Year: 2020
Type: preprint
Abstract: We present BlazePose, a lightweight convolutional neural network architecture for human pose estimation that is tailored for real-time inference on mobile devices. During inference, the network produces 33 body keypoints for a single person and runs at over 30 frames per second on a Pixel 2 phone. This makes it particularly suited to real-time use cases like fitness tracking and sign language recognition. Our main contributions include a novel body pose tracking solution and a lightweight body pose estimation neural network that uses both heatmaps and regression to keypoint coordinates.
Source: arXiv (Cornell University)
Authors: Bazarevsky, Valentin, Grishchenko, Ivan, Raveendran, Karthik, Zhu, Tyler, Zhang, Fan, Grundmann, Matthias
Institution: Google (United States)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3036422827