Navigation and Object Detection for Blind Persons Based on Neural Network

Abstract

Tools for blind people with mobility activities in pedestrian pathways have been widely launched, approved and patented. However, there are still shortcomings that can be done only for pedestrian paths or nearby destinations. In this study, both a camera (detection of the pedestrian path) and LiDAR (detection of surrounding objects) sensors to help disability activities. The first stage of image data from the preparatory camera from RGB to XYZ, color filters, close morphology, resizing, learning and testing of neural networks. Bring up 3 voice attitudes information. Attitudes are perpendicular, left tilted, right tilted, or not reversed to the pedestrian yellow path. The second stage of the LiDAR distance points data is processed into 2D array geometry, learning, and testing of neural networks. Bring up the information 8 voice attitudes. Detection of the cycle and distance of objects right side, front, left, right-front, right-left, front-left, right-front-left, not captured. The test results approximately at lux <15000 got 89.7% accuracy for pedestrian path detection and 87.5% for object detection.

Non-Pharmaceutical Interventions against COVID-19 Pandemic: Review of Contact Tracing and Social Distancing Technologies, Protocols, Apps, Security and Open Research Directions

“…However, although this concept gave insight into sensor-based human proximity sensing, the choice of ultrasonic sensors whose sensing window is about 20° may lead to false-negative errors (where the user is bridging the social distancing protocol but the system fails to detect it). Furthermore, ultrasonic sensors are sensitive to both animate and inanimate objects [ 185 ]. This may as well lead to false-positive errors (falsely alerting the user when close to non-human objects.…”

A comprehensive review of navigation systems for visually impaired individuals

“…They collected, organized, and detected data, converting it into voice for transfer to mobile phones. Setiadi et al [ 88 ] used neural networks to assist the visually impaired. They employed two cameras for pedestrian path detection and Light Detection and Ranging (LiDAR) for environmental sensing.…”

An automated navigation system for blind people

“…Sivan and Darsan [6] ambient assisted living, mobile technology, ultra-sound systems are organized into different parts for collecting data then organizing them, then detecting the data and then ultrasound system converts those into voice and transfers the results to mobile phone. Setiadi et al [7], Sarakhman et al [8] states that using neural networks to help blind people. The researchers used two cameras to detect the pedestrian path and light detection ranging (LiDAR) to detect the surroundings.…”