Realtime Local Navigation for the Blind: Detection of Lateral Doors and Sound Interface

Moreno, Márcio Ferreira; Shahrabadi, Somayeh; José, João; Buf, J. M. H. du; Rodrigues, João M. F.

doi:10.1016/j.procs.2012.10.009

Cited by 29 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The average recognition rates of all directions in three times experiments are respectively 92. 25,94.08, and 95.66 %. Direction 5 and direction 1 are easier for subjects to recognize while the recognition rates of direction 2, direction 3 and direction 4 are a little lower.…”

Section: Tactile Perception Experimentsmentioning

confidence: 94%

“…A new framework is discussed in [23] which detects and recognizes stairs, pedestrian crosswalk based on RGB-D images. An obstacle recognition system is proposed in [24], and M. Moreno [25] discusses a method of detecting lateral doors based on a camera worn at the chest of the user. RecognizeCane [26] is equipped with some simple sensors, such as infrared, brilliance or water sensors to detect a stairway, a water puddle, a zebra crossing or a trash can.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Walking Assistant Robotic System for the Visually Impaired Based on Computer Vision and Tactile Perception

Song

Tian

et al. 2015

Int J of Soc Robotics

View full text Add to dashboard Cite

It is a challenging task for the visually impaired to perceive environment information and walk independently. This paper presents a novel design of a walking assistant robotic system based on computer vision and tactile perception. A novel rollator structure is applied to provide a strong physical support. A Kinect device is used as eyes of the visually impaired to capture the front environment information including color images and depth images. And ultrasonic sensors are utilized to detect the evenness of road surface. A wearable vibro-tactile belt is designed to provide the visually impaired with the environment information through different vibration modes. A feature extraction method of safe directions based on depth image compression is proposed. Background difference method is used to realize moving object detection in order to help the visually impaired perceive environment conditions. The experiment results show that the wearable vibro-tactile belt is practical and the walking assistant robotic system is effective and helpful in aiding the visually impaired to walk independently.

show abstract

Section: Tactile Perception Experimentsmentioning

confidence: 94%

Section: Introductionmentioning

confidence: 99%

A Walking Assistant Robotic System for the Visually Impaired Based on Computer Vision and Tactile Perception

Song

Tian

et al. 2015

Int J of Soc Robotics

View full text Add to dashboard Cite

show abstract

“…-Neural Network AND Assistance technology -Artificial Neural Networks AND Visual disability -Artificial Intelligence AND Visual disability Diversas aplicaciones para la asistencia de personas con discapacidad visual integran el uso de sistemas entrenados con RNA y la adquisición de imágenes con cámaras para el reconocimiento de patrones [45,46]. La detección de diferentes tipos de objetos como puertas, esquinas, bordes, caminos, entre otros que facilitan el reconocimiento de obstáculos [47][48][49] y el reconocimiento de rostros y expresiones faciales para mejorar las interacciones sociales [50].…”

Section: Ayudas Integrando Visión Por Computador Y Redes Neuronales Aunclassified

Dispositivos de asistencia para la movilidad en personas con discapacidad visual: una revisión bibliográfica

Salazar

Mesa

2019

Rev. politec.

View full text Add to dashboard Cite

Este documento presenta una revisión literaria, de los dispositivos de ayuda en la movilidad para personas con discapacidad visual, con el objetivo de obtener una visión clara, sobre el progreso de la tecnología y técnicas empleadas para asistir a esta población. De esta forma, se pretende obtener pautas básicas para analizar los equipos más relevantes, para ayudar a las personas con visión reducida y destacar las mejoras que se podrían implementar. Los dispositivos más comunes, corresponden a la integración de diferentes sensores y componentes electrónicos en bastones, para aumentar su capacidad de detección de obstáculos. Además, se han desarrollado dispositivos con cámaras, que incluyen algoritmos de visión por computador y técnicas de Inteligencia Artificial, para mejorar los resultados y eficiencia de los equipos. Finalmente, se presentan las características fundamentales para los sistemas de asistencia, encontrando que aún no se cuenta con dispositivos que satisfagan las necesidades de los usuarios.

show abstract

“…According to this, upper or lower door corners can't exist in the middle of the image. To further reduce the number of corner points, the image is divided into 5 equal horizontal regions and corners that are located in the middle 1/5 of the image were neglected [25].…”

Section: Comer Reductionmentioning

confidence: 99%

Geometric model for vision-based door detection

Shalaby

Salem

Khamis

et al. 2014

2014 9th International Conference on Computer Engineering &Amp; Systems (ICCES)

View full text Add to dashboard Cite

Emerging assistive technologies, such as assistive domotics and socially assistive robots have considerable potential for enhancing the lives of many elderly and physically challenged people throughout the world. Blind and visually impaired people can use these technologies for many tasks recognizing objects, handling various household duties, navigation in indoor and outdoor environments. Door detection is one of the important issues in indoor navigation. This paper presents a novel vision-based door detection technique. It is based on the geometric properties of the 4-side polygon. The efficacy of the proposed method is tested using large database of images with different levels of complexity. The experimental results show the robust ness of the proposed method against changes in colors, sizes, shapes, orientations, and textures of the door. De tection rate of 83% with relatively low false positive rate for simple images is achieved. This proposed algorithm is suitable for real-time, portable applications where it only requires one digital camera and low computational resources.

show abstract

Realtime Local Navigation for the Blind: Detection of Lateral Doors and Sound Interface

Cited by 29 publications

References 8 publications

A Walking Assistant Robotic System for the Visually Impaired Based on Computer Vision and Tactile Perception

A Walking Assistant Robotic System for the Visually Impaired Based on Computer Vision and Tactile Perception

Dispositivos de asistencia para la movilidad en personas con discapacidad visual: una revisión bibliográfica

Geometric model for vision-based door detection

Contact Info

Product

Resources

About