CHAPTER 8Pose Detection
“Software is eating the world, but AI is going to eat software.”
—Jensen Huang (cofounder and CEO of Nvidia)
8.1 Introduction
Pose detection, also called human pose detection or human pose estimation, is a hot research topic that has attracted the attention of the computer vision community for the past few decades. The key to pose detection is to detect and locate human joints, also known as keypoints in images or videos, such as heads, necks, shoulders, hips, elbows, wrists, knees, ankles, and so on. The pose estimation problem is often referred to as the perspective-n-point problem, in which the goals are to find the pose of an object with a calibrated camera and to find the locations of n 3D points on the object and the corresponding 2D projections in the image.
With pose detection, you can do many cool things, such as recognizing people's activities, teaching people online (sports, workouts, yoga), and gaming. During the 2020 COVID-19 pandemic, there was a rise of yoga apps that use pose detection to help teach people yoga online.
In this chapter, we will first show you how to detect and recognize hand gestures and, related to that, sign language. Then we will introduce body pose detections and, finally, human activity recognition (HAR).
The following are ...
Get Artificial Intelligence Programming with Python now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
