Python: Advanced Guide to Artificial Intelligence

Localizing objects using sliding windows

An intuitive way of localization is to predict several cropped portions of an image with an object. The cropping of the images can be done by moving a window across the image and predicting for every window. The method of moving a smaller window than the image and cropping the image according to window size is called a sliding window. A prediction can be made for every cropped window of the image which is called sliding window object detection. 

The prediction can be done by the deep learning model trained for image classification problems with closely-cropped images. Close cropping means that only one object will be found in the whole image. The movement of the window has to be uniform across the ...