RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose

03/13/2023
by   Tao Jiang, et al.
0

Recent studies on 2D pose estimation have achieved excellent performance on public benchmarks, yet its application in the industrial community still suffers from heavy model parameters and high latency. In order to bridge this gap, we empirically explore key factors in pose estimation including paradigm, model architecture, training strategy, and deployment, and present a high-performance real-time multi-person pose estimation framework, RTMPose, based on MMPose. Our RTMPose-m achieves 75.8 Intel i7-11700 CPU and 430+ FPS on an NVIDIA GTX 1660 Ti GPU, and RTMPose-l achieves 67.0 RTMPose's capability in critical real-time applications, we also report the performance after deploying on the mobile device. Our RTMPose-s achieves 72.2 AP on COCO with 70+ FPS on a Snapdragon 865 chip, outperforming existing open-source libraries. Code and models are released at https://github.com/open-mmlab/mmpose/tree/1.x/projects/rtmpose.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset