← IP Cameras 2013 History →

Training note Video Analytics Human behavior   Training note Video Analytics Left Object Training note Video Analytics Counting

This article attempts to explain what Video Analytics (VA) is and how it differs from IP video surveillance (IPVS).

VA is about “analysis of images” captured by surveillance cameras of an IPVS system in real time.  IPVS analyses images or camera footage in order to produce useful information for surveillance purposes.  For example, we can get alarm alerts from an IPVS system when motion is detected in a pre-defined area by one of its cameras.  VA does the same and a lot more using computing resources outside of the camera and IPVS system.

Motion Detection works on change of pixel state (from 0 to 1 or vice versa).  The user pre-defines how many pixel changes constitute motion.  This algorithm is simple and can easily be done by the camera or IPVS system.  The trouble is that pixel changes occur in many situations such as environmental lighting change during day and night, falling leaves, cats and dogs, tree shades etc.  Many alarms produced by an IPVS system are not what the user needs and they have become nuisances.  VA is here to reduce or even eliminate nuisances.  

In addition to security surveillance of the area under monitoring by cameras, the same image captured can be analysed to produce traffic counts, vehicle license plate number recognition, face recognition, abandoned objects, violation of traffic regulations, and so on.  Applications of VA are indeed limited by our imagination.

(Hover mouse over to enlarge)

To be meaningful, most VA applications have to produce information or alerts in real time.  This condition requires high performance computing of camera images.  Therefore VA is normally done by a separate PC to the NVR of the IPVS system.  Camera footage is fed to both VA and IPVS for processing.  Unfortunately VA requires different view perspective to IPVS in some applications such as people counting versus intruder recognition.  VA is interested in heads and IPVS is interested in face, dress and body shape.   That is, VA may need dedicated cameras to be installed. 

VA is still not a common product off the shelf as of March 2013.  Whilst many IPVS systems offer motion detection of up to 16 cameras for free, one VA license for the recognition of licence plate number of vehicles has a price tag of about $5000 for car park policing and $10,000 for motorway policing.  Applications with a higher level of intelligence will be more expensive as a rule of thumb.

One camera needs one license per application.  Several cameras can share the same VA server as it is a computing resource issue.  In case the VA function is to track a person across several cameras, those cameras have to go the same VA server.

IPVS will incorporate more functions that are current in the domain of VA.  This is a natural technology progression issue.  For sure, VA will move on to tackle more complex scenarios.

END

Back to Video Surveillance Page

Training note Video Analytics Human behavior   Training note Video Analytics Left Object Training note Video Analytics Counting

This article attempts to explain what Video Analytics (VA) is and how it differs from IP video surveillance (IPVS).

VA is about “analysis of images” captured by surveillance cameras of an IPVS system in real time.  IPVS analyses images or camera footage in order to produce useful information for surveillance purposes.  For example, we can get alarm alerts from an IPVS system when motion is detected in a pre-defined area by one of its cameras.  VA does the same and a lot more using computing resources outside of the camera and IPVS system.

Motion Detection works on change of pixel state (from 0 to 1 or vice versa).  The user pre-defines how many pixel changes constitute motion.  This algorithm is simple and can easily be done by the camera or IPVS system.  The trouble is that pixel changes occur in many situations such as environmental lighting change during day and night, falling leaves, cats and dogs, tree shades etc.  Many alarms produced by an IPVS system are not what the user needs and they have become nuisances.  VA is here to reduce or even eliminate nuisances.  

In addition to security surveillance of the area under monitoring by cameras, the same image captured can be analysed to produce traffic counts, vehicle license plate number recognition, face recognition, abandoned objects, violation of traffic regulations, and so on.  Applications of VA are indeed limited by our imagination.

(Hover mouse over to enlarge)

To be meaningful, most VA applications have to produce information or alerts in real time.  This condition requires high performance computing of camera images.  Therefore VA is normally done by a separate PC to the NVR of the IPVS system.  Camera footage is fed to both VA and IPVS for processing.  Unfortunately VA requires different view perspective to IPVS in some applications such as people counting versus intruder recognition.  VA is interested in heads and IPVS is interested in face, dress and body shape.   That is, VA may need dedicated cameras to be installed. 

VA is still not a common product off the shelf as of March 2013.  Whilst many IPVS systems offer motion detection of up to 16 cameras for free, one VA license for the recognition of licence plate number of vehicles has a price tag of about $5000 for car park policing and $10,000 for motorway policing.  Applications with a higher level of intelligence will be more expensive as a rule of thumb.

One camera needs one license per application.  Several cameras can share the same VA server as it is a computing resource issue.  In case the VA function is to track a person across several cameras, those cameras have to go the same VA server.

IPVS will incorporate more functions that are current in the domain of VA.  This is a natural technology progression issue.  For sure, VA will move on to tackle more complex scenarios.

END

Compucon entered the video surveillance industry in 2008 and has come across 4 grades or evolutions of camera technology in the last 5 years.  This article explains the direction of evolution and what are current in 2013.  The information does not refer to 3rd party marketing materials but is based on direct Compucon hands-on experience in our workshop. 

o Let us use 4 letters to represent the 4 grades or evolutions: A, T, E and K.  Compucon cameras are indeed named with these 4 letters as the prefix.  Each letter represents one series, and not one model of cameras.  All cameras mentioned here are Internet Protocol (IP) based.  <Click this to go to the IP Camera main page for detailed specifications and terminologies >

Pictures below, from left to right, are E-53 Indoor, K-3911 Indoor, and K-5211 Outdoor

Features

o A-series base features are 1.3 Megapixels of image resolution (1240 x 1024), MPEG4 hardware compression of image for transmission from the camera to the computer for processing, and Power-over-Ethernet for cabling reduction.  There are other features that are present in some models of the series but not all models.  These other features are Infrared Filtering for optimising the changeover from visible light to low light recording and vice versa, Infrared LED for night vision, variable lens focus for optimising clarity against distance, and Digital Input and Output for connecting the camera to the outside world other than the computer. 

o T-series improves the features from MPEG4 to H264 which is a more effective image compression algorithm, and Dual Streaming with different compression algorithms.

o E-series improves from 1.3 to 3.0 Megapixels (2048 x 1536), adds Wide Dynamic Range capabilities to deal with high lighting contrast, Infrared LED, and Edge Storage to the camera. 

o K-series improves to 4 Megapixels (2032 x 1920) and more advanced Wide Dynamic Range.  Some models also gain optical zooming from remote or automatic on events, 180 and 360 panoramic vision angles, and tracking of object movements.

o As of March 2013, E and K are the dominant series

Prices

o E is the same or cheaper than A and T
o K is more expensive than A and T

Video Management Software

o Version 2.3 has evolved to Version 3.0 which has a better graphical user interface and faster image retrieval process from archive.  However, V3.0 comes with a price tag and we do not recommend an existing surveillance site on V2.3 to upgrade to V3.0.  However, software upgrade to a newer sub-version of V2.3 will be needed in order to accept E-series of cameras.

END

Back to Video Surveillance Page