OBJECT DETECTION FOR THE BLIND USING HAPTIC TECHNOLOGY

Abstract

Visually impaired people face a lot of difficulties accessing information, communicating, and mobility in almost every aspect of their daily life. Unlike a normally sighted person, visually impaired people are unable to view their surroundings. Hence, they have limitations in almost every aspect of their lives like mobility, decision making, etc. They have to face difficulties in accessing information and communicating the same. In this project, we have proposed a low-cost assistive system for the visually impaired called Haptic Obstacle Detector that helps them avoid obstacles around the head area. Thus, their personal, social, as well as professional life, is affected. We propose an object recognition algorithm and an assistive system that is very useful for their safety, quality of life, and freedom from another person all the time. The purpose of this system is to make the visually challenged able to take decisions independently based on the vibration output from this model.

The paper presents an intuitive and low-cost device that helps the blind avoid obstacles around the head height area. The device is called Haptic Obstacle Detector (HOD). HOD uses infrared sensors and ultrasonic sensors to measure the distance between the user and an object within the 3m range.The measurement is then converted to vibrations in different amplitudes and frequencies, which closer distance corresponds to stronger and faster vibrations. HOD can work well in low-light conditions. Measurement accuracy varies with the distance to the object, object geometry, and complexity.

After the distance measurement, the microcontroller provides an output voltage, when the distance is low between the sensor and the object the output voltage is high and vice versa. The range of the Ultrasonic sensors is not high, it can only measure 50cm in open space, for more distance many other powerful sensors are available in the market.

The ultrasonic sensor sends high-frequency pulses, these pulses reflect from the object and takes as Echo, time between echo and Trig is measured by the microcontroller or Arduino which is directly proportional to distance (fig. 1). The speed of sound is 341 meters per second in the air, and the distance between sensor and object is equal to time multiplied by the speed of sound divided by two.

We have used Proteus to design the circuit (fig. 2a) and Tinker cad to simulate the system (fig. 2b), where the high-frequency pulses sent by ultrasonic sensor reflect from the object taken as echo, the time between transmitted and the received waves is

measured by the microcontroller which is directly proportional to distance. As the distance between the sensor and the object reduces, the time between the transmitted and the received waves decreases hence the distance measured also decreases in the same ratio which is then checked by the microcontroller as per the condition set up that is, as the distance reduces a higher output is provided to the vibration motors and hence the vibration increases as the object comes to closer proximity.

Experiments performed have proven that the Haptic Obstacle detectors can detect sharp and complex objects like glass. Results suggest Haptic Object Detector is easy to use and shows a promising concept to help the visually impaired avoid obstacles. The overall system makes use of ultrasound to detect an object and notify the user about the upcoming obstacle through haptic here the sense of touch where the vibrations of the motor increase as the objects approach closer to the user and thereby giving the user an idea about how far the object is from the user. The sensor for object detection needs to be put to test but sonic-based sensors have given the best result for this purpose.

The future scope of this research can be that the entire setup can be used as a wearable device like spectacles (fig. 3). The frame of the spectacles can be used for the placement of the ultrasonic sensor and the microcontroller where the ultrasonic sensor can be placed at different angles to gain a wider range. The frontal frame can make use of a camera module and with the help of object detection, the system can notify if the object is something the user needs to be concerned about or not hence help in distinguish between various objects and which object is at what distance from the user giving the maximum perception of his surrounding and making him aware of the proximity world.