https://github.com/fork123aniket/human-pose-estimation

Implementation for Human Pose Estimation using OpenCV
https://github.com/fork123aniket/human-pose-estimation

body25 coco computer-vision human-pose human-pose-estimation mpii-dataset opencv pose-estimation

Last synced: 3 days ago
JSON representation

Implementation for Human Pose Estimation using OpenCV

• Host: GitHub
• URL: https://github.com/fork123aniket/human-pose-estimation
• Owner: fork123aniket
• License: mit
• Created: 2022-11-26T12:46:09.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2022-11-27T08:37:47.000Z (almost 2 years ago)
• Last Synced: 2023-04-29T09:03:41.806Z (over 1 year ago)
• Topics: body25, coco, computer-vision, human-pose, human-pose-estimation, mpii-dataset, opencv, pose-estimation
• Language: Python
• Homepage:
• Size: 204 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Human Pose Estimation

This repository provides implementation for ***Human Pose Estimation*** that predicts the location of various human keypoints (joints and landmarks) such as elbows, knees, neck, shoulder, hips, chest etc.

## Requirements

- OpenCV

- OpenPose

## Usage

- To download the pre-Trained models, run `sh get_model.sh` command.

- To run pre-Trained model, trained on ***MPII Human Pose*** dataset, on any image, run the following command:-

`python3 human_pose_estimation.py --input  --proto human_pose_proto/mpi/pose_deploy_linevec_faster_4_stages.prototxt --model human_pose_proto/mpi/pose_iter_160000.caffemodel --dataset MPI`.

- To run pre-Trained model, trained on ***COCO*** dataset, on any image, run the following command:-

`python3 human_pose_estimation.py --input  --proto human_pose_proto/coco/deploy_coco.prototxt --model human_pose_proto/coco/pose_iter_440000.caffemodel --dataset COCO`.

- To run pre-Trained model, trained on ***Body_25*** dataset, on any image, run the following command:-

`python3 human_pose_estimation.py --input  --proto human_pose_proto/body_25/body_25_deploy.prototxt --model human_pose_proto/body_25/pose_iter_584000.caffemodel`.

## Results

Following are a few ***human poses*** predicted by the model:-

| Test Image        | Generated Keypoint Skeleton           |

| ------------------- |:----------------------------:|

|  |  |

|  |  |