Welcome to the Bahria University DSpace digital repository. DSpace is a digital service that collects, preserves, and distributes digital material. Repositories are important tools for preserving an organization's legacy; they facilitate digital preservation and scholarly communication.
dc.contributor.author | Aaqib Mehran, 01-243172-045 | |
dc.date.accessioned | 2022-01-17T05:48:10Z | |
dc.date.available | 2022-01-17T05:48:10Z | |
dc.date.issued | 2019 | |
dc.identifier.uri | http://hdl.handle.net/123456789/11583 | |
dc.description | Supervised by Dr. Samabia Tahsin | en_US |
dc.description.abstract | Detecting ships from satellite images is a challenging task in the remote sensing. It is very important for security, traffic management and to avoid smuggling etc. SAR (Synthetic Aperture Radar) is mostly used technology for Maritime monitoring But now researcher are increasingly studying Optical Satellite Images based technologies. Image processing and Computer Vision techniques are previously used to detect ships. In this work, Convolutional Neural Network based approach is used to detect ships in the images. Several Deep Learning Models have been used and tested for this kind of task. We used state-of-art model named Inception-Resnet pre trained on Image-Net dataset. We used the dataset "Ships in Satellite Imagery" to detect if an image contains ships or not. The dataset is public and can be found on Kaggle. The Experimentation done results in success of more than 99% accuracy in detecting ships. | en_US |
dc.language.iso | en | en_US |
dc.publisher | Computer Sciences BUIC | en_US |
dc.relation.ispartofseries | MS (CS);T-0622 | |
dc.subject | Ship Detection | en_US |
dc.subject | Satellite Images | en_US |
dc.title | Ship Detection from Satellite Images | en_US |
dc.type | MS Thesis | en_US |