Yes, you're right, I'm using Kalman filter to "remove" the gravity from the accelerometer data. Then I calculate the magnitude vector and then I check if it is above or below a fixed thresold. It works, but I need to isolate shakes and other movements. I can't rely on GPS data, because when a user is standing I want to stop to read them. I know it's very diffcult. Thanks
On 1 Mar, 15:23, Marcin Orlowski <[email protected]> wrote: > On 1 March 2011 15:06, havanakoda <[email protected]> wrote: > > > I would like to use the accelerometer to detect is a user is walking > > or standing. I'm using a kalman filter and now I'm able to detect it > > but if a user is standing and moves or shake the phone it seems like > > he is moving. > > Kalman is not a detector by itself, but filter. And what you really > detect is in fact not user movement but device movement which then you > *assume* equals user moves (as usually phones do not move by itself). > To make sure user really moves you may need additional location > information. Of course once you have location accelerometer may become > useless however since GPS drains battery badly I'd combine both and > use triangulated provider instead, just to know user moved in given > period of time and combined with your accelerometer readings that may > lead somewhre. Note that user may move but not "wave" (i.e. using car) > > -- > Regards, > Marcin -- You received this message because you are subscribed to the Google Groups "Android Developers" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/android-developers?hl=en
