This is another Raspberry Pi motion tracker based on Python, picamera and opencv.
It makes heavily use of the motion blocks generated by GPU of the Raspberry Pi.
Target A crossing event is detected on a GPIO port and a picture of the event is transmitted via nginx to a smart phone for example.
2019-02-27: V0.5 image released today.
2019-02-09: Today I installed a new Python modul which enables me to have a deeper look inside the load balancing.
All people who are updating the software and using versions before 0.5 have to install this additional module from command line with:
sudo apt-get install python-prctl
Currently this is a beta release.
- The object detection is working quiet well in different light conditions.
- The first outdoor tests went very well but there are limits:
- The camera cannot distinguish between birds/bees and planes. All moving things are evaluated.
- moving objects in the turn area can lead to false positives. (grass, bushes, flags, etc)
- The fisheye setup with the V1 camera seems to be the best setup for our purposes. (F3F model air racing)
- If you want to follow up more far away objects (F3B speed for example) the newer V2 camera is the better choice.
- To improve nearby crossing detection the camera could be mounted straight. (Not in 90 degrees as used before)
- Crossing is now in X direction (viewAngle: 0, xCross: 40, yCross: -1)
- V1 camera from Waveshare with fisheye lens (module G); 1280x960 pixels, 42 f/s; full FOV; 192MB GPU memory
- Mode 5 (1280x720p @ 49 f/s) does not center the frames horizontally
- V2 camera with standard lens; 1632x896, 40 f/s; full FOV; 192MB GPU memory.
- 1280x720p @ 62 f/s (FOV is very small)
- In general the V2 camera needs more light than the V1 with the fisheye
- In stormy conditions you need to fix the camera very well. Otherwise a lot of wrong positives are genenrated.
- The new Raspberry Pi 3 Model B Plus is working. (Speed is not improved)
- The web interface supports the most rudimentary stuff to control the camera.
- no video saving so far.
- we have a printed cover available. (see wiki section)
- you can download the V0.5 image here pi-password: Olav01
- The v0.5 image is created on a B Plus.
see FAQ section
see wiki section
- More testing in real conditions is needed.
- create a full automatic setup with embedded Wifi access point. (just power on the device)
- Make libh264decoder Python 3 able and update the source repository
- if possible avoid to decode h264 (started)