*ObjectR Basic – Rules

Open

Technical Article | TA-20201002-TP-09 VDG Sense | Video Content Analyses | ObjectR Basic Open

Open

Note: ObjectR Basic is not available in VDG Sense 2.5 or higher!

Rule Number

Selection of max. 5 Rules possible. Selection 1,2,3,4 and 5

Rule Active

Activate selected Rule

Rule type

Area of interest
Tripwire
Multiline tripwire
Segment tripwire
Multiline Segment Tripwire
Scene Change

Event text

Event text that’s visible when rule  is triggered

Object type

Anything
Vehicle
Person

Area of interest type

Enters
Exits
Inside
Appears
Disappears
Taken away
Left behind
Loiters

Draw Rule

Enables Rule drawing

Draw filter

Enables filter drawing

Filter
The filter settings are intended to make the rule event generation more robust. The filters are linked to the current rule only, every rule has its own filter settings. The filter settings don’t have any influence on the mark-up data produced by ObjectR. The filters are separated in three sub groups:

• Object Size  Used for absolute size indications for the ObjectR system.  

• Object Size change Used to filter irregular size changes.

• Object shape and direction Used to filter out irregular direction and shapes.  

Object Size
The size filter provides the user to set a minimum and maximum size for the objects that have to trigger a rule. Defining minimum and maximum object size filters requires some preparation, and it frequently involves more than one person to accomplish. This is because some representative objects need to be in front of the camera while the user sets up the filters. Representative objects are people, vehicles, or other things that are of the same type and size as the kinds of objects ObjectR will be monitoring. See below for more information about the types of representative objects to use when setting up filters. Depending on the kinds of events ObjectR are detecting on a particular camera, one of the following may need to take place while you are defining an object filter:

• A person may have to walk or stand within the camera’s field of view.

• A vehicle may have to drive or park within the camera’s field of view.

• You may have to place another object, such as a package or bag, within the camera’s field of view.

The picture at the right represents an example situation in which only vehicles of a certain size may trigger a tripwire. It is an example to set up a filter. Notice that persons who walk over this line will not trigger the tripwire event because the object’ size is smaller than the required minimum size (is smaller than the inner box).

There are two boxes surrounding each object. These represent the minimum and maximum size for objects that are ’Near’ or ’Far’ from the camera’s of field of view. The following steps outline the basic process of setting up minimum and maximum object size filters:

• One
  The object enters the camera’s field of view and moves to a position that is close to the camera (in the foreground), but not so close that the top and bottom of the object cannot be seen.

• Two
  The user setting up the filter resizes the foreground (near) box based on the size of the representative object. Objects which are just as close to the camera as the filter is and smaller than the minimum size box or larger than the maximum size box are ignored by ObjectR for a particular rule.

• Three
  The object moves to a position farther away from the camera than the first position (in the background).

• Four
  The user setting up the filter resizes the background (far) box on the size or the representative object. Objects which are just as far from the camera as the filter is and smaller than the minimum size box or larger than the maximum size box, are ignored by ObjectR for a particular rule.

There are a several important guidelines to follow when setting up object size filters, use these to ensure they
work correctly.

Important guidelines

Object Size change

The object size change filter enables ObjectR to ignore objects that increase or decrease in size between frames of video too quickly to be objects of interest. (In surveillance video, a frame is one still picture in a series of pictures that, when displayed in succession, depicts motion.) The object size filter is most often used in outdoor environments in which shadows and other lighting conditions trigger false alarms. The algorithm uses a multiplier ratio by which the size of an object can increase or decrease. ObjectR will ignore any object that increases or decreases in size more than the amount specified in the Multiplier. The Multiplier is a multiplier of 100%, with 100% representing an object size that does not change between frames. Multiply 100 by the Multiplier to determine the largest possible change in size between frames.

100 * Multiplier = max % of size increase between frames.

Be aware that, when an object increases in size by a multiplier, its overall size (or area) increases more than the multiplier. For example, if an object increases 2 times in length and width from one frame to the next, its area does not increase 2 times. Instead, it increases 4 times in its overall size. Divide 100 by the Multiplier to determine the maximum possible decrease in size between frames. For example, if you specify a Multiplier of 2, ObjectR will ignore objects that increase in size by 200% or more between frames, and they will ignore objects that decrease in size by 50% or more between frames.

100 / Multiplier = max % of size decrease between frames.

Object Shape and direction

The object shape and direction filter enables ObjectR to ignore objects that change shape and move in different directions between frames of video too quickly to be real objects. (In surveillance video, a frame is one still picture in a series of pictures that, hen displayed in succession, depicts motion.) The object shape and direction filter is most often used in outdoor environments in which waves, tree foliage or flags moving in the wind, or erratic lighting conditions trigger false alarms. Be aware that using a shape and direction filter may cause some real events to not be detected by ObjectR. For instance, if a boat was moving through an area of water where there were lots of choppy waves, then the boat may not be identified as an object until it has moved away from those waves.