What hardware platform is required for ObjectVideo OnBoard?

What portion of the processor is utilized by ObjectVideo OnBoard?

How much memory is required to support the ObjectVideo OnBoard application?

Where is the rule inference performed within ObjectVideo OnBoard?

Is there a limit to the number of rules a user can implement on a camera's view?

What is the output of ObjectVideo OnBoard? How much bandwidth is required to support this output?




A: ObjectVideo OnBoard is fully compatible with the Texas Instruments DM64x+ DSP family and Intel x86 line of processors.

• ObjectVideo OnBoard is also compatible with any chip in the TI TMS320DM64X+ series, including the DaVinci™ technology platform.
• Development and performance requirements distributed by ObjectVideo are based on operation on the TI DM642 720MHz and the Intel Core 2 Duo T7400/4MB L2 Cache @ 2.16GHz.
• Refer to ObjectVideo OnBoard Requirements page for detailed hardware specifications.

A: ObjectVideo OnBoard does not require a dedicated processor.

• Original Equipment Manufacturers (OEMs) are able to run additional applications on the same DSP or CPU running the OnBoard software without impacting the performance of ObjectVideo’s library.
• If all ObjectVideo features are activated, ObjectVideo OnBoard requires less than 25% of a TI DM642 @ 720MHz (assumes processing a CIF or 320x240 video feed at 10 frames per second) or less than 7% of an Intel Core 2 Duo T7400/4MB L2 Cache @ 2.16GHz.
• If all of the available ObjectVideo features and functions are not necessary, the percentage of processor utilization reduces even more.
• Refer to ObjectVideo OnBoard Requirements page for detailed hardware specifications.

A: It varies by platform:

• For DSP-based devices, ObjectVideo OnBoard uses 18-24 MB (configurable) per CIF video channel.
• For Intel-based systems, ObjectVideo OnBoard uses 15-24 MB (configurable) per CIF video channel.

A: When implemented within an embedded architecture, ObjectVideo OnBoard performs all video analytics and rule inference on the chip itself.

• Regardless of which platform is used for the analytics, ObjectVideo OnBoard does not require additional backend servers for analysis or application of rules, filters, schedules, etc. This architecture enables truly intelligent devices that take in video and output alerts or other intelligent data.

A: There is no limit on the number of rules or rule types.

• Since each new rule adds negligibly to processing and system memory requirements, there is no impact to users looking to activate a wide set of rules for concurrent real-time detections.
• ObjectVideo OnBoard includes a core set of optimized algorithms that analyze video independent of the rules created. As a result, activating new ObjectVideo rule types (e.g., tripwire, loitering) does not demand incremental processing power.

A: ObjectVideo OnBoard simply outputs alerts, which are user-defined behaviors detected by the system.

• An alert typically consists of alert data (e.g., camera name, rule violated, response message), and pre- and post-alert images.
• Alert images include the rule overlay and object mark-up.
• The alert packet size, assuming two alert images, is approximately 80 KB.
• Alerts can also be configured to send alert data only, which is approximately 15 KB.