Dataset of Public Objects in Uncontrolled Environment for Navigation Aiding

Abstract

Computer vision is a new approach to navigation aiding that assists visually impaired people to travel independently. A deep learning-based solution implemented on a portable device that uses a monocular camera to capture public objects could be a low-cost and handy navigation aid. By recognizing public objects in the street and estimating their distance from the user, visually impaired people are able to avoid obstacles in the outdoor environment and walk safely. In this paper, we created a dataset of public objects in an uncontrolled environment for navigation aiding. The dataset contains three classes of objects which commonly exist on pavements in the city. It was verified that the dataset was of high quality for object detection and distance estimation, and was ultimately utilized as a navigation aid solution.

Toward the design of persuasive systems for a healthy workplace: a real-time posture detection

“…Programmatically, we split the datasets into 90% training and 10% validation datasets for the Yolo-V3 model. The reason for the difference in this split ratio was based on previous studies employing similar ratios, especially for Yolo models (Akut, 2019 ; Setyadi et al, 2023 ; Wong et al, 2023 ).…”

A Lightweight Robust Distance Estimation Method for Navigation Aiding in Unsupervised Environment Using Monocular Camera

“…Training. In the first stage, NFD establishes a deep learning model for training to detect public objects (e.g., fences in the street), which is detailed in [15]. During the training, a certain amount of street view images of public objects were taken by smartphone cameras at random poses.…”

“…We utilized a published dataset on public objects in the uncontrolled environment, which was specifically designed for navigation-aiding purposes [15]. The primary contributions of this work can be summarized as follows:…”

fdata-07-1359906-g0003.tif

“…Programmatically, we split the datasets into 90% training and 10% validation datasets for the Yolo-V3 model. The reason for the difference in this split ratio was based on previous studies employing similar ratios, especially for Yolo models (Akut, 2019;Setyadi et al, 2023;Wong et al, 2023).…”