Humans use their eyes and their brains to see and visually sense the world around them. Computer vision is the science that aims to give a similar, if not better, capability to a machine or computer.
Computer vision is concerned with the automatic extraction, analysis and understanding of useful information from a single image or a sequence of images. It involves the development of a theoretical and algorithmic basis to achieve automatic visual understanding.
In this training we will cover object detection, a computer vision task of localizing objects in images/videos, and classifying them. In particular, we will do transfer learning and use the pytorch FasterRcnn implementation.
- Different approaches to object detection
- Understanding how to create a custom object detection
- Understanding how object detection algorithms come up with a prediction (Anchor boxes, bounding boxes, non maximum suppression)
A basic idea of convolutional neural networks. Some experience with Pytorch