Real time static/dynamic obstacle detection for visually impaired persons

Author(s):  
R. Tapu ◽  
B. Mocanu ◽  
T. Zaharia
Author(s):  
PRATEEK MISHRA ◽  
RAJ KISHOR PAL ◽  
SHIVOM KUSHWAHA ◽  
TUSHAR SRIVASTAVA ◽  
SURESH SHARMA

In This Paper we present a real time domain obstacle detection system for the visually impaired persons to improve their mobility in daily life with the help of obstacle detection sensor installed in their walking stick .System is having a lower cost so it is easily purchasable so it can have a major significance in life of visually impaired persons. This Paper proposes a system to detect any object attached to the floor regardless to their height [1]. Obstacle on the floor in the front of user can be reliably detected in real time using the proposed system implemented by the IR sensor installed on the walk stick of the visually impaired person. Project also contains a navigation system for visually impaired persons to make the life of such persons easier up to some extent. This project is suited for the area where the possibility of blind person is high (like blind school, college)[6]. For transport facility of blind we have first decided the common bus roots of blind then we have placed RF tag to all those buses with unique code. At the second side we have placed RF reader, microcontroller and voice processor. The RF reader receive unique code, microcontroller process this code with defined code, if match found, voice processor get activated and starts speaking bus name, initial destination and final destination. The obstacle detection is also included in the project with voice. The system aims at increasing the mobility of visually impaired people by offering new sensing abilities.


2019 ◽  
Vol 8 (2) ◽  
pp. 5152-5156

Locating objects in an image is a very useful task for robotic navigation and visually impaired persons. The ultimate goal of my work is to position the recognized objects in the image. Objects are detected using Adaboost techniques and also recognized from the real-time images. Objects are detected using AdaBoost classifier. SIFT features are extracted from the objects found in the image and classified using Support Vector Machine, and the position of an objects are estimated. We proposed IOLE algorithm to estimate the location of object in an image


2016 ◽  
Vol 10 (7) ◽  
pp. JAMDSM0094-JAMDSM0094
Author(s):  
Anuar MOHAMED KASSIM ◽  
Takashi YASUNO ◽  
Hiroshi SUZUKI ◽  
Mohd SHAHRIEEL MOHD ARAS ◽  
Hazriq IZZUAN JAAFAR ◽  
...  

Author(s):  
Haoran Zhang ◽  
Yiming Yang ◽  
Jiahao Zhou ◽  
Atif Shamim

This paper presents a compact and wearable frequency-modulated continuous-wave (FMCW) radar on a semi-flexible printed circuit board (PCB) for an anti-collision system. This can enable visually impaired people to perceive their environment better and more safely in their everyday lives. In the proposed design, a multiple-input multiple-output (MIMO) antenna array with four receivers (RXs) and three transmitters (TXs) has been designed to achieve obstacle-detection ability in both horizontal and vertical planes through a specific geometrical configuration. Operating at 76–81 GHz, an aperture coupled wide-beam patch antenna with two parasitic patches is proposed for each channel of RXs and TXs. The fast Fourier transform (FFT) algorithm has been implemented in the radar chip AWR1843 for intermediate frequency (IF) signals to generate a range-Doppler map and search precise target angles in high sensitivity. The complete system, which includes both the MIMO antenna array and the radar chip circuit, is utilized on a six-layer semi-flexible PCB to ensure compactness and ease in wearability. Field testing of the complete system has been performed, and an obstacle-detection range of 7 m (for humans) and 19 m (for larger objects) has been obtained. A wide angular detection range of 64-degree broadside view (±32°) has also been achieved. A voice module has also been integrated to deliver the obstacle’s range and angle information to visually impaired persons.


Sign in / Sign up

Export Citation Format

Share Document