Indoor navigation system for blind

ScienceDaily (May 18, 2012) — University of Nevada, Reno computer science engineering team Kostas Bekris and Eelke Folmer presented their indoor navigation system for people with visual impairments at two national conferences in the past two weeks. The researchers explained how a combination of human-computer interaction and motion-planning research was used to build a low-cost accessible navigation system, called Navatar, which can run on a standard smartphone.

"Existing indoor navigation systems typically require the use of expensive and heavy sensors, or equipping rooms and hallways with radio-frequency tags that can be detected by a handheld reader and which are used to determine the user's location," Bekris, of the College of Engineering's Robotics Research Lab, said. "This has often made the implementation of such systems prohibitively expensive, with few systems having been deployed."

Instead, the University of Nevada, Reno navigation system uses digital 2D architectural maps that are already available for many buildings, and uses low-cost sensors, such as accelerometers and compasses, that are available in most smartphones, to navigate users with visual impairments. The system locates and tracks the user inside the building, finding the most suitable path based on the users special needs, and gives step-by-step instructions to the destination.

"Nevertheless, the smartphone's sensors, which are used to calculate how many steps the user has executed and her orientation, tend to pick up false signals," Folmer, who has developed exercise video games for the blind, said. "To synchronize the location, our system combines probabilistic algorithms and the natural capabilities of people with visual impairments to detect landmarks in their environment through touch, such as corridor intersections, doors, stairs and elevators."

Folmer explained that as touch screen devices are challenging to use for users with visual impairments, directions are provided using synthetic speech and users confirm the presence of a landmark by verbal confirmation or by pressing a button on the phone or on a Bluetooth headset. A benefit of this approach is that the user can leave the phone in their pocket leaving both hands free for using a cane and recognizing tactile landmarks.

"This is a very cool mix of disciplines, using the user as a sensor combined with sophisticated localization algorithms from the field of robotics," Folmer, of the University's Computer Science Engineering Human-Computer Interaction Lab, said.

The team is currently trying to implement their navigation system in other environments and integrate it into outdoor navigation systems that use GPS.

"My research is motivated by the belief that a disability can be turned into an innovation driver," Folmer said. "When we try to solve interaction design problems for the most extreme users, such as users with visual impairments, there is the potential to discover solutions that may benefit anyone. Though the navigation system was specifically developed for users with visual impairments, it can be used by sighted users as well."

For their work on the indoor navigation system for the blind, Bekris and Folmer recently won a PETA Proggy Award for Leadership in Ethical Science. PETA's Proggy Awards ("Proggy" is for "progress") recognize animal-friendly achievements. The navigation system was deemed such an achievement because it could decrease the need to rely on guide dogs.

They presented and demonstrated their research at the IEEE International Conference on Robotics and Automation in St. Paul., Minn. on May 15 and on May 7 at the CM SIGCHI Conference on Human Factors in Computing Systems, which is the premier international conference on human-computer interaction.

Share this story on Facebook, Twitter, and Google:

Other social bookmarking and sharing tools:

Story Source:

The above story is reprinted from materials provided by University of Nevada, Reno.

Note: Materials may be edited for content and length. For further information, please contact the source cited above.

Note: If no author is given, the source is cited instead.

Disclaimer: This article is not intended to provide medical advice, diagnosis or treatment. Views expressed here do not necessarily reflect those of ScienceDaily or its staff.

View the original article here

Sound rather than sight can activate 'seeing' for the blind, say researchers

ScienceDaily (Feb. 8, 2012) — Scientists at the Hebrew University of Jerusalem have tapped onto the visual cortex of the congenitally blind by using sensory substitution devices (SSDs), enabling the blind in effect to "see" and even describe objects.

SSDs are non-invasive sensory aids that provide visual information to the blind via their existing senses. For example, using a visual-to-auditory SSD in a clinical or everyday setting, users wear a miniature video camera connected to a small computer (or smart phone) and stereo headphones.

The images are converted into "soundscapes," using a predictable algorithm, allowing the user to listen to and then interpret the visual information coming from the camera.

Remarkably, proficient users who have had a dedicated (but relatively brief) training as part of a research protocol in he laboratory of Dr. Amir Amedi, of the Edmond and Lily Safra Center for Brain Sciences and the Institute for Medical Research Israel-Canada at the Hebrew University, are able to use SSDs to identify complex everyday objects, locate people and their postures, and read letters and words.

In addition to SSDs' clinical opportunities, using functional magnetic resonance imaging opens a unique window for studying the organization of the visual cortex without visual experience by studying the brain of congenitally blind individuals.

The results of the study in Amedi's lab, recently published in the journal Cerebral Cortex, are surprising. Not only can the sounds, which represent vision, activate the visual cortex of people who have never seen before, but they do so in a way organized according to the large-scale organization and segregation of the two visual processing streams.

For the past three decades, it has been known that visual processing is carried out in two parallel pathways. The ventral occipito-temporal "what" pathway, or the "ventral stream," has been linked with visual processing of form, object identity and color. Its counterpart is considered to be the dorsal occipito-parietal "where/how" pathway, or the "dorsal stream," which analyzes visuo-spatial information about object location and participates in visuo-motor planning.

Although this double dissociation between the processing of the two streams has been thoroughly validated, what remained unclear was the role of visual experience in shaping this functional architecture of the brain. Does this fundamental large-scale organizational principle depend on visual experience?

Using sensory substitution, the Hebrew University scientists, led by Ph.D. student Ella Striem-Amit and Dr. Amedi, discovered that the visual cortex of the blind shows a similar dorsal/ventral visual pathway division-of-labor when perceiving sounds that convey the relevant visual information; e.g., when the blind are requested to identify either the location or the shape of an SSD "image," they activate an area in the dorsal or in the ventral streams, respectively.

This shows that the most important large-scale organization of the visual system into the two streams can develop at least to some extent even without any visual experience, suggesting instead that this division-of-labor is not at all visual in its nature.

Recent research from Amedi's lab and from other research groups have demonstrated that multiple brain areas are not specific to their input sense (vision, audition or touch), but rather to the task or computation they perform, which may be computed with various modalities.

Extending these finding to a large-scale division-of-labor of the visual system further contributes crucial information towards postulating that the whole brain may be task-specific rather than dependent on a specific sensory input. "The brain is not a sensory machine, although it often looks like one; it is a task machine," summed up Amedi.

These findings suggest that the blind brain can potentially be "awakened" to processing visual properties and tasks, even after lifelong blindness, with the aid of visual rehabilitation, using future medical advances, such as retinal prostheses, say the researchers. A summary of these ideas were published recently in a review in Current Opinion in Neurology by Lior Reich and Shachar Maidenbaum from Amedi's lab.

Share this story on Facebook, Twitter, and Google:

Other social bookmarking and sharing tools:

Story Source:

The above story is reprinted from materials provided by Hebrew University of Jerusalem, via AlphaGalileo.

Note: Materials may be edited for content and length. For further information, please contact the source cited above.

Journal Reference:

E. Striem-Amit, O. Dakwar, L. Reich, A. Amedi. The large-Scale Organization of 'Visual' Streams Emerges Without Visual Experience. Cerebral Cortex, 2011; DOI: 10.1093/cercor/bhr253

Note: If no author is given, the source is cited instead.

Disclaimer: This article is not intended to provide medical advice, diagnosis or treatment. Views expressed here do not necessarily reflect those of ScienceDaily or its staff.

View the original article here

Indoor navigation system for blind

ScienceDaily (May 18, 2012) — University of Nevada, Reno computer science engineering team Kostas Bekris and Eelke Folmer presented their indoor navigation system for people with visual impairments at two national conferences in the past two weeks. The researchers explained how a combination of human-computer interaction and motion-planning research was used to build a low-cost accessible navigation system, called Navatar, which can run on a standard smartphone.

"Existing indoor navigation systems typically require the use of expensive and heavy sensors, or equipping rooms and hallways with radio-frequency tags that can be detected by a handheld reader and which are used to determine the user's location," Bekris, of the College of Engineering's Robotics Research Lab, said. "This has often made the implementation of such systems prohibitively expensive, with few systems having been deployed."

Instead, the University of Nevada, Reno navigation system uses digital 2D architectural maps that are already available for many buildings, and uses low-cost sensors, such as accelerometers and compasses, that are available in most smartphones, to navigate users with visual impairments. The system locates and tracks the user inside the building, finding the most suitable path based on the users special needs, and gives step-by-step instructions to the destination.

"Nevertheless, the smartphone's sensors, which are used to calculate how many steps the user has executed and her orientation, tend to pick up false signals," Folmer, who has developed exercise video games for the blind, said. "To synchronize the location, our system combines probabilistic algorithms and the natural capabilities of people with visual impairments to detect landmarks in their environment through touch, such as corridor intersections, doors, stairs and elevators."

Folmer explained that as touch screen devices are challenging to use for users with visual impairments, directions are provided using synthetic speech and users confirm the presence of a landmark by verbal confirmation or by pressing a button on the phone or on a Bluetooth headset. A benefit of this approach is that the user can leave the phone in their pocket leaving both hands free for using a cane and recognizing tactile landmarks.

"This is a very cool mix of disciplines, using the user as a sensor combined with sophisticated localization algorithms from the field of robotics," Folmer, of the University's Computer Science Engineering Human-Computer Interaction Lab, said.

The team is currently trying to implement their navigation system in other environments and integrate it into outdoor navigation systems that use GPS.

"My research is motivated by the belief that a disability can be turned into an innovation driver," Folmer said. "When we try to solve interaction design problems for the most extreme users, such as users with visual impairments, there is the potential to discover solutions that may benefit anyone. Though the navigation system was specifically developed for users with visual impairments, it can be used by sighted users as well."

For their work on the indoor navigation system for the blind, Bekris and Folmer recently won a PETA Proggy Award for Leadership in Ethical Science. PETA's Proggy Awards ("Proggy" is for "progress") recognize animal-friendly achievements. The navigation system was deemed such an achievement because it could decrease the need to rely on guide dogs.

They presented and demonstrated their research at the IEEE International Conference on Robotics and Automation in St. Paul., Minn. on May 15 and on May 7 at the CM SIGCHI Conference on Human Factors in Computing Systems, which is the premier international conference on human-computer interaction.

Share this story on Facebook, Twitter, and Google:

Other social bookmarking and sharing tools:

Story Source:

The above story is reprinted from materials provided by University of Nevada, Reno.

Note: Materials may be edited for content and length. For further information, please contact the source cited above.

Note: If no author is given, the source is cited instead.

Disclaimer: This article is not intended to provide medical advice, diagnosis or treatment. Views expressed here do not necessarily reflect those of ScienceDaily or its staff.

View the original article here