Department of Computer Science

Permanent URI for this communityhttps://repository.cuilahore.edu.pk/handle/123456789/16

Browse

Author: search.filters.author.Dr. Zeeshan GillaniHas files: Yes

Search Results

Now showing 1 - 10 of 22
  • No Thumbnail Available
    Item
    Wildfire Detection using Satellite Imagery
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Faisal Saqib; FA22-RCS-007; Dr. Zeeshan Gillani; LHR TP 9494
    This thesis presents an innovative approach to wildfire detection using satellite imagery, aimed at enhancing detection accuracy and robustness through the fine-tuning of pre trained state-of-the-art deep learning models. Utilizing a dedicated wildfire satellite imagery dataset, our research focused on optimizing these models to better generalize across diverse environmental conditions encountered in satellite data. Key evaluation metrics employed in this study included Dice Loss, Intersection over Union (IoU), and Accuracy, which facilitated comprehensive performance assessments. Our method involved adjusting existing model architectures to improve their efficacy in segmenting and identifying wildfire-affected areas accurately. The results of our experiments indicate significant improvements in model performance, with increased precision in detecting and delineating wildfire boundaries. These findings not only demonstrate the potential of advanced computational techniques in the field of remote sensing for wildfire detection but also provide valuable insights for future applications in environmental monitoring and disaster management. This work underscores the effectiveness of tailored deep learning solutions in enhancing the capabilities of satellite imagery analysis for critical real-world challenges.
  • No Thumbnail Available
    Item
    Trading Bot
    (Library Information Services, CUI Lahore, 2024) Ammar Aamir; FA20-BCS- 076/LHR; Dr. Zeeshan Gillani
    Wealth creation and the stability of the financial system heavily rely on the stock market, which is an essential part of the global economy where brokers and stakeholders usually trade stock manually. Alternatively, intelligent systems are also used that make predictions based on past data to trade automatically. This project proposes “Trading Bot" that facilitates the traders to make trading simpler on NASDAQ stocks by making educated decisions using deep learning models. Utilizing historical data, a deep learning model forecasts stock closing price. The user-friendly interface enables users to visualize predictions and execute manual or automated trades based on these insights. Additionally, “Trading Bot" can also be useful for amateur users that are interested in investing in stocks.
  • No Thumbnail Available
    Item
    Visual Shop
    (Library Information Services, COMSATS University Islamabad, Lahore Campus., 2022-11-20) Asim Ramzan; FA18-BCS-128; Dr. Zeeshan Gillani
    With over two decades of internet boom, shopping trends have changed a lot. People use human computer interaction for shopping online. After a decade of internet rise, intelligent systems were designed to interact with humans to assist in online shopping. These bots were trained to start conversations the way humans talk and helped searching products via text inputs or voice messages. These intelligent systems were not good at searching products via images or based on certain features. Mostly it is a hectic process for customers to describe these types of features while hunting for products online. This brings us to the need of searching by image assistant or Visual Shop which recommends products based on the image provided by the user. Users can capture a snap from the device directly or take any pictures from social media to follow the latest trends and search for the same products on an e-commerce store. A recommendation system helps in online shopping based on the previous shopping or search history. It uses stats and knowledge retrieval methods to come up with best matching product suggestions. It will be wired to provide relative outcomes to the customer queries by applying machine learning based image detection methods.
  • No Thumbnail Available
    Item
    Vehicle Tracking System
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Rao Mubashar Ali , Ali Suhaib Shahid , Ammar Yasee; FA17-BCS-124 , FA17-BCS-082 , FA17-BCS-033; Dr. Zeeshan Gillani; LHR TP 7519
    The increase in population in metropolitan cities has given rise to severe traffic management problems and security issues. The rise in CCTV (Closed-circuit television) based solution has enabled us to monitor traffic but the sheer number of the cameras has given rise to another challenge of monitoring these systems and analyse this rich information. The advancement in computer vision techniques and GPU (Graphical processing unit) has now enable techniques than can automatically task which was only possible by humans in the past. CNN (Convolutional neural networks) based models can enable us to use real time videos of traffic data to aid in analysing the traffic conditions which in turn helps us in effective decision making regarding our cities to make them intelligent and safe. We will employ futuristic algorithms on the NVIDIA AI city datasets to evaluate the traffic detection and tracking systems.
  • No Thumbnail Available
    Item
    Artistify – Artist Identification of an Artwork using CNN
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Usama Anwar Butt; SP17-BCS-128; Dr. Zeeshan Gillani; LHR TP 7169
    Identifying the artist of the painting is a particularly difficult problem if there are no other metadata concerning the accessible image. Historians and Librarians in the past used to catalogue of notable artworks and used to debate over possible painters that might have originally painted the piece. This is a topic of active research in the computer vision field because of the challenging nature of the problem. We will apply a class of deep neural networks which is a Convolution Neural Network to analysing visual imagery. Using a dataset that contains artwork from the most creative artists of all time like Andy Warhol and Vincent Van Gogh, my network will learn the pattern and characteristics of the art and classify the given artwork to best predict the likely artist. Our goal is to create a model that learns to identify the artist analyzing new pictures.
  • No Thumbnail Available
    Item
    Plant Disease Phenotype Identification and Classification via Deep Learning
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Haider Ali Khichi , Muhammad Abdullah Aqib; SP17-BCS-038 , SP17-BCS-062; Dr. Zeeshan Gillani; LHR TP 7163
    Humans face global food shortages in the upcoming years, and we must maximize the yield of common crops to feed the growing population. Plant diseases are a major threat to small and large farm owners alike. These diseases reduce the potential yield of the crops, and in some severe but frequent cases, up to 100%. The identification of these diseases remains a challenge despite government efforts to educate farmers. There is a need for identification of these diseases early on so that they can be treated quickly. The pervasiveness of smartphones among farmers around the world offers the potential of adopting recent technological developments in computer science to develop a solution that can help in plant disease phenotype identification. This rich ecosystem of diverse communities can be a great advantage to crop heath and consequently the human race. To utilize the potential of these technologies we use a dataset curated by PlantVillage that contains over 50,000 images of 14 different crops that can be utilized to perform disease identification using modern deep learning algorithms. The models can then be employed by smartphones to identify the diseases and recommend possible treatments
  • No Thumbnail Available
    Item
    Deep learning approach for mango varieties identification using UAV imagery
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) ANISH HASSAN; SP19-BCS-009; Dr. Zeeshan Gillani
    In this study, we propose a deep learning approach for the detection, variety identification, and health assessment of mango trees using UAV imagery. We used a DJI P4 Multispectral camera to collect images of mango orchards which were then used to train YOLOv5, YOLOv7, and Detectron2, three state-of-the-art object detection models. Our models were able to accurately detect trees in an image and classify the variety of the mango tree, as well as identify whether the tree is healthy or not. This approach can be useful for monitoring and managing mango orchards, as it allows for the efficient and accurate identification of tree variety and health status. This can be helpful for farmers as it can assist in early identification of diseased or unproductive trees, enabling timely action to be taken, such as providing targeted treatment or replacing the unproductive trees. Additionally, identifying the variety of the tree can help farmers in making better decision regarding harvesting, pruning and other orchard management tasks. The use of DJI P4 Multispectral camera enabled us to acquire both RGB and NDVI data, which helped us to differentiate the healthy trees from the unhealthy ones. The results of our study showed that the YOLOv5 model performed the best, achieving an overall accuracy of more than 80% in tree detection, variety identification and health assessment, demonstrating the potential of UAV imagery, multispectral sensor and deep learning in fruit orchard management. The proposed approach can be easily scaled and applied to other crop fields as well, providing farmers with a reliable and efficient tool for monitoring and management of their orchards.
  • No Thumbnail Available
    Item
    CNN based techniques for Detecting Anomalies in the Crop
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Rimsha Urooj , Shifa Allah Baksh , Fatima Batool; FA17-BSE-154 , FA17-BSE-164 , FA17-BSE-017; Dr. Zeeshan Gillani; LHR TP 7027
    The population across the globe is increasing at an alarming rate across the globe. This is giving rise to many challenges and one of the primary challenges is to feed an ever-increasing population with the same resources availed. This will lead to a food security and food crisis if we are not able to adapt our farming methods to modern technologies. With the advancement in computer vision techniques by using advanced CNN-based methods we can now analyse crops to detect anomalies in the crop. These applications could provide a foundation for the development of expertise aid or automatic screening tools. Such tools could contribute to further sustainable agricultural traditions and greater food production safety.
  • No Thumbnail Available
    Item
    Terrific Traffic
    (Library Information Services, COMSATS University Islamabad, Lahore Campus., 2020-11-20) Sarmad Khan; FA16-BCS-099; Dr. Zeeshan Gillani; LHR TP 6158
    The proposed is a system to detect traffic violations through anomalies detection using Machine Learning techniques from within a live traffic video stream. An anomaly is considered an irregularity or an event which would not occur in normal circumstances. Keeping traffic violations in account the circumstances will be such as Accidents, car crashes and lane violation. The proposed system will be able to differentiate not only between a normal and an abnormal event based on the events in the video stream but will also classify the anomaly accordingly. The purpose of this system is to automate and facilitate the traffic surveillance tasks in daily life. This result is achieved through implementing Image Processing and Deep learning techniques to predict the anomalous section of a video.
  • No Thumbnail Available
    Item
    Deep Learning-Based Prediction of Urban Area Expansion
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Hamza Ali; FA20-RCS-003; LHR TP 8360; Dr. Zeeshan Gillani
    Multi-temporal data can be useful in many research areas. Multi-temporal data provides us with high-resolution satellite imagery. This high-resolution data can be used to understand change detection in a specific area or the layout of that complete area. To use multi-temporal data, especially custom datasets for deep learning models is real headache. Moreover, Multi temporal data can be very useful with Artificial Intelligence to develop models to tackle different problems like wildfire detection, traffic flow detection, etc. This thesis focuses on two problems 1st one is how can custom multi-temporal dataset which consists of a small sample be used to develop a deep learning model for semantic segmentation purpose of given custom dataset and 2nd problem is related to Urban expansion. The problem of urban expansion is a major issue all over the world, especially in the countries of Africa. Urban expansion has a direct impact on both economic growth and climate change. In this era Machine learning and Computer Vision techniques will provide a vital role to create a model which will help to tackle this problem using multi-temporal data. This thesis methodology is to use custom satellite images data set of a specific area and create a deep learning segmentation model to do segmentation and prediction of different areas in satellite images especially, the urban part. This research focuses on the RGB multi-temporal data set of Dakar, Senegal which is one of the Seaports on the Western Coast of Africa. This thesis methodology is divided into two separate parts. 1st part is about segmentation, an experiment was conducted using with simple Multi U-Net architecture and it achieved more than 85% accuracy on the validation dataset. After these predictions were made using random images from the test dataset. 2nd part focused on the urban expansion problem and trained a Regression model using an Artificial Neural Network which only got a 12% MSE value with 97.25% accuracy and predicts urban expansion on basis of pixel values from remote sensing data using population data from the year 2022 to 2031