Show simple item record

Fast and Accurate Feature-based Region Identification

dc.contributor.authorMaduakor, Ugochukwu Francis
dc.description.abstractThere have been several improvement in object detection and semantic segmentation results in recent years. Baseline systems that drives these advances are Fast/Faster R-CNN, Fully Convolutional Network and recently Mask R-CNN and its variant that has a weight transfer function. Mask R-CNN is the state-of-art. This research extends the application of the state-of-art in object detection and semantic segmentation in drone based datasets. Existing drone datasets was used to learn semantic segmentation on drone images using Mask R-CNN. This work is the result of my own activity. I have neither given nor received unauthorized assistance on this work.en_US
dc.description.sponsorshipAUST and AfDB.en_US
dc.subject2019 Computer Science and Engineering Thesesen_US
dc.subjectMaduakor Ugochukwu Francisen_US
dc.subjectProf. Lehel Csatóen_US
dc.subjectinstance segmentationen_US
dc.subjectobject detectionen_US
dc.subjectMask R-CNNen_US
dc.subjectdrone program- mingen_US
dc.subjectcomputer visionen_US
dc.titleFast and Accurate Feature-based Region Identificationen_US

Files in this item


This item appears in the following Collection(s)

  • Computer Science105

    This collection contains Computer Science Student's Theses from 2009-2022

Show simple item record