Multisensor - Based Object Detection in Indoor Environment for Visually Impaired People

Human vision plays a vital role in awareness about surrounding environment. The term visual impairment covers wide range and variety of vision, from blindness and lack of usable sight; to low vision, which cannot be corrected to normal vision with standard eyeglasses or contact lenses. Visually impaired tools can assist them to enrich their lifestyle. To provide assistance to visually impaired people, this paper presents multisensor-based system for object detection in indoor environment. Object detection is performed on a captured image using statistical parameters, which is further validated using support vector machine algorithm. To increase the accuracy of the object detection, multi-sensor concept is employed by interfacing ultrasonic sensor. Moreover, small object near feet is detected using infrared sensor. Experimental results show efficacy of the proposed method.