Pose estimation outputs a skeleton of keypoints for each person, frame by frame. From those joint coordinates a product can count reps, analyse a golf swing, or recognise gestures. MediaPipe Pose, RTMPose, and ViTPose are common engines.

Book cover: AI for Video, Volume 6 of the Fora Soft Video Engineering Handbook

The book · Volume 6 of 7

AI for Video: A Complete Guide to Intelligence in Video Products: From Models and Inference to Computer Vision, Speech, Search, and Generative Video

Pose estimation drives rep counters, swing analysis and gestures, and jitter between frames is what makes them feel unreliable. This volume covers pose estimation in depth: keypoints and skeletons, MediaPipe Pose, RTMPose and ViTPose, tracking poses over time, and on-device deployment. Written by Nikolay Sapunov, CEO at Fora Soft.

Read it on Amazon →Kindle & paperback · Fora Soft Video Engineering Handbook

Need pose estimation accurate enough for fitness or sports analysis?

Send us sample movements, and we will benchmark pose estimation models on accuracy, jitter and frame rate on your target devices. 250+ video products shipped since 2005.

Book a 30-min call →WhatsApp →Email us →