LSTABLE:  LEFT-SHIFT CAMERA ON XY TABLE

			     Bob Bolles
			    April 2, 1985


Taken with the Sony camera (borrowed from Stan Reifel) with the 12.5mm lens
and the IR filter from the Fairchild head (which Bill took out for other
reasons).  The Sony camera has several advantages over the GE and the
Fairchild.  It is inexpensive ($1000.).  It appears to have none of the
patterning I've seen in both the others (4 row and 4 column-type of "mesh"
over the image).  It has much better sensitivity than the Fairchild
(I could barely see anything with the same lens and filter on the
Fairchild.)  It appears to have good blooming characteristics.  The sunlight
and flourescents don't cause it to bloom like the Fairchild.

I took CAL0.IMG and CAL20.IMG via USR:[BOLLES]CALCAM.ICP, which takes one
picture, moves the table 20" back from the target, and takes the second one.

Using the formula of March 28 (page 3) I computed the following pixel sizes:

		1 horizontal pixel = .001170018"
		  1 vertical pixel = .001089928"

which would make the 256x240 (sampled down from 512x480) image plane to be
.2995"(h) x .2616"(v).  The specs say that the sensitive area on the chip
is 8.8mm x 6.6mm or .3477" x .2596".  I don't understand the difference
in the horizontal sizes.

Using this formula the two image plane distances corresponding to 30" on
the target were .1602925" and .1689388", which I believe should be the
same, if the optics is symmetric, which it is.  I don't know why there is
such a difference.  (Maybe poor pointing accuracy of the cursor on the
images ... only to the closest pixel.)

I then used the 90" tape measured distance from the lens center to the
target to get another estimate of the image plane distances.  For a 30"
target, the image plane distance should be 1/3 of F, which is .492126,
which is .164042".  Since that is a compromise between the two estimates
from the first method I decided to use it and recompute the pixel sizes.
The new sizes are:

		1 horizontal pixel = .001197387"
		  1 vertical pixel = .001058336"

However, this still does not account for the larger horizontal chip
dimension.  In pixels, 30" corresponds to 175 horizontal pixels and 201
vertical.  If the aspect ratio is 4:3 so that 512 horiz pixels covers
4 and 512 vert pixels covers 3, then one would think that the ratio
would be more like 150 H pixels and 200 V pixels for 30".

These pixel sizes imply a field of view of 34.6 degrees H by 28.9 degrees V.

*** Notice that the images were actually taken by shifting the table RIGHT.
To correct for this their names will be redone sometime so that they
really go right to left, which will confuse people if the clock can
be read ... It'll go backwards, Oh, well.  See the ICP macro file
SEQUENCE.ICP which was used to take the sequence ... it contains the
cropping and resampling instructions ... basically 512x480 out of 512x512
and then sampled down to 256x240.

The camera, instead of being horizontal, was tilted down slightly.  We
measured the tilt to be 7/32" over 2 & 5/8" which corresponds to an angle
of 4.763642 degrees.  At .001058336"/pixel this is an image plane distance
of .0410105" or 38.75 pixels (out of 240 V pixels).  Thus, the focus
of expansion for AHTABLE pictures would be at (128,158) (starting with
(0,0) vs (1,1)).  To check this I took a horizontal picture (HORIZNTL.IMG)
and marked the piercing point (256,240) in it and located that point
in AHTAB125.IMG.  It was at (128,160), which agrees quite well with the
number mentioned above.  I then computed the angle that would place the
focus of expansion at (128,160), which is 4.916568 degrees.  I'll use
that as the pitch angle.

Horizontal distances (vs. distances along the axis of the camera, which
is pointing down slightly) to some of the objects in the scene are:

	21.0 -- closest leg of the ladder
	21.5 -- the tip of the leaf at the top of the last image
	27.5 -- closest leaf at the bottom of the last image
	39.0 -- far leg of the ladder
 	40.5 -- closest (upper left) corner of the shirt
	64.5 -- post near the middle of the picture
	68.0 -- lower left corner of the tilted wood backing for a light
	68.5 -- string holding the lead weight
	72.5 -- closest corner of the small box on the table
	72.5 -- label on the motor
	75.5 -- top right corner of tilted wood backing board
	79.0 -- closest side of the small conveyorbelt
	80.0 -- diagonal brace for the post (from top center to the left)
	91.5 -- top of the small vertical leaf of vertical plant on left
	95.5 -- pot holding that plant
	119.5 - the group of wires dropping down to the back of the terminals
	122.5 - upper right, closest corner of the keyboard
	100.0 - upper left corner on the back of the terminal
	148.5 - front of pot at the far end of the terminal table
	208.0 - front leg of the chair on the left
	224.5 - the back of the chair on the left
	277.0 - rightmost left of the cart, in the distance
	285.5 - leftmost pt on the black shade of the standing photo light
	295.5 - left visible left of the cart
	318.5 - left front side of the black cabinet on the right
	368.5 - far side of the tall cabinets on the left
	472.5 - front of the shelfs against the back wall
	491.5 - the clock

These distances were measured with a tape measure ... originally from
the vise holding the camera and then subtracting 3.5" to the lens center.