Skip to content
This repository has been archived by the owner on Jan 23, 2021. It is now read-only.
/ DTP-Source Public archive

Drone Tracking Program (DTP)

Notifications You must be signed in to change notification settings

justinwyh/DTP-Source

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

29 Commits
 
 
 
 
 
 
 
 

Repository files navigation

DTP-Source

FYP: Drone Tracking Program (DTP)

This is a final deliverable of a FYP.

Requirements:

  1. Windows 10
  2. Nvidia GPU that supports CUDA 10.1
  3. A drone that is compatile with the DJI Windows SDK. Please check all supported drones here.

Installation

  1. Download DTP_Data folder and the DTP program on the Github Release page.
  2. Run requirements.bat under DTP_Data. Please visit here if you encounter any installation issues.
  3. Install the DTP program by right-clicking the DTP_Package_1.0.1.0_Test\Add-AppDevPackage.ps1 in the release app package.
  4. Replace "from pysot." with "from PySOT.pysot" and replace "from toolkit." with "from PySOT.toolkit." in all Python files under DTP_Data\Source\PySOT
  5. Download the pretrained PySOT models here and place them under DTP_Data\Source\PySOT\experiments.
  6. Start the program and update the DTP data path in the program.

Build DTP from scratch

Please reference here and then download the SDK here.

References

https://github.com/STVIR/pysot/

https://github.com/jorge-pessoa/pytorch-msssim