This is a DeepStream application to demonstrate a human pose estimation pipeline.
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 | |
You will need
To get started, please follow these steps.
$DEEPSTREAM_DIR/sources/apps/sample_apps
.$DEEPSTREAM_DIR/libs
with the ones provided in this repository under bin/
. Please note that these are not inter-compatible across platforms. $ cd deepstream-pose-estimation/
$ sudo make
$ sudo ./deepstream-pose-estimation-app <file-uri> <output-path>
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.
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.