The human mind is the most powerful computing device currently available. While it is
great at abstract association, image recognition and many other tasks, it is not suited for massive information storage, calculation and tedious tasks. VCA supports the human operator much as a spreadsheet complements an accountant.
Anyone who hasever taken notes on a regular basis understands how limiting handwritten notes can be; finding specific information in a notebook can be time-consuming and frustrating. In the past, video archives were nothing more than a collection of footage waiting to be reviewed. With the advent of intelligent surveillance systems, raw video has been transformed into actionable information.
Video content analysis (VCA) has been plagued by bad business practices and unrealistic expectations, but the technology is, in many ways, still evolving and there have already been tried and tested real-life success stories that benefit from it.
The key for VCA to provide maximum value is having a clearly defined problem and realistic expectations of a solution. “There have been successful projects installed all across Europe,” said Gerard Otterspeer, CCTV Product Marketing Manager, Bosch Security Systems. “In Greece, for example, they use video analytics in tunnels to detect if someone is driving the wrong way or at the wrong speed.
That's directional detection coupled with speed detection. If a car stops in the tunnel for a certain amount of time, which is object loitering, the local authorities can be notified. Furthermore, a clear distinction is made between size and object shape, so the system knows if it's looking at a person or a car.”
Quality Comes With a Tag
What exactly is intelligent video? It is a system that analyzes millions of pixels at blazing speeds, Otterspeer said. “No matter what detection you choose, as simple as it may seem, all of it depends on the underlying algorithm. The first step is to analyze all those pixels and then identify objects. Only when you have the objects can you set the rules. So, it all starts with the quality of the algorithm, and this varies greatly from provider to provider.”
For example , in a complex environment where there are objects walking past one another in the background and foreground, the object IDs may be merging and splitting constantly since the camera is not aware of depth in the scene. “A lot of time and efforts have gone into optimizing ID tracking to ensure there is a right balance. If this is not done properly and two objects merge into one, it messes up the detection,” Otterspeer explained.
Many camera companies are giving away their software at low or even zero costs. However, you get what you pay for, which is nothing, cautioned Ivy Li, cofounder and MD of iOmniscient. “System integrators sometimes complain that the products they were using did not work — if they bought them based on price rather than quality and functionality, they should not be surprised.” Developing VCA algorithms requires a tremendous amount of time and resources. When a provider is giving them away for free, it is possible that they did not put in that much effort to begin with. Came r a s , DVRs a n d o t h e r hardware devices are becoming commodities with reasonable quality, leaving price the only thing to compete on, Li said. “This is not yet true for video analytics. The huge difference in quality drives the market and solution prices.”
Most companies already offer reliable, basic solutions such as line crossing, zone entry/exit and tampering detection. Price per channel for these is dropping since most companies can deliver, said Thejaswi Bharadwaj, Head of Civilian Technologies at Delopt. “However, for analytics that involve significant R&D and intellectual property such as people counting, PTZ tracking and ALPR, the prices will stay steady for quite a while.” Today, many camera and DVR manufacturers give away their software for free to sell their other products, Li said. “If you want a good, working product, you would have to pay for it. It's the same with transportation. You can get a bicycle very cheaply. However, it will not get you from Beijing to Paris quickly.”
"Many VCA solutions on the market today use video motion detection. Today's VCA uses advanced technology which applies machine vision to video scenarios in security and business intelligence applications," said Ed Troha, MD of Global Marketing at ObjectVideo. "Video motion detection is often used in products as an added component to drive hardware sales. These are not truly intelligent analytics and can have limited reliability."
Processing
The algorithms determine how intelligent the VCA is, said Patrick Lim, Director of Sales and Marketing for Ademco Far East. “There are products that use entrylevel processors but perform very intelligent functions without a problem. However, having a more powerful processor gives you some space to accommodate future firmware upgrades that can bring more complex algorithms and smarter features.”
VCA algorithms are very computationally intensive, and any increase in available processing power results in the ability to deploy more accurate algorithms without increasing solution prices, said Zvika Ashani, CTO of Agent Video Intelligence. “Computerized vision is a science that has many applications other than security, and advances are slowly applied to VCA, resulting in an increase in solution accuracy.”
Organizations that have the luxury of applying their algorithms to different industries have the greatest advantage since they can adapt and apply their algorithms to different applications, achieving economy of scale and knowledge-sharing among different projects, Otterspeer added. "For example, algorithm R&D could be centralized and later utilized across divisions such as automotive and security."