Pasha, Rahandi Noor (2020) Deteksi Ketersediaan Lahan Parkir Pada Data Video Menggunakan Mask Region-based Convolutional Neural Network. Other thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
05111640000054-undergraduate_thesis.pdf Download (6MB) | Preview |
Abstract
Machine learning telah menjadi bagian dari kehidupan sehari-hari bagi banyak orang. Salah satu pengaplikasian machine learning adalah deteksi ketersediaan lahan parkir. Deteksi ketersediaan lahan parkir mengkategorikan lahan parkir menjadi tersedia atau sedang terpakai berdasarkan fitur dari gambar tersebut. Banyak perusahaan, badan riset dan universitas yang terus mengembangkan machine learning agar mendapat hasil yang lebih akurat dan cepat. Convolutional Neural Network (CNN) adalah salah satu deep neural network yang cocok digunakan untuk mengolah data yang berbentuk 2 dimensi, seperti gambar dan video. Tugas akhir ini mengusulkan sistem deteksi ketersediaan lahan parkir secara otomatis menggunakan Mask Region-based Convolutional Neural Network. Data pelatihan menggunakan dataset “Common Objects in Context” (COCO) yang berisi gambar bermacam – macam objek, data uji coba diambil dari dataset CNRPark yang berisi foto dari banyak lahan parkir dan data CCTV departemen Informatika ITS yang nantinya menjadi tujuan deteksi ketersediaan lahan parkir yang dibuat. Hasil evaluasi sistem pada dataset CNRPark didapatkan rata – rata akurasi sebesar 81,14% dan pada data CCTV departemen Informatika ITS didapatkan rata – rata akurasi sebesar 86,07%
==================================================================================================================================
Machine learning has become a part of the daily life of people around the world. One of the application of machine learning is parking lot occupancy detection. Parking lot occupancy detection categorize a parking lot whether its occupied or unoccupied based on the features extracted from the image. Many companies, researchers and universities keep improving the machine learning to get a better and faster result. Convolutional Neural Network (CNN) is one of the deep neural network that suitable to process 2 dimentional data like image and video. In this undergraduate thesis, the writer is proposed an algorithm for parking lot occupancy detection automatically. The goal is simplifying and reducing the cost of parking lot occupancy detection. The train data used in this thesis is taken from “Common Objects in Context” (COCO) dataset which contains images of various kinds of objects, the test data is taken from CNRPark which contains pictures from many parking spots which will be the goal of parking lot occupancy detections. The result of the system evaluation on the CNRPark datasets obtained an average accuracy of 81.14% and the CCTV data of the ITS Informatics Department obtained an average accuracy of 86,07%
| Item Type: | Thesis (Other) |
|---|---|
| Additional Information: | RSIf 006.32 Pas d-1 2020 |
| Uncontrolled Keywords: | Convolutional Neural Network, Data CCTV, Dataset Common Objects in Context, Dataset CNRPark, Deteksi Ketersediaan Lahan Parkir, Mask Region-based Convolutional Neural Network |
| Subjects: | T Technology > T Technology (General) > T57.5 Data Processing |
| Divisions: | Faculty of Information and Communication Technology > Informatics > 55201-(S1) Undergraduate Thesis |
| Depositing User: | Rahandi Noor Pasha |
| Date Deposited: | 11 Mar 2025 03:06 |
| Last Modified: | 11 Mar 2025 03:06 |
| URI: | http://repository.its.ac.id/id/eprint/73699 |
Actions (login required)
 |
View Item |