The convolutional sliding windows, although computationally much more efficient, still has the problem of detecting bounding boxes accurately, since the boxes don’t align with the sliding windows and the object shapes also tend to be different. The YOLO algorithm overcomes this limitation by dividing a training image into grids and assigning an object to a grid if and only if the center of the object falls inside the grid. This way, each object in a training image can get assigned to exactly one grid and then the corresponding bounding box is represented by the coordinates relative to the grid.
In the test images, multiple adjacent grids may think that an object actually belongs to them. In order to resolve this, the intersection ...