Deep Multi-Layer Perceptron-Based Obstacle Classification Method From Partial Visual Information: Application to the Assistance of Visually Impaired People

Abstract

How to navigate safely, recognize encountered obstacles, and move independently from one location to another in unknown environments are some of the challenges that face visually impaired people. By proposing a solution towards overcoming these challenges, this work will be of most importance to visually impaired people. In this work, we propose a consistent, reliable and robust smartphone-based method to classify obstacles in unknown environments from partial visual information based on computer vision and machine learning techniques. Our proposed method handles high levels of noise and bad resolution in frames captured from a phone camera. In addition, our proposed method offers maximum flexibility to users and use the least expensive equipment possible. Moreover, by leveraging on deep-learning techniques, the proposed method enables semantic categorization in order to classify obstacles and increase the awareness of the explored environment. The efficiency of the work has been experimentally measured on a variety of experiments studies on different complex scenes. It records high accuracy of [90.2 % ]. INDEX TERMS Image analysis, image classification, supervised learning, mobile applications.

Smart Assistive System for Visually Impaired People Obstruction Avoidance Through Object Detection and Classification

“…Because of signal losses, a Global Positioning System (GPS) does not operate effectively indoors [22], [23]. To deal with such situations, there is a technique called Preliminary Data Requirements (PDR) that estimates a pedestrian's position using inertial sensors [24], [26]. Inertial sensors include motion sensors (accelerometers) and rotation sensors (gyroscope sensors) to uninterruptedly measure by dead reckoning the position, the orientation, and the velocity (direction and speed of movement) of a moving object.…”

“…Hence, fulfilling the daily tasks of life becomes extremely hard for them. This can lead to difficulties which can only be temporarily subdued by some assisting personnel, and cases exist where certain situations might be fatal, not only for the individual, but also anyone in the surrounding environment [2]. With the innovations in scientific area, much research was proposed that specifies the designing of gadgets for visually impaired individuals.…”

“…With the innovations in scientific area, much research was proposed that specifies the designing of gadgets for visually impaired individuals. These gadgets [2]- [4] were simple and durable, but they were deficient in terms of usage and accuracy.…”

“…being that normal persons also ignore small things that do not intend to cause any significant harm. Therefore, the system will also recognize the scenes [2], [11], [12] for the intended user. All this information will be communicated in the form of voice to the person, in order to avoid any damage.…”

Efficient Multi-Object Detection and Smart Navigation Using Artificial Intelligence for Visually Impaired People

“…A wearable deep learning-based drug pill recognition system for the improvement in safety to visually impaired people using medicines works by reducing the risk of taking incorrect drugs [ 27 ]. An assistive device to help visually impaired people using partial visual information and machine learning techniques which enables semantic categorization for the classification of obstacles in front of them achieves a highest accuracy of 90.2% [ 28 ].…”