The “in the pipeline” blog also contains the “things I won’t work with” section (https://blogs.sciencemag.org/pipeline/archives/category/thin...) which is one of the most awesome reads ever, at least for people with some practical experience of an organic chemistry lab.
Working as a chemist for a while, one tends to develop an explosion sense. Because it is never your stuff blowing up, but rather the postdoc behind you dumped his peroxide waste into the organic waste bottle or whatever and you're not looking at it.
There's a bunch of very subtle hisses,"stretches", gentle little clinks, "gas expansion into a closed container" that all seem to indicate an explosion is in progress.
Personally, I will pre-consciously teleport out the room when this happens. After leaving the field for more lucrative sofware stuff, it has embarrassed me a few times and saved my skin a few times (shoddy LP cylinder igniting, low pressure plastics getting attached to a soda stream carbonator etc)
Setting up motion is easy enough if you have some scripting skills - a lot easier than the opencv approach in the article. There are articles online using motion with raspberry pi and a USB webcam to do the sort thing described in the article (eg http://m.instructables.com/id/Raspberry-Pi-remote-webcam/).