Maulana, Muhammad Azhar (2024) Reidentifikasi Orang pada Data Visible-Infrared Menggunakan Klasifier Swin Transformer. Other thesis, Institut Teknologi Sepuluh Nopember.
Text
5024201062-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (22MB) | Request a copy |
Abstract
Reidentifikasi orang menjadi topik penelitian yang sangat hanget dalam beberapa tahun terakhir dalam visi komputer. Dalam penelitian ini mengusulkan pendekatan reidentifikasi orang yang menggunakan klasifier Swin Transformer pada data citra visual-infrared. Swin Transformer, sebuah arsitektur Transformer yang terkenal karena kinerjanya yang unggul dalam tugas-tugas visi komputer dalam citra visible, diadaptasi untuk tugas reidentifikasi orang dalam citra visible-infrared. Dataset visible-infrared yang digunakan pada penelitian ini adalah dataset RegDB, kemudian model Swin Transformer diaplikasikan sebagai klasifier. Pendekatan ini memungkinkan penangkapan fitur yang efektif dari citra visual dan inframerah, memanfaatkan keunggulan Swin Transformer dalam menangkap dependensi lokal dan global.
========================================================================
Reidentification of individuals has become a highly heated topic in recent years within computer vision. This research proposes an approach to person reidentification using the Swin Transformer classifier on visual-infrared image data. The Swin Transformer, an architecture renowned for its superior performance in computer vision tasks with visible images, is adapted for person reidentification in visual-infrared images. The dataset used for this research is the RegDB visible-infrared dataset. The Swin Transformer model is then applied as a classifier. This approach enables effective feature extraction from both visual and infrared images, leveraging the Swin Transformer’s excellence in capturing local and global dependencies.
Item Type: | Thesis (Other) |
---|---|
Uncontrolled Keywords: | Reidentifikasi, Visible-Infrared, Reidentification, Visible-Infrared. |
Subjects: | T Technology > T Technology (General) > T57.5 Data Processing T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models. T Technology > T Technology (General) > T59.7 Human-machine systems. |
Divisions: | Faculty of Electrical Technology > Computer Engineering > 90243-(S1) Undergraduate Thesis |
Depositing User: | Muhammad Azhar Maulana |
Date Deposited: | 08 Aug 2024 07:39 |
Last Modified: | 08 Aug 2024 07:39 |
URI: | http://repository.its.ac.id/id/eprint/111781 |
Actions (login required)
View Item |