Browsing by Author "Atiqur Rahman"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Open Access
    Augmented Reality Home Decorator
    (North South University, 2019) AL-AMIN; SHARIEAZ KAVIER; Atiqur Rahman; 1520664042; 1513192642
    This project presents an application of Augmented Reality (AR) for interior design. Due to huge advancements in computer vision algorithms and cheap hardware, Augmented Reality is becoming mainstream. All over the world, most of the sales come from physical stores. Buying furniture from brick-and-mortar shops is cumbersome and time-consuming. AR is changing the furniture industry. In an AR environment, virtual furniture could be placed and manipulated in the physical world in real time, which allows the user to have an interactive experience. Users would be able to visualize exactly how a table would look in their kitchen, dining room, bedroom, or anywhere they want. When people can place an actual couch in the living room or visualize how a bookshelf would look in a Different color. The risk of product return and logistics is drastically reduced. As online stores replace brick-and-mortar shops. AR will play a vital role in the furniture sales. This project provides new ways an individual/enterprise could utilize AR to design interiors.
  • Thumbnail Image
    Item
    Open Access
    Deep Learning Approach for Keypoint-Based Bangla Word Sign Detection for Videos
    (North South University, 2023) Arnop Singh Durjoy; MD. Shahidul Islam; Mahidul Islam Bhuiyan; Atiqur Rahman; 2011061042; 2011703642; 2011111642
    This research delves into the realm of Bangla sign language recognition, focusing on developing a robust system for interpreting and analyzing gestures depicted in videos. Employing a keypoint based approach and leveraging deep learning technology, specifically a two-layer LSTM architecture, our methodology aims to interpret Bangla word signs accurately. The project's foundation lies in a meticulously curated custom dataset featuring 51 unique signs captured by two proficient signers, ensuring comprehensive coverage of articulation, speed, and style variations. Our system's tailored approach acknowledges a bridge to communication gaps and enhances accessibility for the Bangla-speaking Deaf community. Beyond technical advancements, this research aims to elevate societal awareness and foster employment opportunities for the Deaf population, ultimately contributing to a more inclusive world. The outcomes of this project have the potential to not only revolutionize Bangla sign language recognition but also pave the way for broader applications in accessibility and advancements in deep learning technology for diverse sign languages worldwide.
  • Thumbnail Image
    Item
    Open Access
    Efficient Intelligent Solar Tracking Control System
    (North South University, 2021) Mahima Anwar; Asif Abbas; Tahsin Tabassum Urnisha; Atiqur Rahman; 1631549043; 1721367043; 1632001043
    The electricity demand of Bangladesh has been increasing at an average pace of 10% over the last decade. There is still a scarcity of electricity in many rural areas of Bangladesh. A renewable-energy-based system will bring more benefits than conventional power. Solar energy is a renewable, free source of energy that is sustainable and also a non-polluting source of energy. Nowadays, solar power is being used to meet the shortfall of electricity. The paper considers an efficient intelligent solar tracking system to increase the efficiency of solar energy production. The purpose of the paper is to generate electricity from solar energy & increase efficiency. In the project, two dual-axis solar panels, which have been attached with two servo motors, collect solar energy by rotating both vertically and horizontally. Another solar panel is connected, which lies in a horizontal plane, to compare the difference in the electrical output of the two different setups and calculate the efficiency. Data is collected in different weather conditions by the solar panels. The RF module is used to transmit data over the wireless channel. The receiver part of the RF module is connected to the computer, and the received data is monitored in real time. The main aim of this project is to increase the efficiency of the solar panel to meet the rising demand for electricity at a lower cost in Bangladesh. Solar energy can be widely used for different purposes in Bangladesh by installing large solar grids to minimize the cost and get maximum efficiency.
  • Thumbnail Image
    Item
    Open Access
    Vehicle Identification and Counting System Using Machine Learning
    (North South University, 2021) Md. Shahrior Gohor; B. M Tanvir Hossain; Atiqur Rahman; 1610824042; 1611687042
    In the realm of road management, the significance of intelligent vehicle recognition and counting has grown immensely. However, this task is made inherently challenging by the wide variety of vehicle sizes and shapes on the road, which directly influences the accuracy of vehicle counting. To tackle this challenge, we present a robust vision-based vehicle recognition and counting system that employs the Yolo machine learning method. In the context of intelligent road traffic management and control, accurate vehicle identification and comprehensive statistics in road monitoring video sequences are paramount. The proliferation of traffic surveillance cameras has resulted in a vast reservoir of traffic video footage for analysis. An elevated viewing angle is necessary to achieve a broader view of the road surface. But at this increased viewing angle, the size of vehicles varies significantly, and the accuracy of detecting smaller objects situated farther from the road diminishes. In light of these formidable challenges posed by diverse camera conditions, addressing and surmount these obstacles effectively is crucial. In this study, we propose a promising approach for vehicle detection that goes beyond mere identification. The findings from our system serve as a foundational component for multi-object tracking and vehicle counting. Our vision-based approach, utilizing the Yolo machine learning method, is tailored to accommodate the dynamic nature of road traffic. By continuously improving the accuracy of vehicle recognition and counting, we contribute to more intelligent road traffic management and control. The insights gained from this system offer valuable data for traffic analysis and decision making, ultimately leading to safer and more efficient roadways.