Vision based guide-dog robot system for visually impaired in urban system

Kou, Xiangxin; Wei, Yuanlong; Lee, Min-Cheol

doi:10.1109/iccas.2013.6703876

Cited by 6 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, since these devices are becoming more accessible, a wide number of assistive technologies have been proposed to support people in everyday activities. Following this trend, several solutions for crosswalks' detection and localization are based on images acquired by smartphones, which may bring some challenges, such as the need to correctly point the camera to the crosswalk (as in [3], [2], [4]) or the need to turn on a sidewalk to acquire panorama images [1], [5]. Besides that, one can take advantage of microphones and other sensors to perform automatic image acquisition, as in [6], despite being limited to very specific scenarios/conditions (i.e., considering that there are buzzers to indicate go and stop status near traffic lights).…”

Section: Introductionmentioning

confidence: 99%

“…RELATED WORK In recent years, several works have been done regarding pedestrian crossing detection and localization to aid visually impaired people to cross the street independently and in a safer way. Many of these works were developed for images captured on the ground (i.e., by a smartphone, robot or vehicle), as in [6], [3], [2], [4], [1], [5]. As mentioned in the work of Senlet and Elgammal [8], road, building and vegetation's detection from aerial images has been extensively studied in remote sensing.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Crosswalk Localization from Low Resolution Satellite Images to Assist Visually Impaired People

Ghilardi

Jacques

Manssour

2018

IEEE Comput. Grap. Appl.

View full text Add to dashboard Cite

In this article, we propose a model for crosswalk detection and localization by using satellite images captured from Google Maps, for the purpose of assisting visually impaired people. The detection is performed by an SVM classifier, which is combined with Google Road Map to speed up computation time and to eliminate some possible false alarms. We assume that a visually impaired person holds a smartphone with an embedded GPS, which is used to initialize the extraction of images from Google Maps, as well as to assist its user by providing audio feedback of the nearest detected crosswalk. This issue brings forward significant interest and it is also very challenging, mainly due to illumination changes, occlusion, image noise and resolution, besides the quality of crosswalks that sometimes are badly painted in many developing countries. Experimental results indicate that the proposed model works well in low resolution images, effectively detecting and localizing crosswalks in simulated scenarios.

show abstract