Browsing by Author "Walgampaya, N"

Now showing 1 - 2 of 2

Embargo
EyeVista: An assistive wearable device for visually impaired sprint athletes
(IEEE, 2016-12-16) Peiris, H; Kulasekara, C; Wijesinghe, H; Kothalawala, B; Walgampaya, N; Kasthurirathna, D
On-going progressions of Information Technology increase the scope for computer vision-based interventions to facilitate efficient and promising technology for people with disabilities. This project aims to develop a wearable navigational assistive device, titled EyeVista, to facilitate visually impaired sprint athletes. It is a lightweight, easy-to-use, customizable and low-cost wearable jacket built-in with off-the-shelf based on computer vision techniques. Synthesis of research initially reflects the impact of the main barriers of a human guide and how to break down such barriers. In doing so, we hope to introduce an alternative to the current practice of having a human guide for blind athletes, overcoming the shortcomings of it. The designed system uses Raspberry Pi single board computer to process the real-time image captured by Raspberry Pi camera module to navigate the athletes within the assigned track and to avoid collisions. As a result, we believe the project EyeVista will empower the visually impaired sprint athletes to enhance their performance by easing their mobility by allowing the user to move within their relevant track lanes and avoid collisions without the support of a human guide and enhance the independence, safety along with the quality of life.
Embargo
Using CNNs RNNs and Machine Learning Algorithms for Real-time Crime Prediction
(IEEE, 2019-12-05) Rajapakshe, C; Balasooriya, S; Dayarathna, H; Ranaweera, N; Walgampaya, N; Pemadasa, N
Over the recent years crime rates in Sri Lanka have drastically increased. Main priority of police is to prevent crime occurrences in order to enhance public safety. Criminals use advanced technologies, which make the crime investigations cumbersome. Police officers spend lot of time and effort on these investigations. A wide range of researches are being conducted in the areas of Artificial Intelligence (AI) and Neural Networks to automate crime detection and prediction. In this paper, we present machine learning and deep learning based E-police system to enhance public safety and support law enforcement. Main objective of the system is prevention of crimes. E-Police is an application that helps police officers to get informed about the incidents happening around in real-time. In addition, system provides predictions about possible crimes likely to take place in future so that precautions can be taken to prevent those.