GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → NVIDIA-AI-IOT → Deepstream_pose_estimation

NVIDIA-AI-IOT / Deepstream_pose_estimation

Licence: other
This is a sample DeepStream application to demonstrate a human pose estimation pipeline.

Labels

computer-visionreal-timehuman-pose-estimation

Projects that are alternatives of or similar to Deepstream pose estimation

FastPose
pytorch realtime multi person keypoint estimation
Stars: ✭ 36 (-78.57%)
Mutual labels:  real-time, human-pose-estimation
Openpose train
Training repository for OpenPose
Stars: ✭ 381 (+126.79%)
Mutual labels:  human-pose-estimation, real-time
Pytorch realtime multi Person pose estimation
Pytorch version of Realtime Multi-Person Pose Estimation project
Stars: ✭ 205 (+22.02%)
Mutual labels:  human-pose-estimation, real-time
Openpose unity plugin
OpenPose's Unity Plugin for Unity users
Stars: ✭ 446 (+165.48%)
Mutual labels:  human-pose-estimation, real-time
Keras realtime multi Person pose estimation
Keras version of Realtime Multi-Person Pose Estimation project
Stars: ✭ 728 (+333.33%)
Mutual labels:  human-pose-estimation, real-time
Shelfnet Human Pose Estimation
Fast and accurate Human Pose Estimation using ShelfNet with PyTorch
Stars: ✭ 95 (-43.45%)
Mutual labels:  human-pose-estimation, real-time
Lightweight Human Pose Estimation 3d Demo.pytorch
Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.
Stars: ✭ 331 (+97.02%)
Mutual labels:  human-pose-estimation, real-time
Openpose
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Stars: ✭ 22,892 (+13526.19%)
Mutual labels:  human-pose-estimation, real-time
Trt pose
Real-time pose estimation accelerated with NVIDIA TensorRT
Stars: ✭ 525 (+212.5%)
Mutual labels:  human-pose-estimation, real-time
Lightweight Human Pose Estimation.pytorch
Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.
Stars: ✭ 958 (+470.24%)
Mutual labels:  human-pose-estimation, real-time
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 (-18.45%)
Mutual labels:  human-pose-estimation, real-time
Signalr.orleans
SignalR backend based on Orleans.
Stars: ✭ 156 (-7.14%)
Mutual labels:  real-time
Awesome Human Pose Estimation
A collection of awesome resources in Human Pose estimation.
Stars: ✭ 2,022 (+1103.57%)
Mutual labels:  human-pose-estimation
Optical Flow Filter
A real time optical flow algorithm implemented on GPU
Stars: ✭ 146 (-13.1%)
Mutual labels:  real-time
Hedgedoc
HedgeDoc - The best platform to write and share markdown.
Stars: ✭ 2,498 (+1386.9%)
Mutual labels:  real-time
Keraspersonlab
Keras-tensorflow implementation of PersonLab (https://arxiv.org/abs/1803.08225)
Stars: ✭ 163 (-2.98%)
Mutual labels:  human-pose-estimation
Vnect
Real-time 3D human pose estimation, implemented by tensorflow
Stars: ✭ 157 (-6.55%)
Mutual labels:  human-pose-estimation
Cdcl Human Part Segmentation
Repository for Paper: Cross-Domain Complementary Learning Using Pose for Multi-Person Part Segmentation (TCSVT20)
Stars: ✭ 143 (-14.88%)
Mutual labels:  human-pose-estimation
Arepl Vscode
program python in real-time
Stars: ✭ 142 (-15.48%)
Mutual labels:  real-time
Real Time Ml Project
A curated list of applied machine learning and data science notebooks and libraries across different industries.
Stars: ✭ 143 (-14.88%)
Mutual labels:  real-time
View All Similar Projects ➔

DeepStream Human Pose Estimation

Human pose estimation is the computer vision task of estimating the configuration (‘the pose’) of the human body by localizing certain key points on a body within a video or a photo. The following application serves as a reference to deploy custom pose estimation models with DeepStream 5.0 using the TRTPose project as an example.

A detailed deep-dive NVIDIA Developer blog is available here.

Input Video Source Output Video

Prerequisites

You will need

  1. DeepStreamSDK 5.0
  2. CUDA 10.2
  3. TensorRT 7.x

Getting Started:

To get started, please follow these steps.

  1. Install DeepStream on your platform, verify it is working by running deepstream-app.
  2. Clone the repository preferably in $DEEPSTREAM_DIR/sources/apps/sample_apps.
  3. Download the TRTPose model, convert it to ONNX using this export utility, and set its location in the DeepStream configuration file.
  4. Replace the OSD binaries (x86 or Jetson) in $DEEPSTREAM_DIR/libs with the ones provided in this repository under bin/. Please note that these are not inter-compatible across platforms.
  5. Compile the program
 $ cd deepstream-pose-estimation/
 $ sudo make
 $ sudo ./deepstream-pose-estimation-app <file-uri> <output-path>
  1. The final output is stored in 'output-path' as Pose_Estimation.mp4

NOTE: If you do not already have a .trt engine generated from the ONNX model you provided to DeepStream, an engine will be created on the first run of the application. Depending upon the system you’re using, this may take anywhere from 4 to 10 minutes.

For any issues or questions, please feel free to make a new post on the DeepStreamSDK forums.

References

Cao, Zhe, et al. "Realtime multi-person 2d pose estimation using part affinity fields." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017.

Xiao, Bin, Haiping Wu, and Yichen Wei. "Simple baselines for human pose estimation and tracking." Proceedings of the European Conference on Computer Vision (ECCV). 2018.

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].