ok, moving object detected and is<br>
stationary. What next?<br><br>A video camera can be used. An open source program like this can be used : <a href="http://dorgem.sourceforge.net/">http://dorgem.sourceforge.net/</a><br><br>Focal point of lens can be used for depth perception (perspective)<br>
<br>Then you can code the screen pixels such that the extreme left top is  (x,y) 0&#39;0  and Z being a variable - etc<br>
<br>
a) Calculate position X,Y,Z ( grid based )<br><span style="color: rgb(0, 0, 153);">
b) approach target</span><br style="color: rgb(0, 0, 153);"><span style="color: rgb(0, 0, 153);">c) redetect target - or update target</span><br style="color: rgb(0, 0, 153);"><span style="color: rgb(0, 0, 153);">d) approach target (by avoiding obstacles)</span><br style="color: rgb(0, 0, 153);">
<span style="color: rgb(0, 0, 153);">e) redetect target</span><br style="color: rgb(0, 0, 153);"><span style="color: rgb(0, 0, 153);">f) approach target (its a loop)</span><br>e) identify target<br>f) determine cause of action<br>
<br><br>Its a dumb system, because if the target becomes stationary ; then the code will deem it as part of background...<br><br>Unless one has a memory bank that &#39;remembers&#39; bearing  and shape of the scanned object  - even if the pursuing object changes direction to avoid obstacles... <br>
<br><br>