comeon
December 28, 2022, 10:32am
1
posetnet model in jetson-inference can use in deepstream?
<img src="https://github.com/dusty-nv/jetson-inference/raw/master/docs/images/deep-vision-header.jpg" width="100%">
<p align="right"><sup><a href="segnet-camera-2.md">Back</a> | <a href="depthnet.md">Next</a> | </sup><a href="../README.md#hello-ai-world"><sup>Contents</sup></a>
<br/>
<sup>Pose Estimation</sup></s></p>
# Pose Estimation with PoseNet
Pose estimation consists of locating various body parts (aka keypoints) that form a skeletal topology (aka links). Pose estimation has a variety of applications including gestures, AR/VR, HMI (human/machine interface), and posture/gait correction. [Pre-trained models](#pre-trained-pose-estimation-models) are provided for human body and hand pose estimation that are capable of detecting multiple people per frame.
<img src="https://github.com/dusty-nv/jetson-inference/raw/dev/docs/images/posenet-0.jpg">
The [`poseNet`](../c/poseNet.h) object accepts an image as input, and outputs a list of object poses. Each object pose contains a list of detected keypoints, along with their locations and links between keypoints. You can query these to find particular features. [`poseNet`](../c/poseNet.h) can be used from [Python](https://rawgit.com/dusty-nv/jetson-inference/dev/docs/html/python/jetson.inference.html#poseNet) and [C++](../c/poseNet.h).
As examples of using the `poseNet` class, we provide sample programs for C++ and Python:
- [`posenet.cpp`](../examples/posenet/posenet.cpp) (C++)
- [`posenet.py`](../python/examples/posenet.py) (Python)
These samples are able to detect the poses of multiple humans in images, videos, and camera feeds. For more info about the various types of input/output streams supported, see the [Camera Streaming and Multimedia](aux-streaming.md) page.
## Pose Estimation on Images
show original
yingliu
December 28, 2022, 12:35pm
2
The posenet example in jetson-inference is based on TensorRT API, which doesn’t use deepstream framework.
There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks
Seems the model is an ONNX model. It can be used in DeepStream, you need to customize the preprocess and postprocess with DeepStream APIs by yourself. An easy way is to use the pose model provided by deepstream_tao_apps/apps/tao_others/deepstream-bodypose2d-app at master · NVIDIA-AI-IOT/deepstream_tao_apps (github.com)
system
January 31, 2023, 3:22am
6
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.