Browsing by Author "Thilakarathna, T"

Now showing 1 - 5 of 5

Embargo
Chess ADC – An Automated Aide-De-Camp
(IEEE, 2020) Divulage, A; Bandara, R; Liyanage, T; Ishara, M; Gamage, A. I; Thilakarathna, T
Various types of tools and techniques are used to analyse chess games. The existing most successful and accredited method is, electronic boards where it is able to track and extract the movement data with the help of electronic equipment and pressure detecting sensors [1]. But that solution is expensive. Chess ADC is a comprehensive framework that can be used by anyone for practicing and developing chess skills. It allows users to play chess games on a real chessboard and measure their level of skill. Although chess is a very complicated game that has many different patterns of piece movements, all the number of states that a game can have is finite. We can solve chess with just math if we have unlimited amount of computing power [2]. Deep learning models have already been used in research on various board games such as backgammon, checkers, Go and chess [3]. Chess ADC also utilizes these technologies to give a better user experience for the players. We call this system “Chess ADC – An Automated Aide-De-Camp” because it functions as an aide-de-camp for chess. The system uses a special camera rig to capture different states of the board as images. Players are guided with onscreen instructions to set up the environment at the beginning of each game. At this stage, the position of each chess piece is validated. If the system was able to find any misplaced piece, it notifies the player to correct the position. This process is handled using image processing combined with machine learning. After setting up the board correctly, players can start the game. While in the game, each position of the chess piece is tracked and validated against chess rules. This helps to correct the mistakes of the players. The system asks the players to correct the mistakes if it has detected any mistake. Image processing and chess.js library will be used to achieve this. In difficult situations, players can request hints from the system about the best move they can make. The system will give the best move for that situation using the Stockfish engine. At the same time, the system tries to predict the opponent’s next move based on the generated hint from the engine. The best move and the prediction are displayed on the mobile screen of the player so that the player can decide the next move. An artificial neural network (ANN) developed combining one Convolutional Long Short-term Memory (ConvLSTM) neural network and six different Convolutional neural networks (CNN) is used to make predictions about the opponent. Chess-ADC can recognize the winning probability of every move of the chess pieces. And recognize special moves that have an important impact on the probability of winning. And the player can see those good-bad moves and it is very important for the learning process. We use portable notation files for the storing of game details so that the players will be able to view the past games. The system stores all the matches in a database. This way the players can re-watch the games that they have played before and improve their game strategies while looking at the changes in the win percentage. Gathered data are analyzed and advanced reports are generated. Players can access these reports through user accounts. These reports will help the players to identify the best moves and the worst moves that they have made.
Embargo
Computer Vision Based Privacy Protected Fall Detection and Behavior Monitoring System for the Care of the Elderly
(IEEE, 2021-09-07) Fernando, Y. P. N; Gunasekara, K. D. B; Sirikumara, K. P; Galappaththi, U. E; Thilakarathna, T; Kasthurirathna, D
The elderly population constitutes a large percentage of the society hence making elderly care a top priority. Falls have been identified as a leading issue among major problems faced by them. Concerning this, many monitoring devices have been developed, most of them focusing solely on one specific health care aspect or related to fall detection, and are based on sensors and wearable devices which are usually uncomfortable for daily use. Considering these aspects, the solution proposed in this research is a real time computer vision-based system that monitors behavior and detects anomalies through deep learning. The monitoring is mainly focused on detecting unusual behavior including falls, and monitoring routine activities to detect deviations. A device approach is used to deploy the deep learning models and consists of IP camera-based monitoring which uses a special privacy protected procedure that ensures the detection is done based on meta data and therefore no camera image or footage is stored. The research is mainly focused on four major components which are user identification, fall detection, routine variance detection and device configuration.
Embargo
Computer-Vision Enabled Waste Management System for Green Environment
(IEEE, 2021-12-09) Hewagamage, P; Mihiranga, A; Perera, D; Fernando, R; Thilakarathna, T; Kasthurirathna, D
Waste management has become a critical requirement to maintain a green environment in Sri Lanka as well as other countries. Town councils have to regularly collect different types of wastes to clean cities/towns. Hence managing the waste of the cities is a challenging task. However, most of the urban councils currently use a manual approach to managing waste. However, it results in many difficulties for the people and cleaning staff who involve in the process by following strict guidelines. Issues due to waste contamination, no proper information management of waste collection, and no punctuality in removing waste from the garbage bins are some of the significant issues arising from the manual process. Due to the drawbacks of the manual approach, social issues, environmental issues, health issues can occur easily. This paper proposes a better solution to replace this manual system with an automated system to overcome these issues. Hence, the main objective of this research is to introduce an ICT-based innovative design that can be used to develop an effective waste management system in town councils. In the proposed model, we will introduce a Computer Vision-based smart waste bin system with real-time monitoring that incorporates various technologies such as computer vision, sensor-based IoT devices, and geographical information system (GIS) related technologies. Our proposed solution consists of a waste bin system, which is capable of automated waste segregation. Our design facilitates the admin users to expand the waste bin kit by adding more waste categories in a user-friendly manner, making our product adaptive in any environment. At the same time, waste bins can notify the real-time waste status. Our system generates the optimum collection routing path and displays it in a mobile app using those real-time status details. We also demonstrate a low-cost prototype.
Embargo
DFOG-Image Processing Application for Real-Time Defogging
(IEEE, 2020-11-04) Indiketiya, I. H. O. H; Kulasekara, K. M. R. A; Thomas, J. M; Gamage, I; Thilakarathna, T
The enhancement of real-time video taken under bad visibility or bad weather is a vital necessity in consumer transport industry and computer vision applications. During the past decade, many researchers have been devoted to the problem of how to remove fog noise from real-time video. Nowadays vehicle industry uses various computing systems to assist in the transport of travelers from one location to another .now most of the cars have revers camera front cameras and sensors who give the signal when the vehicle is near to another object. These detections and identification are useful for the safe operation of vehicles. When looking through vehicle accident history, many accidents caused bad weather conditions. Fog, haze, rain, and other natural weather conditions cannot remove physically. Fog and haze block vison above 1 kilometer. There is a defogger in the windscreen, but it is only removed Mist on the windscreen. For the driver's vision above the rode, there is no such thing for that. The purpose of this research paper is introducing a new system to remove fog from real-time video and give detailed visual to the driver in foggy or other bad weather condition. This D-Fog system includes functions such as give clear realtime visual in bad weather condition, recognize, and give details about the object above the road, give the distance between objects and vehicle. In this system, main function is producing real-time defogged, clear video. Combination of Ha and Hoon method and Dark channel priority method used to get this real-time defog video. To recognize the object, this system has use thermal sensors and heat maps. To get the distance between object and vehicle this system has use LIDAR sensors. Because of this facility, we can name this system as three in one system.
Embargo
SMART Garbage Bin Kit Expandable and Intelligent Waste Management System using Deep Learning and IoT for Modern Organizations
(IEEE, 2021-12-02) Hewagamage, P.; Perera, D; Thilakarathna, T; Kasthurirathna, D; Fernando, R; Mihiranga, A
According to published statistics, Sri Lanka produces garbage around 7000MT per day, and every organization directly contributes this national amount depending on the waste management practices. 'Waste contamination' is a critical issue that affects waste management, and it should be addressed during the garbage collection process. This has led to environmental hazards resulting in health and other social issues. Hence, it is a responsibility of an organization to separate the garbage during the collection process using a suitable technique. In this paper, we are proposing a smart garbage bin kit that automates the separation of garbage collection, which minimizes human error using AI-based technologies. IoT-based devices connected to a smart garbage bin kit guide the user to the correct bin. At the same time, our proposed system can be easily expanded for new special waste categories as well. The other important issue of the current garbage management is improper time management of the garbage removal process in organizations. This happens due to the lack of real-time data on waste bins, and collection is based on the fixed time interval irrespective of the status and location of garbage bins. In the proposed system of SMART Garbage Bin Kit, the group of all interconnected garbage bins is monitored in real-time to identify the optimum collection path considering the location and the status of garbage bins using an optimized algorithm. Hence, the study presented in this paper integrates several intelligent approaches together with IoT based network to build a cutting-edge device, declared as SMART Garbage Bin kit. The prototype system has been built as a part of the research study to demonstrate its feasibility and sustainability.