SISTEM PENDETEKSI BUS DAN TRUK MENGGUNAKAN METODE DEEP LEARNING YOU ONLY LOOK ONCE ( YOLO )
Total View This Week0

Institusion

Universitas Sriwijaya

Author

KHARISMA DESFIAN (STUDENT ID : 09011281320014)
Sri Desy Siswanti (LECTURER ID : 0007127410)
Huda Ubaya (LECTURER ID : 0216068101)

Subject

Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation. 

Datestamp

2021-01-21 08:03:09 

Abstract :
In computer vision, there are several problems, including object detection and image classification. Deep Learning You Only Look Once (YOLO) which is an Artificial Intelegence model of an improved Artificial Neural Network (ANN) is one method that is being developed and is widely used for object detection. In this research, the Deep Learning You Only Look Once (YOLO) model is applied to detect two classes of detection object, which are buses and trucks. With training data using 120 images and test data using 30 images, with resolution 450x300 pixels. YOLO performance with a threshold of 0.25 has an accuracy value of 93.33%, a precision value of 92.30% and a recall value of 100%. YOLO performance with a threshold of 0.45 has an accuracy value of 96.66%, a precision value of 96.15% and a recall value of 100%. YOLO performance with a threshold of 0.85 has an accuracy value of 96.66%, a precision value of 96.15% and a recall value of 96%. 

File :
RAMA_56201_09011281320014.pdf
RAMA_56201_09011281320014_TURNITIN.pdf
RAMA_56201_09011281320014_0007127410_0216068101_01_front_ref.pdf
RAMA_56201_09011281320014_0007127410_0216068101_02.pdf
RAMA_56201_09011281320014_0007127410_0216068101_03.pdf
RAMA_56201_09011281320014_0007127410_0216068101_04.pdf
RAMA_56201_09011281320014_0007127410_0216068101_05.pdf
RAMA_56201_09011281320014_0007127410_0216068101_06_ref.pdf
RAMA_56201_09011281320014_0007127410_0216068101_07_lamp.pdf