53
Camera Placement for Facial Analysis:
4 Factors
1. Field of View Determines Size and Resolution of Face
Facial analysis requires a certain minimum resolution level to be effective. This resolution level is measured in pixels.
•
3VR requires a minimum of 35 horizontal pixels between the eyes (or about 80 - 100 horizontal pixels across
the head) to perform facial analysis.
•
3VR performs analysis of all analog NTSC video at 4CIF (704 x 576 pixels)
Given these facts and that the average width between eyes is 3”, and the width of a head is approximately 6 - 7”, an
NTSC camera at 4CIF resolution can capture faces in a field of view
(FOV)
no more than about
4.5 feet
.
Rule of thumb:
place a person standing in the foreground in optimal focus. When they hold their arms stretched out
from side-to-side, you should not be able to see their hands (the image should be cut off at their wrists). If you can
see their hands in the image when they are standing in focus in the foreground, the field of view is too wide for facial
analysis.
Rule of thumb:
if you are looking at prerecorded images from a camera already placed, measure the width of the
head, and if it is smaller than 1/7 (about 15%) of the field of view, the field of view is too wide for facial analysis.
Poor FOV
5.5 feet
Face = 1/9 of image
Excellent FOV
3.5 feet
Face = 1/6 of image
Maximum Acceptable
FOV
4.5 feet
Face = 1/7 of image
Summary of Contents for P-Series SmartRecorder
Page 4: ...4...
Page 9: ...Product Diagrams M Series SmartRecorder Front view Back view Product Diagrams 9...
Page 10: ...10...
Page 31: ...Chapter 1 Installing a 3VR SmartRecorder 31...
Page 32: ...32...
Page 47: ...Chapter 2 Configuring a 3VR SmartRecorder 47...
Page 48: ......