Computer Vision System for the Blind Veteran

Blindness Clinical Trial

Official title:

Computer Vision System for the Blind Veteran

Clinical Trial Details — Status: Completed

Administrative data

• NCT number: NCT00920231
• Other study ID #: C6731-R
• Status: Completed
• Phase: Phase 1
• First received: June 11, 2009
• Last updated: December 18, 2015
• Start date: November 2011
• Est. completion date: September 2015

Study information

• Verified date: December 2015
• Source: VA Office of Research and Development
• Contact: n/a
• Is FDA regulated: No
• Health authority: United States: Federal Government
• Study type: Interventional

Clinical Trial Summary

This is a feasibility study involving a small number of blind subject to evaluate the effectiveness of using a software and associated hardware components to assist the blind in identifying and locating objects of interests and to assist in way finding tasks. After the system has been successfully tested by the blindfolded engineers, it will be evaluated in a small number of blind subjects.

Description:

This is primarily an engineering project to develop computer vision algorithms for an integrated system comprising of a laptop computer, webcam, gps, digital compass, microphone, and stereo earphones. The system will be voice controlled. The algorithm will be trained to identify and located objects and navigationally landmarks in real-time, previously selected by sighted developers. After the system has passed objective engineering milestones, blind subjects will be tested to determine whether the novel system will improve the ability of the blind to travel over a test course in a hospital setting.

Recruitment information / eligibility

• Status: Completed
• Enrollment: 16
• Est. completion date: September 2015
• Est. primary completion date: December 2013
• Accepts healthy volunteers: No
• Gender: Both
• Age group: 18 Years to 80 Years

Eligibility

Inclusion Criteria:

• age 18 and over

• legally blind

Exclusion Criteria:

• decreased hearing

• unable to understand or follow instructions

• inability to walk and stand for 10 minutes

Study Design

Allocation: Non-Randomized, Endpoint Classification: Efficacy Study, Intervention Model: Parallel Assignment, Masking: Open Label, Primary Purpose: Supportive Care

Related Conditions & MeSH terms

• Blindness

Intervention

Device:
• initial system
The computer vision system is used to assist blind subject to navigate an extended path with multiple turns within a hospital setting.The initial prototype system would have been successfully tested for outdoor navigation and basic object recognition tasks.
• modified system
The problems associated with the initial system were identified and modified. This modified system was tested with a second separate group of subjects. The redesigned system is used to assist blind subject to navigate the same extended path with multiple turns within a hospital setting.

Locations

Country	Name	City	State
United States	Baltimore VA Medical Center VA Maryland Health Care System, Baltimore, MD	Baltimore	Maryland
United States	Atlanta VA Medical and Rehab Center, Decatur	Decatur	Georgia

Sponsors (1)

Lead Sponsor	Collaborator
VA Office of Research and Development

Country where clinical trial is conducted

United States, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Frequency of Device Failures Per Attempt to Complete a Navigation Course	device failures were defined as any failure to provide correct location and direction information at thre appropriate time, resulting in a mistake that needed the initial prototype's ability to meet their travel needs at a good to excellent range.	The subject is given as much time as needed to complete the task	No
Secondary	Ability to Meet the Subjective Travel Needs of the Blind Subject	This is a subjective rating that incorporates user friendliness of the system and the specific needs of the subject. The subject is asked to rate whether the device meets his or her travel needs on a 1 to 7 scale with 1 being excellent and 7 being very poor.	no time limit	No