Deteksi Kerumunan Menggunakan Metode Fully-Convolutional Network pada Kamera Drone
Submission Date: 2021-08-19 12:42:05
Accepted Date: 2021-12-22 11:54:06
Abstract
Pada masa pandemi virus COVID-19 pemerintah menetapkan peraturan yang mengharuskan masyarakat untuk menerapkan beberapa protokol kesehatan. Salah satunya adalah menghindari kerumunan dan menjaga jarak. Untuk membantu pengawasan kepatuhan masyarakat terhadap protokol tersebut pada area yang luas, diperlukan sebuah sistem monitoring untuk memantau adanya kerumunan dengan menggunakan drone. Video yang direkam menggunakan kamera drone diproses menggunakan metode Fully-Convolutional Network (FCN) dengan menggabungkan loss function untuk tugas klasifikasi yang menentukan kerumunan atau tidak dan loss function untuk tugas regression yang menghitung kepadatan berdasarkan rata rata clustering coefficient. Penelitian ini mengimplementasikan metode FCN dengan input berupa rangkaian gambar yang diambil dari video sehingga menghasilkan output berupa keputusan apakah sejumlah orang dalam gambar itu berkerumun atau tidak. Data latih yang digunakan adalah VisDrone Dataset dan P-DESTRE Dataset yang terdiri dari rangkaian gambar yang direkam menggunakan drone yang diterbangkan dengan ketinggian rata-rata dengan mengambil contoh video berisi kerumunan dan bukan kerumunan. Hasil pengujian terbaik didapatkan menggunakan pre-trained model 5 dimana memiliki 2 keluaran yaitu 1 klasifikasi dan 1 regresi yaitu memiliki akurasi klasifikasi sebesar 0,978 sedangkan mean ablosute error untuk regresinya sebesar 0,141.
Keywords
COVID-19; Crowd Detection; Fully-Convolutional Network; Convolutional Neural Network; Clustering Coefficient; Drone
CC Licencing
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Refbacks
- There are currently no refbacks.
Jurnal Teknik ITS by Direktorat Riset dan Pengabdian Masyarakat (DRPM) ITS is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Based on a work at https://ejurnal.its.ac.id/index.php/teknik.
Statistik Pengunjung