Raspberry PI-TIMOLO ( PI-TImelapse, MOtion, LOwLight ) uses RPI picamera and OpenCV for Remote Headless Security Monitoring using Motion Tracking, Rclone Auto Sync files with remote storage services. Auto Twilight Transitions and Low Light Camera Settings. Panoramic images using PanTiltHat and More. This project is featured on GitHub Awesome software.
MIT License
548
stars
101
forks
source link
pi-timolo release 7.0 Now uses OpenCV Motion Tracking #67
After looking at my speed camera code and having issues with pi-timolo previous motion detection false positives, I decided to change pi-timolo to use OpenCV and a simplified Motion Tracking. You can tune using track length trigger and min area. This code uses pi-camera streaming. I will look at adding web cam support but thought I would release this version first. I recommend you rename the previous pi-timolo and do a fresh install of vers 7.0.
I have pi-timolo.py with a single core RPI and it works just fine. I have trees moving at the front of my house and did get a few false positives but otherwise performs very well. I have added a QuickPic feature to capture steam images directly so the stream does not have to be stopped and restarted to take a full pi-camera image. QuickPic is a smaller image size but still good enough. I have also left trackingInfo setting to True, but I recommend you turn this off to reduce verbose logging.
Your comments would be greatly appreciated.
Thanks Claude ...
After looking at my speed camera code and having issues with pi-timolo previous motion detection false positives, I decided to change pi-timolo to use OpenCV and a simplified Motion Tracking. You can tune using track length trigger and min area. This code uses pi-camera streaming. I will look at adding web cam support but thought I would release this version first. I recommend you rename the previous pi-timolo and do a fresh install of vers 7.0.
I have pi-timolo.py with a single core RPI and it works just fine. I have trees moving at the front of my house and did get a few false positives but otherwise performs very well. I have added a QuickPic feature to capture steam images directly so the stream does not have to be stopped and restarted to take a full pi-camera image. QuickPic is a smaller image size but still good enough. I have also left trackingInfo setting to True, but I recommend you turn this off to reduce verbose logging.
Your comments would be greatly appreciated. Thanks Claude ...