Use Jetson as a ground station for FPV enthusiasts.
Main features as follows:
- FPV features
- MSPOSD for ground station
- video-viewer
- Adaptive wireless link
- Jetson video analysis
- detectnet for object detection
- segnet for segmentation
- posenet for pose estimation
- imagenet for image recognition
- yolo for object detection
- Real time video stabilizer
- DeepStream analysis
- ByteTrack
finish main features that planned to implementextension commands for video-viewer/imagenet/detectnet/segnet/posenet- adaptive Open IPC link management
- stabilizer doesn't seem to be that stabilized
optimize yolo performance- follow me Rover drive
add Ultralytics YOLO11 on NVIDIA Jetson using DeepStream SDK and TensorRTadd DeepStream analysisadd ByteTrack analysis- [Request] Add RTP H265 support #1
- optimize performance, especially AI model/tracking algorithm etc.
- improve FPS rate over/up to 60FPS when dsyolo using BYTETrack
All these fun points serve as potential starting points for deepening the project.
- How to install the software?
- How to use the software?
- How to optimize YOLO performance?
- How to work with OpenIPC camera?
- wfb-wifibroadcast@svpcom
- msposd@tipoman9 for betalight/inav/ardupilot
- wfb-stabilizer@ejowerks
- wfb-stabilizer@tipoman9
- video-viewer@dusty-nv
- jetson-inference@dusty-nv
- jetson-yolo from nvidia
- DeepStream-Yolo@marcoslucianops
- deepstream_python_apps
- Ultralytics YOLO11
- OpenIPC for IP camera
- ByteTrack, simple, fast and strong multi-object tracker