# ZheC/Realtime_Multi-Person_Pose_Estimation

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

Repository: https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation
Canonical: https://ross.abutalabs.com/products/realtime_multi-person_pose_estimation
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Topics: human-pose-estimation, realtime, caffe, human-behavior-understanding, deep-learning, computer-vision, matlab, python, cpp11, cvpr-2017
Last push: 2020-03-21T13:01:08+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3551, "days_push": 2356, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5123, forks 1351 (observed 2026-08-28T04:09:10.923912+00:00)

## What it is
Reference implementation of the CVPR'17 paper 'Realtime Multi-Person Pose Estimation', a bottom-up approach that detects keypoints for multiple people in real time without a person detector. Built on Caffe with Python/Matlab/C++ tooling, it is the original codebase behind OpenPose.

## Use cases
- detect human body keypoints in images
- estimate poses of multiple people in realtime video
- reproduce the CVPR 2017 OpenPose paper results
- train a multi-person pose estimation model on COCO keypoints
- run pose estimation demos on webcam footage

## When to choose
- you need the original reference implementation of the CVPR'17 bottom-up pose estimation method
- you are doing research on multi-person pose estimation and want the paper's exact code
- you want to study or port the Caffe-based OpenPose predecessor

## When to avoid
- you need a production-ready or actively maintained pose estimation library
- you prefer modern frameworks like PyTorch or TensorFlow - use the community reimplementations or OpenPose instead
- you need permissive licensing - the license is non-standard

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, deep-learning, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python, cpp, windows
- tags: human-pose-estimation, openpose, caffe, realtime, cvpr-2017, keypoint-detection, research-code, linux, macos

## Member repositories
- ZheC/Realtime_Multi-Person_Pose_Estimation (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:10.923912+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:02:05.096148+00:00, confidence not recorded.
  - readme: https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation (fetched 2026-08-28T04:09:10.923912+00:00, sha f577087d70a0)
- Data as of 2026-08-30T08:39:29.467469+00:00.