Penerapan Gamma Correction Dalam Peningkatan Pendeteksian Objek Malam Pada Algoritma YOLOv5

Abstract

YOLOv5 (You Only Look Once) is a popular object detection method used in the field of computer vision. YOLOv5 is often used to detect objects in images and videos in real-time with high speed and accuracy. This method is easy to use because it is open-source, so it can be directly used to create a model that fits the object you want to detect. YOLOv5 can easily recognize objects detected during the day, but this method has difficulties when it is made to detect objects at night. With the improvisation of the YOLOv5 method which can accurately detect objects at night, other researchers who wish to conduct research related to object detection at night can use the exact technique to produce more accurate object detection. This study uses the Gamma Correction method by adding a Gamma of 2 so that the trained image dataset becomes bright and YOLOv5 can recognize objects at night more easily. As a result, an improvised technique using Gamma Correction can make YOLOv5 recognize objects and make detections at night more accurately, where the average accuracy obtained before improvisation is 0.846, while after improvisation the results obtained are 0.918. From these average results, it can be stated that the gamma correction method can improve the accuracy results in object detection on YOLOv5