particularyoung children, dislike to be touched on their face and vehemently object to any devices attached to their heads.A non-contact, infrared-based system that tracks the reflected laser speckle pattern of skin is proposed by Reillyand O’Malley [25].Corneal reflection systems. Other commercial systems that allow people with severe disabilities access toa computer are based on measuring corneal reflections [23, 9, 10]. Such systems determine gaze direction bycomparing the pupil position in an image of a user’s eye with the light pattern that occurs when incident lightis reflected from the convex surface of the cornea [29, 16, 26]. Corneal reflection systems have the disadvantagesthat they need careful calibration, require the user to keep his or her head almost completely still, and are notinexpensive. For example, the Permobil Eye Tracker [23], which uses goggles containing infrared light emittersand diodes for eye-movement detection, costs between $9,900 and $22,460. Recent research advances promiseless expensive gaze-tracking solutions [21]. Users with severe disabilities are often not able to keep their headsstill enough to use commercial gaze trackers reliably. Chin rests are then used, but they are uncomfortable. Inaddition, any interruption requires recalibration. The calibration process is too difficult to understand for veryyoung children.EOG-based systems. Other control devices measure the electro-oculographic potential (EOG) to detect eyemovements [29, 20, 7] or analyze features in electroencephalograms (EEG) [19, 24]. Gips et al. [7, 14] havedesigned “EagleEyes,” an EOG-based system that enables people who can move their eyes to control the mouse.Electrodes are attached on the user’s face to measure changes in EOG that occur when the position of the eyerelative to the head changes. Amplified voltages are translated into the position of the cursor on the screen.


View Full Document

Stanford HPS 154 - The Camera Mouse Visual Tracking of Body Features

Download The Camera Mouse Visual Tracking of Body Features
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view The Camera Mouse Visual Tracking of Body Features and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view The Camera Mouse Visual Tracking of Body Features 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?