BlazePose: On-device Real-time Body Pose tracking
BlazePose: On-device Real-time Body Pose tracking
复制标题
BlazePose：设备上实时身体姿势跟踪
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Matthias Grundmann
中科院分区：
文献类型：
--
作者：
Valentin Bazarevsky;Ivan Grishchenko;Karthik Raveendran;Tyler Lixuan Zhu;Fan Zhang;Matthias Grundmann
我们提出了BlazePose，这是一种用于人体姿势估计的轻量级卷积神经网络架构，专为移动设备上的实时推理而定制。在推理过程中，网络为一个人生成33个身体关键点，并在Pixel 2手机上以每秒30帧以上的速度运行。这使得它特别适合于实时用例，如健身跟踪和手语识别。我们的主要贡献包括一个新的身体姿势跟踪解决方案和一个轻量级的身体姿势估计神经网络，它使用热图和回归到关键点坐标。
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.