Search Results

Mobility of people with disabilities is one of the most important challenges for their social integration. There have been significant effort to develop assistive technologies to guide the PWD during their mobility in recent years. However, these technologies have limitations when it comes to the navigation and guidance of these people through accessible routes. This is specifically problematic in indoor environments where detection, location and tracking of people, and other dynamic objects that may limit the mobility of these people, are very challenging. Thus, many researches have leveraged the use of sensors to track users and dynamic objects in indoor environments. However, in most of the described methods, the sensors are manually deployed. Due to the complexity of indoor environments, the diversity of sensors and their sensing models, as well as the diversity of the profiles of people with disabilities and their needs during their mobility, the optimal deployment of a sensor network is a challenging task. There exist several optimization methods to maximize coverage and minimize the number of sensors while maintaining the minimum connectivity between the sensor nodes in a network. Most of the current sensor network optimization methods oversimplify the environment and do not consider the complexity of 3D indoor environments. In this paper, we propose a novel 3D local optimization algorithm based on a geometric spatial data structure that takes into account some of these complexities for the purpose of helping PWD in their mobility in 3D indoor environments such as shopping centers, museums and other public buildings.