8000 GitHub - Shreyas-NR/falldetection: Master's Thesis: Stereo Vision-Based Fall Prediction and Detection using Human Pose Estimation on the AMD Kria K26 SOM
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Master's Thesis: Stereo Vision-Based Fall Prediction and Detection using Human Pose Estimation on the AMD Kria K26 SOM

License

Notifications You must be signed in to change notification settings

Shreyas-NR/falldetection

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

falldetection

Stereo Vision-Based Approach

Click here for details.

Wearables

Using lattice iCE40 UltraPlus and caffe CBSR strucutre

Caffe

  • CBSR
  • Number output 16 or 64
  • Bias term
  • TP,FP,TN,FN
  • Compare output
  • kernel_size

ICE40UP

  • Run on board
  • LED show different state
  • LED show machine learning result(Important)
  • Feed data from csv
  • Feed data from sensor

Tensorflow

  • Which structure works
  • Restrictions

Board different

The caffe and tensorflow has different requirement when run on MDP and ICE40 development board

Paticipant

1/200

About

Master's Thesis: Stereo Vision-Based Fall Prediction and Detection using Human Pose Estimation on the AMD Kria K26 SOM

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 88.5%
  • C++ 9.6%
  • Shell 1.9%
0