Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

This Git repo allows to implement the state-of-the-art MaskRCNN algorithm for instance segmentation on the video feed from DJI-Tello drone.

License

NotificationsYou must be signed in to change notification settings

dronefreak/dji-tello-object-detection-segmentation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Implement Real-Time Semantic Segmentation withMask_RCNN.

Requirements

  • Ubuntu 18.04
  • Python 3.6
  • Tensorflow 1.9
  • Keras 2.1.6
  • OpenCV 4.0

The algorithm has been tested on the above mentioned configuration, but I'm pretty sure that other combinations would also work effectively. But please make sure that you have TF/Keras combination as mentioned above. Opencv 3.4 would suffice.

This implementation would work better if you have a GPU in your system and use CUDA-accelerated learning. In a MSI laptop with 1050Ti (4 GB with 768 cuda cores), i5-8220 and 8GB RAM, the FPS obtained is 4.637.

Also, in order to test it on a Tello, make sure that you have the drone turned on and connected to its WiFi network. Once you esecute this code, pressTAB to take-off andBACKSPACE to land. Other manual navigation commands are given in the header of the python code.

Getting Started

Make sure you have installedTelloPy fromhttps://github.com/hanyazou/TelloPy.

Install Dependencies (Not Mentioned Above)

$ sudo -H pip3 install -r requirements.txt$ sudo -H pip3 install av opencv-python$ sudo -H pip3 install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI

Using pre-trained weights for MS COCO

It is includedin {telloCV-masked-rcnn.py} that downloading the pre-trained weightsfor MS COCO.

Run Demonstration

$ python3 telloCV-masked-rcnn.py

Alternatively, you could download the weights file fromhere.

Mask RCNN COCO Object detection and segmentation

About

This Git repo allows to implement the state-of-the-art MaskRCNN algorithm for instance segmentation on the video feed from DJI-Tello drone.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors2

  •  
  •  

Languages


[8]ページ先頭

©2009-2025 Movatter.jp