Demining Project
Overview
Landmine detection is a complex and highly dangerous task. Most
demining operations are done using hand-held detectors, which means
that the operator is always at risk of serious injury or death.
One of the most important factors that determines the probabilty of
detection is the operator performance.
Therefore, it is very important that we train the operator well and
are able to assess their performance accurately. The achieve these
objectives, we have been developing two training tools, the 3-D tracker
for real-time feedback during training, and the virtual mine lane for
interactive training. We have been using the 3-D tracker successfully
to assess the performance of an operator as a part of a successful
training program.
The 3-D tracking system consists of two video cameras mounted
with a vertical stereo baseline of about 7 feet. The system
tracks the detector head at about 30 frames per second, and computes
the 3-D world position. It uses this information to build up a
coverage map and to compute to speed at which the detector is moving.
The coverage map is used to determine if the operator missed any
areas during scanning. It is also color coded based on either the
speed or the height of the detector. This will show areas where
the detector is outside of its optimal operating range.
The virtual mine lane builds on the tracking system by adding
elements to simulate a mine lane to allow training anywhere, anytime.
A video projector is used to display a ground texture, and optionally
the coverage map and mine footprints. A sound is generated to simulate
the output that a real mine detector would generate as it passes over
a mine.