posted on 2018-01-15, 17:00authored byYahya Q.I. Al-Fadhili
Cerebral Visual Impairment (CVI) is a medical area that concerns the study of the effect of brain damages on the visual field (VF). People with CVI are not able to construct a perfect 3-Dimensional view of what they see through their eyes in their brain. Therefore, they have difficulties in their mobility and behaviours that others find hard to understand due to their visual impairment.
A branch of Artificial Intelligence (AI) is the simulation of behaviour by building computational models that help to explain how people solve problems or why they behave in a certain way. This project describes a novel intelligent system that simulates the navigation problems faced by people with CVI. This will help relatives, friends, and ophthalmologists of CVI patients understand more about their difficulties in navigating their everyday environment.
The navigation simulation system is implemented using the Unity3D game engine. Virtual scenes of different living environments are also created using the Unity modelling software. The vision of the avatar in the virtual environment is implemented using a camera provided by the 3D game engine. Given a visual field chart of a CVI patient with visual impairment, the system automatically creates a filter (mask) that mimics a visual defect and places it in front of the visual field of the avatar. The filters are created by extracting, classifying and converting the symbols of the defected areas in the visual field chart to numerical values and then converted to textures to mask the vision. Each numeric value represents a level of transparency and opacity according to the severity of the visual defect in that region. The filters represent the vision masks.
Unity3D supports physical properties to facilitate the representation of the VF defects into a form of structures of rays. The length of each ray depends on the VF defect s numeric value. Such that, the greater values (means a greater percentage of opacity) represented by short rays in length. While the smaller values (means a greater percentage of transparency) represented by longer rays. The lengths of all rays are representing the vision map (how far the patient can see).
Algorithms for navigation based on the generated rays have been developed to enable the avatar to move around in given virtual environments. The avatar depends on the generated vision map and will exhibit different behaviours to simulate the navigation problem of real patients. The avatar s behaviour of navigation differs from patient to another according to their different defects.
An experiment of navigating virtual environments (scenes) using the HTC Oculus Vive Headset was conducted using different scenarios. The scenarios are designed to use different VF defects within different scenes. The experiment simulates the patient s navigation in virtual environments with static objects (rooms) and in virtual environments with moving objects. The behaviours of the experiment participants actions (avoid/bump) match the avatar s using the same scenario.
This project has created a system that enables the CVI patient s parents and relatives to aid the understanding what the CVI patient encounter. Besides, it aids the specialists and educators to take into account all the difficulties that the patients experience. Then, is to design and develop appropriate educational programs that can help each individual patient.
This work is made available according to the conditions of the Creative Commons Attribution-NonCommercial-NoDerivatives 2.5 Generic (CC BY-NC-ND 2.5) licence. Full details of this licence are available at: http://creativecommons.org/licenses/by-nc-nd/2.5/
Publication date
2018
Notes
A Doctoral Thesis. Submitted in partial fulfilment of the requirements for the award of Doctor of Philosophy of Loughborough University.