-
Notifications
You must be signed in to change notification settings - Fork 172
Motion Detection
Moe edited this page Feb 26, 2017
·
16 revisions
To use a Plugin please refer to the Plugins page
Name | Type | Description | Warnings |
stemkoski Motion Detector | Node.js, shinobi-stemkoski.js | This is a method for reading differences in frames with the node-canvas. The method was made by @stemkoski on github, hence the name. | Region Detector does not seem to work correctly. Full frame detection works. |
OpenCV Object Tracker | Node.js, shinobi-opencv.js | This is an object tracker interfaced through a Node.js wrapper. | Frame input is limited to 1 fps or you will get Segmentation errors causing the plugin to crash. |
OpenCV Object Tracker | Python, shinobi-opencv.py | An attempt at copying the the node.js version by moeiscool. | Currently does not work. Process will not stay alive for requests. |
CCV.js Object Tracker | Node.js, shinobi-ccv.js | Currently only a face detector. The current cascade can be replaced. | Uses a lot of CPU power, like a lot. |
Not everyone uses motion detection or object tracking and the libraries required can be bothersome to install based on the OS. For example if I make shinobi-opencv.js a feature then everyone will be required to install OpenCV 2.4 just to use basic features in Shinobi. This also allows us to swap the plugin with a custom one or run it on another machine entirely. Sharing the work between multiple machines can be a great way to optimize performance.