Data Augmentation Using Brightness and Darkness to Enhance the Performance of YOLO7 Object Detection Algorithm

The object detection field depends on various techniques for duplicating the dataset without adding additional images. The data augmentation is the recommended technique that can be used to duplicate the dataset. In this paper, we trained YOLOv7 with a dataset that is part of the Open Images dataset that has 8,600 images with four classes (Car, Bus, Motorcycle, and Person). We used two different data augmentations techniques for duplicates and improvement of our dataset, and we compared the result of the proposed augmented data using brightness and darkness with the result of the original data. The evaluation result for the augmented data gives a promising result for every object, and every kind of data augmentation gives a different improvement. The mAP@.5 of all classes was 76%, and F1-score was 74%. The proposed improved methods increased the mAP@.5 value by +13% and F1-score by +11%.