A Unix, Windows, Raspberry Pi Object Speed Camera using python, opencv, video streaming, motion tracking. Includes a Standalone Web Server Interface, Image Search using opencv template match and a whiptail Admin Menu Interface Includes picam and webcam Plugins for motion track security camera configuration including rclone sync script. watch-app allows remotely controller camera configuration from a remote storage service name. Uses sqlite3 and gnuplot for reporting. Recently added openalpr license plate reader support.
Sometimes there are so many events that MO_TRACK_EVENT_COUNT is reached very fast. Because of this a a new 'track' is started, detecting the vehicle a second time.
Increasing MO_TRACK_EVENT_COUNT helps, but then sometimes (when a car is moving to slow?) the MO_TRACK_EVENT_COUNT is not reached, thus not detecting the car.
Is there something I can do about this?
I just started playing around with this yesterday, so I'm still in the process of tweaking everything.
Thanks for the great app by the way! It seems to work very nice out-of-the-box. Our street's limit is 20kph and we have the feeling nobody adheres to it, so I'm trying to gather some data to confirm this.
Sometimes there are so many events that
MO_TRACK_EVENT_COUNTis reached very fast. Because of this a a new 'track' is started, detecting the vehicle a second time.Increasing
MO_TRACK_EVENT_COUNThelps, but then sometimes (when a car is moving to slow?) theMO_TRACK_EVENT_COUNTis not reached, thus not detecting the car.Is there something I can do about this?
I just started playing around with this yesterday, so I'm still in the process of tweaking everything.
Thanks for the great app by the way! It seems to work very nice out-of-the-box. Our street's limit is 20kph and we have the feeling nobody adheres to it, so I'm trying to gather some data to confirm this.