?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=PENGEMBANGAN+YOLOv4+DENGAN+FITUR+EKSTRAKTOR%0D%0AMobileNetV3+UNTUK+DETEKSI+DAN+KLASIFIKASI+PLAT%0D%0A%0D%0AKENDARAAN&rft.creator=AURA+HUSNAINI+PUTRI%2C+ZAIDANI&rft.subject=000+Ilmu+komputer%2C+informasi+dan+pekerjaan+umum&rft.subject=001+Ilmu+pengetahuan&rft.subject=500+ilmu+pengetahuan+alam+dan+matematika&rft.description=Computer+vision+banyak+dimanfaatkan+untuk+pengembangan+teknologi+seperti%0D%0Adeteksi+objek.+Dalam+deteksi+objek%2C+terdapat+berbagai+algoritma+yang+dapat%0D%0Adigunakan+salah+satunya+YOLO.+Metode+ini+menggunakan+deep+learning+untuk%0D%0Amelakukan+deteksi+secara+real-time.+Pada+penelitian+ini+akan+dilakukan%0D%0Apengembangan+YOLOv4+dengan+fitur+ekstraktor+MobileNetV3+untuk+melakukan%0D%0Adeteksi+dan+klasifikasi+plat+kendaraan.+Hasil+penelitian+ini+menunjukkan+bahwa%0D%0Apengembangan+YOLOv4-MobileNetV3+memiliki+tingkat+performa+yang+lebih%0D%0Atinggi+dibandingkan+original+YOLOv4%2C+yang+menggunakan+CSPDarknet53%0D%0Asebagai+fitur+ekstraktor.+Evaluasi+perbandingan+performa+antara+kedua+model%0D%0Aadalah+dari+segi+performa+akurasi+dan+waktu+komputasi.+YOLOv4-MobileNetV3%0D%0Amemiliki+rata-rata+akurasi+sebesar+97.54%25+sedangkan+YOLOv4-CSPDarknet53%0D%0Amemiliki+rata-rata+akurasi+sebesar+96.93%25.+Dalam+hal+waktu+komputasi%2C%0D%0AYOLOv4-MobileNetV3+membutuhkan+waktu+yang+lebih+sedikit+yaitu+rata-rata%0D%0Asekitar+0.133+seconds+sedangkan+YOLOv4-CSPDarknet53+membutuhkan+rata-rata%0D%0Awaktu+sekitar+0.418+seconds+untuk+melakukan+deteksi+warna+plat+kendaraan.%0D%0A%0D%0AKata+Kunci%3A+Deep+Learning%2C+Fitur+Ekstraktor%2C+YOLOv4%2C+MobileNetV3%2C+Deteksi%2C%0D%0AKlasifikasi%2C+Plat+Kendaraan.%0D%0A%0D%0AComputer+vision+is+widely+utilized+in+the+development+of+technologies+such+as%0D%0Aobject+detection.+In+object+detection%2C+various+algorithms+can+be+used%2C+one+of+which%0D%0Ais+YOLO.+This+method+uses+deep+learning+to+detect+vehicle+plates+on+the+highway%0D%0Ain+real+time.+In+this+research%2C+the+YOLOv4+model+was+improved+with+the%0D%0AMobileNetV3+feature+extractor+for+vehicle+license+plate+detection+and%0D%0Aclassification.+The+results+of+this+study+show+that+the+development+of+YOLOv4-%0D%0AMobileNetV3+has+a+higher+performance+compared+to+the+original+YOLOv4%2C+which%0D%0Auses+CSPDarknet53+as+a+feature+extractor.+The+performance+comparison%0D%0Aevaluation+between+the+two+models+focuses+on+accuracy+and+computational+time.%0D%0AYOLOv4-MobileNetV3+achieved+an+average+accuracy+of+97.54%25%2C+whereas%0D%0AYOLOv4-CSPDarknet53+achieved+an+average+accuracy+of+96.93%25.+In+terms+of%0D%0Acomputation+time%2C+YOLOv4-MobileNetV3+required+less+time%2C+averaging+around%0D%0A0.133+seconds%2C+compared+to+YOLOv4-CSPDarknet53%2C+which+averaged+around%0D%0A0.418+seconds+for+vehicle+license+plate+color+detection.%0D%0A%0D%0AKeywords%3A+Deep+Learning%2C+Feature+Extraction%2C+YOLOv4%2C+MobileNetV3%2C%0D%0ADetection%2C+Classification%2C+Vehicle+Plate.&rft.publisher=FAKULTAS+MATEMATIKA+DAN+ILMU+PENGETAHUAN+ALAM&rft.date=2024-07-11&rft.type=Skripsi&rft.type=NonPeerReviewed&rft.format=text&rft.identifier=http%3A%2F%2Fdigilib.unila.ac.id%2F83543%2F1%2F2017051045%2520-%2520Aura%2520Husnaini%2520Putri%2520Zaidani%2520-%2520FIle%2520ABSTRAK%2520-%2520Aura%2520Husnaini%2520P.%2520Z.pdf&rft.format=text&rft.identifier=http%3A%2F%2Fdigilib.unila.ac.id%2F83543%2F2%2F2017051045%2520-%2520Aura%2520Husnaini%2520Putri%2520Zaidani%2520-%2520Full%2520Skripsi%2520-%2520Aura%2520Husnaini%2520P.%2520Z.pdf&rft.format=text&rft.identifier=http%3A%2F%2Fdigilib.unila.ac.id%2F83543%2F3%2F2017051045%2520-%2520Aura%2520Husnaini%2520Putri%2520Zaidani%2520-%2520Tanpa%2520Bab%2520Pembahasan%2520-%2520Aura%2520Husnaini%2520P.%2520Z.pdf&rft.identifier=++AURA+HUSNAINI+PUTRI%2C+ZAIDANI++(2024)+PENGEMBANGAN+YOLOv4+DENGAN+FITUR+EKSTRAKTOR+MobileNetV3+UNTUK+DETEKSI+DAN+KLASIFIKASI+PLAT+KENDARAAN.++FAKULTAS+MATEMATIKA+DAN+ILMU+PENGETAHUAN+ALAM%2C+UNIVERSITAS+LAMPUNG.+++++&rft.relation=http%3A%2F%2Fdigilib.unila.ac.id%2F83543%2F