Videos
Videos
Click on the thumbnails below to download the videos. Each of the videos is between 30 and 40 MB in size.
The upper left image shows the raw video input with the sufficiency index (SI) and necessity index (NI) of each object overlaid on top of the image. The upper right image shows the color segmentation. The lower left image shows the motion segmentation. And finally, the lower right image is the camera view after we’ve applied the blur filter (to remove many of the noise artifacts).
Narcissus marks objects that it detects as self by coloring those pixels green.
1 color marker, no distractors
These movies show Narcissus tracking a single (blue) color marker with no distracting color markers.
 Run 1 |
 Run 2 |
 Run 3 |
2 color markers, no distractors
Here Narcissus is tracking a two (blue and purple) color markers with no distracting color markers.
 Run 1 |
 Run 2 |
 Run 3 |
2 color markers, with a semi-random distractor
Again Narcissus is tracking two (blue and purple) color markers, but this time a third (red) distractor is randomly waved about in the image frame.
 Run 1 |
 Run 2 |
 Run 3 |
2 color markers, with an anticipatory distractor
Finally, we tested Narcissus by tracking its two (blue and purple) color markers and a (red) distractor. However, this time the red color marker is moved in synchrony with Narcissus’ own movements in an attempt to fool Narcissus into detecting the distractor mark as itself.
 Run 1 |