INDRAJAYA, CHRISNA (2022) PENGOLAHAN CITRA UNTUK KLASIFIKASI JENIS KENDARAAN MENGGUNAKAN RASPBERRY PI SECARA REAL TIME. S1 thesis, UNIVERSITAS SULTAN AGENG TIRTAYASA.
![[img]](https://eprints.untirta.ac.id/style/images/fileicons/text.png) |
Text
COVER.pdf Restricted to Registered users only Download (1MB) |
|
Text
BAB 1.pdf Restricted to Registered users only Download (718kB) |
|
Text
BAB 2.pdf Restricted to Registered users only Download (1MB) |
|
Text
BAB 3.pdf Restricted to Registered users only Download (1MB) |
|
Text
BAB 4.pdf Restricted to Registered users only Download (1MB) |
|
Text
BAB 5.pdf Restricted to Registered users only Download (586kB) |
|
Text
DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (711kB) |
|
Text
LAMPIRAN.pdf Restricted to Registered users only Download (711kB) |
Abstract
Penelitian ini merancang sebuah sistem yang dapat melakukan klasifikasi kendaraan mobil, mobil pick up, truk 2 as, truk 3 as, truk 4 as, truk 5 as/lebih, bus besar, bus sedang. Sistem yang dibuat menggunakan program dengan bahasa Python dan hardware Raspberry Pi. Klasifikasi jenis kendaraan menggunakan framework Tensorflow Lite dan model SSD-MobilenetV2. Model SSD�MobilenetV2 harus di-training dahulu sebelumnya supaya dapat melakukan klasifikasi jenis kendaraan. Proses training dilakukan di Google Colaboratory karna terdapat super GPU sehingga akan mempercepat proses training. Hasil dari proses training kemudian di optimalisasi sehingga akan memperkecil ukuran file. Setelah model SSD-MobilenetV2 dibuat maka dapat mebuat program untuk melakukan klasifikasi jenis kendaraan secara realtime menggunakan Raspberry Pi. Hasil dari klasifikasi kemudian dikirimkan ke database MySQL. Pengujian akurasi menghasilkan rata-rata akurasi 99.405% untuk semua jenis kendaraan. Akurasi pengiriman data ke database menghasilkan rata-rata akurasi 84.661%. Hasil FPS yang didapat rata-rata 2.6 FPS.
| Item Type: | Thesis (S1) | ||||||
|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||
| Additional Information: | This research designed a system that can classify cars, pick-up cars, truck 2 axles, truck 3 axles, truck 4 axles, truck 5 axles / more, large bus, medium bus. The system is created using a program in the Python language and Raspberry Pi hardware. The vehicle type classification uses the Tensorflow Lite framework and the SSD�MobilenetV2 model. The SSD-MobilenetV2 model must be trained beforehand in order to classify the type of vehicle. The training process is carried out at Google Colaboratory because there is a super GPU so it will speed up the training process. The results of the training process are then optimized so that it will reduce the file size. After the SSD-MobilenetV2 model is made, it can create a program to classify vehicle types in real time using the Raspberry Pi. The results of the classification are then sent to the MySQL database. Accuracy testing yields an average accuracy of 99.405% for all vehicle types. Accuracy data delivery to the database resulted in an average accuracy of 84,661%. The average FPS results obtained are 2.6 FPS. Keywords: Classification of vehicle types, image processing, Raspberry Pi, Tensorflow Lite, Google Colab, SSD-mobilenetV2, database MySQL | ||||||
| Uncontrolled Keywords: | Kata Kunci: Klasifikasi jenis kendaraan, Pengolahan citra, Raspberry Pi, Tensorflow Lite, Google Colab, SSD-MobilenetV2, database MySQL | ||||||
| Subjects: | S Agriculture > SH Aquaculture. Fisheries. Angling | ||||||
| Divisions: | 03-Fakultas Teknik 03-Fakultas Teknik > 20201-Jurusan Teknik Elektro |
||||||
| Depositing User: | Perpustakaan Pusat | ||||||
| Date Deposited: | 01 Aug 2022 10:01 | ||||||
| Last Modified: | 01 Aug 2022 10:01 | ||||||
| URI: | http://eprints.untirta.ac.id/id/eprint/15022 |
Actions (login required)
 |
View Item |