Security Dealer & Integrator

JUL 2016

Find news and information for the executive corporate security director, CSO, facility manager and assets protection manager on issues of policy, products, incidents, risk management, threat assessments and preparedness.

Issue link: http://sdi.epubxp.com/i/703941

Contents of this Issue

Navigation

Page 21 of 109

t ISC West, I was privi- leged to moderate an educational session on future trends in video. e panel, sponsored by Pivot3, included NVIDIA, which was slightly puzzling to me at the time. If you are like me, your likely exposure to NVIDIA was the last time you bought a PC and wanted to upgrade the graphics card to a more powerful option for better video rendering and response. at capability is still a major part of NVIDIA's repertoire, but I was curious why NVIDIA was presenting at, or even attending ISC West, for that matter. NVIDIA's Adam Scraba and Saurabh Jain took the time to educate me about why they are excited about video surveillance. It centers around the core of all of NVIDIA's products — the Graphics Processing Unit (GPU) — which achieves extraordinary levels of processing power by using a large number of cores acting in parallel. is is in contrast to a standard CPU, with a limited number of cores processing a task in sequential fashion. The Power of GPUs GPUs directly address the information and processing that can occur with image analysis at the pixel level. In the past, the field of computer vision used complex dedicated algorithms to analyze objects, but was limited by available processing power. e tasks lent themselves to massive parallel pro- cessing, but the cost to implement was prohibitive. A great example is facial recognition, where available processing power and cost limitations may lead to compromises — perhaps in resolution or frame rate. GPUs change the game by packaging new levels of video/pixel processing performance affordably into widely available hardware. e power of GPUs now enable real applications to use a form of arti- ficial intelligence (AI) called "Deep Learning." Rather than dedicated customized algorithms, the GPU is programmed to learn, like the neural network in a brain. A June 2016 IEEE publication states: "Data lines possessed by each neuron of the network communicate with one another…e technique lets the net- work form neural relationships most relevant to each new situation." With exposure to lots of data of a specific type over time, the sys- tem gets smarter. ink of vehicle or license plate recognition, for exam- ple. A Honda CRV could be distin- guished from an Acura RDX. State license plates could be recognized by portions of a design as well as the state name —just by showing the system a large sample of cars and license plates. Because the effort is in the learning, not the programming, accuracy goes up, scalability increases and develop- ment costs tumble. Impact on Video Video analytics will become better and faster thanks to these GPUs. Analysis will be less constrained by pre-deter- mined rules, making it easier to spot abnormalities. Video will become a rel- evant, valuable component in Big Data, because more useful metadata about the scene will be a part of the video file allowing search, sort and aggregation aer the fact. Processing will enable video enhancement with far greater accuracy. It will assist decisions about whether to store or not store data, based on type of motion and scene characteristics. One industry projection estimates that by 2019, the world will be storing 2500 PB/ day! IHS Technology forecasts a 14.8 percent annual growth rate from 2014- 2019. us, storing only what is needed will have enormous financial impli- cations; and throughput is claimed to increase by a factor or 10 to 12 times. Implementation of GPU technology may occur at several points, starting at the camera. e provisioned chips will replace current processors and contain CPU, GPU and all needed I/O. ey will perform compression very efficiently, as well as analytics. e pro- jected cost differential to implement is in the $100-150 range. NVIDIA projects that gateways pro- cessing multiple video streams will be used in between the edge and the point 20 Security Dealer & Integrator / www.SecurityInfoWatch.com July 2016 Tech Trends BY RAY COULOMBE The Power to Learn It is still early, but security manufacturers are actively building deep learning capabilities into video products A GPUs will perform compression as well as analytics . The projected cost differential to implement is in the $100-150 range.

Articles in this issue

Links on this page

Archives of this issue

view archives of Security Dealer & Integrator - JUL 2016