Real-time 2D Multi-Person Pose Estimation

WHAT IS IT?

The pose of the human can reveal much about the characteristics and the activity he/she is doing. This work heavily optimizes the OpenPose approach to reach real-time inference on CPU with negligible accuracy drop. It detects a skeleton (which consists of keypoints and connections between them) to identify human poses for every person inside the image. The pose may contain up to 18 key points: ears, eyes, nose, neck, shoulders, elbows, wrists, hips, knees, and ankles. This work can detect multiple persons and their pose in the image.

HOW TO USE?

To run The Inference Script run this command python run.py --image

SAMPLE COMMAND

python run.py --image image/img.jpg | ARGUMENTS | DETAILS | HELP OPTIONS | |---|---|---| | –image | Input Image | Mention the input Image path |

WHAT ARE THE REQUIREMENTS?

To get all the requirements and dependencies installed run the command For GPU - pip install -r gpu_requirements.txt For CPU - pip install -r cpu_requirements.txt