Continuing from the previous section, this article will delve into how to utilize YOLOv8 to train a custom dataset annotated by Label Studio, as well as how to employ Python to save the inferred video results locally.
The Otsu's method was proposed in 1979, which segmented images by maximizing variance between classes. In other words, the Otsu's method is a nonparametric segmentation method that divides an image into different regions based on the intensity of the pixels. This article will introduce the Otsu's method in two sections. First, we will understand the principles of the Otsu's method by reviewing the mathematical formulas in the literature. Finally, we will implement the details using Matlab/Python.