Active Vision Sensor Planning of CardEye Platform

1
Active Vision Sensor Planning of CardEye Platform
Researchers
Sponsor
Sherif Rashad, Emir Dizdarevic, Ahmed Eid,
Chuck Sites and Aly Farag
US Army Mounted Maneuver BattleSpace Lab
2
Objective
The main objective of this project is to design
and implement an active sensor planning algorithm
for the CardEye platform. For this system,
generalized camera parameters such as position,
orientation, and optical settings have to be
determined according to the new position of the
robot arm so that its features are within the
field of view of the CardEye cameras and are in
focus.
3
System Overview
Sending the captured images of robot arm to be
displayed
Robot Arm
CardEye active vision system
Sending planned parameters to CardEye to adjust
the cameras settings according to the new
settings
Super Computer
Transmit current coordinates to super computer
using the serial port
Sensor Planning
Reading robot coordinates from super computer
4
CardEye Platform

• This platform uses an agile trinocular vision
  head contains three CCD cameras (c, c, c)
  with their lenses for the automated zoom and
  focus.
• The cameras are placed at equal distances from
  each other. The cameras can translate (t) along
  their mounts to change the baseline distance.
• At the same time, the cameras can rotate towards
  each other to fixate to a point in space by
  changing the vergence angle (?).
• The target is assumed to be inside a sphere that
  has a radius (R).

5
Geometry for Sensor Planning

• Camera Parameters
• translation (t)
• vergence angle (b)
• filed of view angle(a)
• (for zoom setting)

6
Sensor Planning

• The system's fixation point is the center C of
  the sphere. The center of the sphere is at
  distance d from the origin along the z axis.
• Every time, the sensor planning module will
  have the radius R and the distance d only (to be
  calculated from the initial position and the
  current coordinates of the robot).
• For suitable planning, we should calculate t for
  translation, b for adjusting the vergence angle
  so all cameras can fixate on the same point in 3D
  space, and a to set the zoom of the cameras.

7
System Constraints(a) Overlap Constraint
where

• By maximizing d, overlap area is also maximized.
• By decreasing t, we increase the overlap.

8
System Constraints(b) Disparity Constraint
Total Angular Disparity
By increasing t, more adequate depth information
can be recovered from the imaged object.
9
Analysis of System Constraints

• For effective reconstruction, the images must
  display adequate depth information (increase t)
  and have a fairly large overlap area (decrease
  t).
• Solution
• 1. Analyze the effect of object distance on
  overlap and disparity angles and compute
  translation t.
• 2. Normalize the translation values based on the
  physical range of the system translation.
• 3. Estimate the system workspace
• 4. Repeat step 1 and compute t as function of
  object distance d.

10
2nd-order polynomial equation for sensor
placement t
Five cases of object size are analyzed and their
solution for t is estimated for each case
Case 1 0.2m ltR lt 0.3m, 1.200m lt d lt 7m t
0.005622 d2 0.04068 d 0.04125 m Case 2
0.3m lt R lt 0.5m, 1.925m lt d lt 7m t 0005812
d2 004702 d 0.01307 m Case 3 05m lt R lt
0.7m, 2.650m lt d lt 7m t 0006205 d2 005530
d 0.09068 m Case 4 0.7m lt R lt0.9 m,
3.375m lt dlt 7m t 0006882 d2 006668 d
0.20372 m Case 5 09m lt R lt1.0m, 4.100m lt
d lt 7m t 0007990 d2 008380 d 0.37802 m
3rd-order polynomial equation was for the voltage
used to control the zoom in lenses
11
Sample of Results (1)
After Sensor Planning
Before Sensor Planning
At d2.091m and R0.399m
12
Sample of Results (2)
Before Sensor Planning
After Sensor Planning
At d1.525m and R0.200m