5.Demo Screen
The [Demon screen] provides the following information.
To check the following information on the [Demo Screen], you need to set the detection area/line in AI Video Motion Detection. If this is not set, the following information is not displayed.
2.
Detection object icons
-
When [Display score] is On, the Detection Object icons are displayed in the upper left corner of the detection frame.
-
When [Display Object Name] is On, the name of the On-site learning object appears on the icon.
3.
Detection frame
-
When an object is detected, a detection frame is displayed. The detection frames are blue, light blue, and red.
-
Blue: indicates the detected object.
-
Light blue: indicates a Detection Object for which [Improving false detection] has been selected in the [On-site Learning function]. This is displayed when [Display frame for improving false detection] is On.
-
Red: indicates objects in the area where the alarm occurred and objects that cross the line in the set direction.
4.
Detection scores for detection object
-
When [Display score] is set to On, the detection score is displayed in the detection frame. "**" may be displayed when the detection score is below the threshold.
5.
White dot on the detection frame
-
Displays the base position of the detection frame.
6.
Detection area
-
Displays a colored frame for the detection area set in AI Video Motion Detection.
-
Area 1: white, Area 2: blue, Area 3: green, Area 4: red, Area 5: yellow, Area 6: light blue, Area 7: purple, Area 8: pink
-
Solid line: Area set to "Enabled"
-
Dashed line: Area set to "Disabled"
7.
Detection line
-
Displays a colored line for the detection line set in AI Video Motion Detection.
-
Line 1: white, Line 2: blue, Line 3: green, Line 4: red, Line 5: yellow, Line 6: light blue, Line 7: purple, Line 8: pink
-
Solid line: Line set to "Enabled"
-
Dashed line: Line set to "Disabled"
8.
Direction label
-
Displays labels ([Cross line detection]: A, B, [Count function]: In, Out) for the direction in which Cross line counting is performed in [AI motion detection] ([Cross line detection]) and [Count function].
8.
Number of counts (Display only when [Detection frame and set area/line display] is selected for [Count function])
-
Displays a colored line for the number of objects counted in the direction set in [Cross line counting] from the [Count function].
You can make the following settings on the [Demo screen].
1.
[Detection frame and set area/line display]
-
Select the content of the [Demo screen] live image.
Select from [AI motion detection (Detection setting 1)], [AI motion detection (Detection setting 2)], and [Count function].
-
This is not displayed if AI Video Motion Detection Application is not installed.
2.
[Display score]
-
Set to On to display Detection Object icons and detection scores.
3.
[Measure score]
-
Set to On to measure the maximum and minimum detection scores and display the measurement results (MAX/MIN) on the demonstration screen. Set to Off to stop measuring.
4.
[Human identification threshold]
-
Set the detection threshold for people. The smaller the value, the easier it is to detect human, but it is also likely to return more false detections.
1 to 99
Default: 20
5.
[Vehicle identification threshold]
-
Set the detection threshold for vehicles. The smaller the value, the easier it is to detect vehicles, but it is also likely to return more false detections.
1 to 99
Default: 70
6.
[Bicycle identification threshold]
-
Set the detection threshold for bicycles. The smaller the value, the easier it is to detect bicycles, but it is also likely to return more false detections.
1 to 99
Default: 55
7.
[Display frame for Improving false detection]
-
Set to On to display the detection frame (light blue frame), detection score, and [Threshold setting] of the Detection Object for which [Improving false detection] is selected in [On-site Learning Function].
8.
[Display Object name]
-
Set to On to display the name of the configured On-site learning object in the detection frame.
9.
[Threshold setting] of on-site learning object
-
Set the detection threshold for objects 1 to 5. The smaller the value, the easier it is to detect objects 1 to 5, but it is also likely to return more false detections.
1 to 99
Default: 50

・Use Mozilla Firefox, Google™ Chrome™, and Microsoft Edge to view the [Demo screen]. Internet Explorer is not supported.


・The [Demo screen] can only be displayed in one browser at a time. Simultaneous access across multiple browsers is not supported.


・If [Data Encryption] is set to [On], no [Demo screen] images are displayed.


・When used at the same time as other function extension software, the positions of people on the [Demo screen] and the detection frame may become misaligned.
・Since the [Demo screen] is only used for demonstrations, we do not recommend using it for actual operations.

5.1About threshold settings for [Improving false detection]

This section describes the threshold settings for detection objects for which [Improving false detection] is selected for the On-site Learning Function.
The figure below shows an image of improving false detection when a chair is misdetected as a person. (1) is the detection result when a chair is mistakenly detected as a person, and (2) is the detection result when a chair is learned by selecting [Improving false detection] for [On-site learning function] in this product.
In improving false detection, detection frames where the detection results of (1) and (2) overlap are considered to be subject to improving false detection and are eliminated from the detection results ((3) in the figure below). The detection result of (3) is displayed on the demo and simulation screens.
The threshold setting of the detection object affects the detection result of (2). Detection frames that are not adopted in the detection result of (2) are not subject to improving false detection, so please turn [DIsplay frame for Improving false detection] On and adjust the threshold so that a frame for improving false detection (light blue frame) is displayed on the detection object you want to improve false detection.