We are not far from the day when most video products will include embedded content analysis, making all video products smarter. However, there is a lack of solid technical information to help compare available technologies. The problem is that companies often make grand claims, but many fall far short in performance, leading to widespread disappointment.

The purpose of this article, therefore, is to outline the general principles of how video analytics works, in non-technical language, and examine how competing technologies try to solve these problems. The results vary dramatically, and a closer look shows why there are such big differences in performance.

Video analytics systems are built on three core components:

- Motion detection and object segmentation: This is where the video is processed to separate foreground objects from the background. This is the most processor intensive part of video analytics, accounting for up to 80% of the computational resources. However, there is a wide range in how well different products segment moving objects from the rest of the video.

- Object Tracking: This step tracks groups of pixels that are foreground objects as they move from frame to frame. If a group of pixels moves across the scene, it is probably a foreground object. The challenge is to track this blob of changing pixels. Once again, there is a huge range in performance from the different approaches taken.

- Object Classification: This function identifies the type of object detected. If a group of pixels moves across the scene, it is probably a foreground object. The challenge is to track this blob of changing pixels. Once again, there is a huge range in performance from the different approaches taken.

Systems vary in how well they perform each of these three steps. For example, there are many products being sold today as video analytics that are better described as “advanced video motion detection.” They can extract blobs of pixels moving across a scene, but cannot tell whether these objects are people, vehicles or anything else. In other words, they have no object classification.

Such systems have a harder time distinguishing a branch blowing in the wind from a person, but some of them have added object size calibration to help ignore things that are too big or too small. Large animals and tree branches are still a problem with these technologies, and they also require someone manually calibrating each camera for object sizes. Advanced video motion detection systems might be able to perform all the behavior detection types you see in the best video analytics systems, such as tripwires, direction of travel, intrusion detection, etc., but their results cannot compare to the accuracy of systems with superior object classification.

This is just one example of where some products skimp to reduce the amount of processing required. The problem is that you can’t easily tell the difference by just looking at such solutions or reading their literature. They claim to offer all of the same features you see in high end systems. However, the differences in results are stark.

Even the best of the advanced video motion detection systems are at least 10X worse compared to even the poorest true video analytics products. Extensive testing easily proves this out, but most integrators and users don’t have the time to test dozens of products to find one that works.

For a more detailed description of how video analytics works, read All Analytics are not Created Equal by Doug Marman, CTO and VP of Products at VideoIQ, at http://www.videoiq.net/products/resources.

Video Analytics (VA) is one of the most rapidly growing fields of the video surveillance industry. It is also known as Intelligent Video Surveillance. Video Analytics greatly enhances the power and analytical capabilities of network camera software.

As the name suggest, the purpose of Video Analytics is to carefully analyze video surveillance footage. Most forms of VA network camera software are even able to perform these analyses in real time. The analyses can take many shapes and forms. One of the more common (and simplest) forms is that of motion detection.

Taking video from network cameras which record images in a digital format, the video analytic software examines images not just frame by frame but pixel by pixel. A pixel is the most basic unit of information contained in a digitized image or video. What might appear to be only a minor change when looking at the full picture might actually cause a major change to a group of pixels, which the software recognizes and then informs the user. Video analytics software can catch even the slightest changes in an image from frame to frame by catching differences in the information sent.

When using VA software, then, it is good to have high resolution images. The higher the resolution of the video, the more precisely the software can analyze. This is because the higher the resolution of the camera, the more pixels are used to capture the image and thus there is more information for the software to analyze.

This network camera software can also be configured to recognize and distinguish certain objects, or tell objects apart. For example, if you are monitoring a specific item your shop, you could program the software to recognize that object and notice if it should change at all or go missing. Because it can differentiate between objects, it would also be able to tell if the item were replaced with something else.

Video analytics network camera software can also be used to do things such as count people walking on a sidewalk or cars passing down a busy street. With its detailed analyzing capabilities it is able to tell people and cars apart from each other and from the background, providing accurate statistics on these occurrences.

While an important part of network camera software, video analytics is not the only part. It is used to analyze information, but the software in general can also be used for many other purposes. For example, should the VA tool pick up something unusual, such as a missing object, or motion when there should be no motion or something of that sort, it can activate alarms in the building, contact the police or other authorities and even send you an e-mail notification of the event. This is known as advanced event management and is one of the many added capabilities of network camera software which utilizes video analytics tools.