All Projects → PJunhyuk → People Counting Pose

PJunhyuk / People Counting Pose

Licence: apache-2.0
Odin: Pose estimation-based tracking and counting of people in videos

Projects that are alternatives of or similar to People Counting Pose

Pytorch pose proposal networks
Pytorch implementation of pose proposal networks
Stars: ✭ 93 (-36.73%)
Mutual labels:  pose-estimation
Cpm
Convolutional Pose Machines in TensorFlow
Stars: ✭ 115 (-21.77%)
Mutual labels:  pose-estimation
Paz
Hierarchical perception library in Python for pose estimation, object detection, instance segmentation, keypoint estimation, face recognition, etc.
Stars: ✭ 131 (-10.88%)
Mutual labels:  pose-estimation
Fingerpose
Finger pose classifier for hand landmarks detected by TensorFlow.js handpose model
Stars: ✭ 102 (-30.61%)
Mutual labels:  pose-estimation
Aruco tracker
Aruco Markers for pose estimation
Stars: ✭ 111 (-24.49%)
Mutual labels:  pose-estimation
Tf2 Mobile 2d Single Pose Estimation
💃 Pose estimation for iOS and android using TensorFlow 2.0
Stars: ✭ 122 (-17.01%)
Mutual labels:  pose-estimation
Dataset utilities
NVIDIA Dataset Utilities (NVDU)
Stars: ✭ 90 (-38.78%)
Mutual labels:  pose-estimation
Gccpm Look Into Person Cvpr19.pytorch
Fast and accurate single-person pose estimation, ranked 10th at CVPR'19 LIP challenge. Contains implementation of "Global Context for Convolutional Pose Machines" paper.
Stars: ✭ 137 (-6.8%)
Mutual labels:  pose-estimation
Iros20 6d Pose Tracking
[IROS 2020] se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains
Stars: ✭ 113 (-23.13%)
Mutual labels:  pose-estimation
Smplpp
C++ Implementation of SMPL: A Skinned Multi-Person Linear Model
Stars: ✭ 126 (-14.29%)
Mutual labels:  pose-estimation
Nuitrack Sdk
Nuitrack™ is a 3D tracking middleware developed by 3DiVi Inc.
Stars: ✭ 103 (-29.93%)
Mutual labels:  pose-estimation
Human Pose Estimation From Rgb
Human Pose Estimation from RGB Camera - The repo
Stars: ✭ 108 (-26.53%)
Mutual labels:  pose-estimation
Posefromshape
(BMVC 2019) PyTorch implementation of Paper "Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objects"
Stars: ✭ 124 (-15.65%)
Mutual labels:  pose-estimation
Eao Slam
[IROS 2020] EAO-SLAM: Monocular Semi-Dense Object SLAM Based on Ensemble Data Association
Stars: ✭ 95 (-35.37%)
Mutual labels:  pose-estimation
Tensorflow realtime multi Person pose estimation
Multi-Person Pose Estimation project for Tensorflow 2.0 with a small and fast model based on MobilenetV3
Stars: ✭ 129 (-12.24%)
Mutual labels:  pose-estimation
Awesome Computer Vision
Awesome Resources for Advanced Computer Vision Topics
Stars: ✭ 92 (-37.41%)
Mutual labels:  pose-estimation
Chainer Pose Proposal Net
Chainer implementation of Pose Proposal Networks
Stars: ✭ 119 (-19.05%)
Mutual labels:  pose-estimation
Posenet Coreml
I checked the performance by running PoseNet on CoreML
Stars: ✭ 143 (-2.72%)
Mutual labels:  pose-estimation
Human Falling Detect Tracks
AlphaPose + ST-GCN + SORT.
Stars: ✭ 135 (-8.16%)
Mutual labels:  pose-estimation
3dpose gan
The authors' implementation of Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations
Stars: ✭ 124 (-15.65%)
Mutual labels:  pose-estimation

Odin

Pose estimation-based tracking and counting of people in videos

Demo

Demo on YouTube
Paper Abstract

Usage

Uses Docker

Pull docker image

$ docker pull jgravity/tensorflow-opencv:odin
$ docker run -it --name odin jgravity/tensorflow-opencv:odin bin/bash

Download/Install code

# git clone https://github.com/PJunhyuk/people-counting-pose
# cd people-counting-pose
# chmod u+x ./compile.sh && ./compile.sh && cd models/coco && chmod u+x download_models_wget.sh && ./download_models_wget.sh && cd -

Download sample videos in testset

# cd testset && chmod u+x ./download_testset_wget.sh && ./download_testset_wget.sh && cd -

Tracking people

# python video_tracking.py -f '{video_file_name}'

Qualified supporting video type: mov, mp4
You have to put target video file in ./testset folder

Arguments

-f, --videoFile = Path to Video File
-w, --videoWidth = Width of Output Video
-o, --videoType = Extension of Output Video

Example
# python video_tracking.py -f 'test_video_01f.mov'

Check results

> docker cp odin:/people-counting-pose/testset/{video_file_name} ./

Just get pose of people (without tracking)

# python video_pose.py -f '{video_file_name}'

Qualified supporting video type: mov, mp4

Dependencies

Use Docker jgravity/tensorflow-opencv,

or install

  • python 3.5.3
  • opencv 3.1.0
  • jupyter 4.2.1
  • git 2.1.4
  • tensorflow 1.3.0
  • pip packages
    • scipy 0.19.1
    • scikit-image 0.13.1
    • matplotlib 2.0.2
    • pyYAML 3.12
    • easydict 1.7
    • Cython 0.27.1
    • munkres 1.0.12
    • moviepy 0.2.3.2
    • dlib 19.7.0
    • imageio 2.1.2

Results (time required)

Check results_log

Reference

Test dataset

Citation

@inproceedings{insafutdinov2017cvpr,
    title = {ArtTrack: Articulated Multi-person Tracking in the Wild},
    booktitle = {CVPR'17},
    url = {http://arxiv.org/abs/1612.01465},
    author = {Eldar Insafutdinov and Mykhaylo Andriluka and Leonid Pishchulin and Siyu Tang and Evgeny Levinkov and Bjoern Andres and Bernt Schiele}
}

@article{insafutdinov2016eccv,
    title = {DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model},
    booktitle = {ECCV'16},
    url = {http://arxiv.org/abs/1605.03170},
    author = {Eldar Insafutdinov and Leonid Pishchulin and Bjoern Andres and Mykhaylo Andriluka and Bernt Schiele}
}

Code

pose-tensorflow - Human Pose estimation with TensorFlow framework
object-tracker - Object Tracker written in Python using dlib and OpenCV

LICENCE

Apache License 2.0

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].