Nvidia Jetson Body Pose Estimation with posenet
more info
https://microcontrollerkits.blogspot....
PoseNet Model : Pose-ResNet18-Body
KeyPoints : 18
Performance Result
Image
[image] saved ‘out.jpg' (1920x1080, 3 channels)
[TRT] ------------------------------------------------
[TRT] Timing Report networks/Pose-ResNet18-Body/pose_resnet18_body.onnx
[TRT] ------------------------------------------------
[TRT] Pre-Process CPU 0.08505ms CUDA 0.75511ms
[TRT] Network CPU 141.51538ms CUDA 140.91484ms
[TRT] Post-Process CPU 11.97670ms CUDA 11.82979ms
[TRT] Visualize CPU 34.30075ms CUDA 34.65588ms
[TRT] Total CPU 187.87788ms CUDA 188.15562ms
[TRT] ------------------------------------------------
Video 1280x720 MP4
14 -17 fps
What is Pose Estimation and 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 are provided for human body and hand pose estimation that are capable of detecting multiple people per frame.
The poseNet 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 can be used from Python and C++.
สอบถาม :
อดุลย์ นันทะแก้ว 081-6452400
LINE : adunnan
email : [email protected]
FaceBook : / adun.nantakaew
Page : / softpowergroup
Web Blog : http://raspberrypi4u.blogspot.com/
Web Blog : http://microcontrollerkits.blogspot.com/
WebSite : https://softpower.tech