3 – 3 HSA Course Outline V3 Demo01 1 V3

On your journey to becoming an expert in computer vision, it will often be up to you to think about how humans reason and interpret information. And then learn techniques to translate that reasoning into code. In this course, we focus on three main areas of computer vision techniques, that are modeled on human understanding. First, we look at the foundational math and programming concepts behind pattern recognition in classification tasks. This section will be all about creating algorithms that can one, isolate important distinguishing information about an object in an image, things like an objects unique shape or color. And two, how do you ignore irrelevant parts of an image, things like a plane background or noise. Second, we’ll learn about deep learning algorithms that have led to state of the art advances in computer vision technology. We’ll cover architectures like region based convolutional neural networks, that identify where an object is in an image. And we’ll talk about models that use recurrent neural networks. This section will be all about applications that aim to reach human levels of scene understanding. Third, we’ll discuss object tracking techniques. Using spatial information gathered over time, you’ll learn about predicting the location of an object and determining its movement. This is an ongoing area of research, especially in the field of autonomous vehicles like self driving cars and drones. I’m really looking forward to covering such a variety of computer vision techniques.

%d 블로거가 이것을 좋아합니다: