Skip to main content

A mouse in the house : Webcam motion detection



We have a mouse in the house. I wanted to have the little intruder on camera. I dug out the old webcam and started to google for webcam motion detection software. Unfortunately a free but closed source program (Yawcam) won over a open source one (Dorgem). You can see the results in the video above.

The mouse makes its appearances at 3:00am, 3:50am and 5:26am. I forgot to add in time stamps to the images, but Yawcam can do that.

Dorgem was not satisfactory because I couldn't get motion detection to work. There was no way to adjust the threshold. I set it to take shots every 1s and it saved images with time stamped filenames (and a time stamp on the image itself) but the motion detection did not work. Perhaps the CCD noise kept triggering the software, I just got image dumps regularly at the 1s rate. [Help page on how to use Dorgem for motion detection]

Yawcam is more professionally designed. It has a motion detection preview pane where you can adjust thresholds or have the software adjust it automatically. The software highlights in real-time parts of the image where it detects motion. I found the auto-set tolerance level (20%) to be a bit high, perhaps because my motion trigger - a mouse - occupied a small part of the frame. I set the tolerance to 5% and the threshold to 95%.

Yawcam logs each motion event with several useful parameters. It has a "motion %". The first mouse appearance is triggered by a value of 5%. In contrast me walking across the kitchen is at 48%. My guess is that the % is the percentage of the screen that goes above motion detection threshold.

Once again:









Comments

  1. I would love to know more about how you did this, Do you think that there is any way I could rig a wireless wifi cam to do the same thing?

    ReplyDelete
  2. Hi, yes it should be possible same as with a wired cam.

    You could check if the software the webcam came with motion detection in which case it should be very straight forward. If not, do a web search for "webcam motion detection" which should let you do it. I see that dorgem has shut down.

    Best

    ReplyDelete

Post a Comment

Popular posts from this blog

Python: Multiprocessing: passing multiple arguments to a function

Write a wrapper function to unpack the arguments before calling the real function. Lambda won't work, for some strange un-Pythonic reason.


import multiprocessing as mp def myfun(a,b): print a + b def mf_wrap(args): return myfun(*args) p = mp.Pool(4) fl = [(a,b) for a in range(3) for b in range(2)] #mf_wrap = lambda args: myfun(*args) -> this sucker, though more pythonic and compact, won't work p.map(mf_wrap, fl)

Flowing text in inkscape (Poster making)

You can flow text into arbitrary shapes in inkscape. (From a hint here).

You simply create a text box, type your text into it, create a frame with some drawing tool, select both the text box and the frame (click and shift) and then go to text->flow into frame.

UPDATE:

The omnipresent anonymous asked:
Trying to enter sentence so that text forms the number three...any ideas?
The solution:
Type '3' using the text toolConvert to path using object->pathSize as necessaryRemove fillUngroupType in actual text in new text boxSelect the text and the '3' pathFlow the text

Calculating confidence intervals: straight Python is as good as scipy.stats.scoreatpercentile

UPDATE:
I would say the most efficient AND readable way of working out confidence intervals from bootstraps is:

numpy.percentile(r,[2.5,50,97.5],axis=1)

Where r is a n x b array where n are different runs (e.g different data sets) and b are the individual bootstraps within a run. This code returns the 95% CIs as three numpy arrays.


Confidence intervals can be computed by bootstrapping the calculation of a descriptive statistic and then finding the appropriate percentiles of the data. I saw that scipy.stats has a built in percentile function and assumed that it would work really fast because (presumably) the code is in C. I was using a simple minded Python/Numpy implementation by first sorting and then picking the appropriate percentile data. I thought this was going to be inefficient timewise and decided that using scipy.stats.scoreatpercentile was going to be blazing fast because
It was native C It was vectorized - I could compute the CIs for multiple bootstrap runs at the same time …