Deteksi Pejalan Kaki pada Zebra Cross untuk Peringatan Dini Pengendara Mobil Menggunakan Mask R-CNN
Submission Date: 2021-08-30 13:54:54
Accepted Date: 2021-12-22 11:58:52
Abstract
Dewasa ini, fitur keselamatan pada kendaraan roda empat atau mobil sudah sangat berkembang pesat. Hal tersebut terbukti dengan banyaknya produsen mobil yang menerapkan teknologi seat belt, air bag, adaptive cruise control, electronic stability control, autonomous emergency braking, blind spot monitoring dan lain sebagainya. Namun, fitur yang sudah disebutkan diatas dinilai masih kurang ramah bagi pejalan kaki. Terbukti menurut data dari WHO, terdapat 270.000 pejalan kaki meninggal dunia setiap tahun atau sekitar 22% dari seluruh korban meniggal akibat kecelakan di jalan. Berawal dari permasalahan tersebut, penulis akan melakukan penelitian mengenai pendeteksian pejalan kaki pada zebra cross untuk peringatan dini pengendara mobil sebagai topik penelitian. Pada tugas akhir ini, terdapat 3 objek yang akan dideteksi yaitu pejalan kaki, zebra cross dan pengendara motor dengan menggunakan metode Mask R-CNN. Namun, objek utama yang dideteksi adalah pejalan kaki dan zebra cross, sehingga hasil deteksi pengendara motor tidak ditampilkan pada gambar akhir. Hasil terbaik yang didapatkan adalah pada penggunaan ResNet-101 untuk backbone Mask R-CNN dengan skor mAP sebesar 90.476%, mAR sebesar 88.889% serta F1-Score sebesar 87.777%.
Keywords
Mask R-CNN; Pejalan Kaki; Pengolahan Citra;Zebra Cross
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