Mastering Computer Vision with TensorFlow 2.x

The concept of IOU

IOU is an object detection evaluation metric based on the degree of overlap between the predicted bounding box and the ground truth bounding box (hand labeled). Let's have a look at the following derivative of IOU:

The following image illustrates IOU, showing the predicted and ground truth bounding box of a large van:

In this case, the IOU value is close to around 0.9 as the overlap area is very high. If the two bounding boxes do not overlap, then the IOU value is 0, and if they do overlap by 100%, then the IOU value is ...