pouyan
/
kinect
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
kinect/codes/Azure-Kinect-Samples/body-tracking-samples/offline_processor
History
davoudn 5986417fda reorganising folders. 2024-03-06 21:35:53 +03:30
..
CMakeLists.txt reorganising folders. 2024-03-06 21:35:53 +03:30
README.md reorganising folders. 2024-03-06 21:35:53 +03:30
main.cpp reorganising folders. 2024-03-06 21:35:53 +03:30
offline_processor.sln reorganising folders. 2024-03-06 21:35:53 +03:30
offline_processor.vcxproj reorganising folders. 2024-03-06 21:35:53 +03:30
offline_processor.vcxproj.filters reorganising folders. 2024-03-06 21:35:53 +03:30
packages.config reorganising folders. 2024-03-06 21:35:53 +03:30

README.md

Azure Kinect Body Tracking OfflineProcessor Sample

Introduction

The Azure Kinect Body Tracking OfflineProcessor sample demonstrates how to playback a recording Azure Kinect MKV file, run through the body tracking SDK and store the body tracking results in a json file.

Notice: the current implementation is not the most efficient way to process a recording file offline. It simply synchronously pushes and pops the capture to/from the tracker queue. To achieve the best performance, you would need to create separate reader thread and process thread. And keep pushing new frames to the tracker without waiting for the k4abt_pop_result to return successfully.

Usage Info

offline_processor.exe <input_mkv_file> <output_json_file>