AutomatedBuildings.com Article - Building Analytics from a Different View

"Not everything that can be counted counts, and not everything that counts can be counted."
Albert Einstein

When we think of analytics related to buildings systems we generally think of predictive analysis or fault detection and diagnostic software tools related to HVAC systems. Video analytics, that is software that can analyze and identify people, objects and events is obviously different but in many ways can be just as important in providing information on building use and performance. The reason is that like the iconic Swiss Army Knife, video cameras can be multi-functional. The analysis of digital images addresses aspects of physical security but goes way beyond that to provide data and information for building life safety, energy management and overall building performance. What you find is that this one device, the video camera, has a variety of uses for sensing and gathering data about the building condition and performance. This is a good thing as more high quality and relevant building data is critical in generating actionable information and key to better management and building performance.

If you assume that the video camera is an extension of the human eye, the analytical software is the extension of the human brain. On the market today are cameras that can detect smoke or fire, identify specific people, detect motion, determine if objects have been moved and provide occupancy data including the actual number of people in a space. Generally, if you can develop a pixel template of the event or condition you are trying to track, the video analytic software can detect the event or condition.

The video analytic process starts with cameras capturing successive digital video images of a “coverage area”. The digital image consists of “pixels”, a contraction of the words “picture element” and the smallest element of the digital image. The analytic software first analyzes pixels, their patterns, the adjacency of pixels, the changing of pixels over time and other attributes, and then compares the pixels or bitmaps to a database or templates of objects, conditions and events. When the software gets a reliable match between the digital image of the coverage area and its database of templates or conditions, the video system identifies or senses an event, state or situation.

Video cameras are a staple of physical security systems. In the past, you typically had a “security operations center” where personnel viewed the feeds from the cameras and subjectively determined whether an event or action had taken place that warranted action. One of the largest benefits of using analytics in a typical video surveillance security system is improved detection and identification of threats, conditions and events. (Yes…. machines outperforming humans). The software is working 24/7 with a constant level of accuracy. Also many video surveillance operations are not real time, with video simply being archived and available for searching and reviewed after and incident. Even if the system is manned the attention span of personnel in a security operations center is oftentimes very short and inconsistent.

[an error occurred while processing this directive] Potential Uses of Video Analytics as Sensors

The analytic tools related to video cameras are extensive. As one would expect, most are geared towards some aspect of security and they include:

Some of the more innovative and interesting aspects of video analytics are people counting for occupancy and using video as a detector of fire and smoke. Here’s an overview of these two applications:

Occupancy, People Counting and Energy

The simple act of counting people entering or exiting buildings or spaces within a building can provide very valuable data which can be used in a number of different ways. One of those primary uses is energy management. At the core of energy management in a building is an alignment between energy consumption and occupancy of building space. Getting the data on energy consumption is fairly easy through the use of meters or utility billings. Obtaining data on accurate occupancy is much more challenging. Aside from retail buildings, very few building owners or facility managers have data on the number of people in their buildings, a time profile of their occupancy, or the count of occupants within the building or space..

The general options for gathering occupancy data are infrared sensors around the door frames, people carrying RFID tags, or access control card swiping, all of which have some issues or shortcomings.

In a video analytic solution cameras are place above an entrance or exit that can detect people and their movement in or out of the space or building. Systems typically collect statistics on space occupancy and variations of occupancy during the day or by day.

One example of the benefits of occupancy and people counts is using actual people counts at the beginning of the workday to startup and ramp up the HVAC system properly. People counting can also be utilized in the ventilation of certain spaces. For example, one of the advanced HVAC control approaches is CO2 Demand Control Ventilation (DCV). It’s best used in large areas, open office spaces, theaters, assembly areas, ballrooms, etc. A CO2 sensor is used to optimize the use of outdoor air and the energy required to condition the air. The CO2 sensor is really a “people counter” or at least a metric that helps reflect occupancy. However detecting occupancy through CO2 sensors has its limits and at times can be unreliable and provide poor estimates of occupancy. People counting technology with accuracy rates of 95% provides more reliable and accurate estimates of occupancy. Not only can you use the occupancy data to improve energy demand but the occupancy data can be used for to evaluate space utilization.

Video Smoke Detectors

In the life safety area, video analytics capture images and use an algorithm to compare those to a database of smoke and fire patterns. Typically these tools are assessing changes in brightness, contrast, motion and color. The use of video in this manner has several advantages. One benefit is the cameras may reduce or possibly eliminate the need for tradition smoke detectors. Another is that you can use the video smoke detector in spaces where a traditional smoke detector may not work; such as vehicle tunnels, high ceilings or where the detection device may be exposed to outdoor elements. The first recognition of video images used for fire and smoke detection was in the 2007 edition of NFPA 72. (As always however, their use should be discussed and approved by the local authority having jurisdiction (AHJ), generally the Fire Marshall).

With typical smoke detectors the smoke from a fire has to move or be transported to the smoke detector causing “transport delay”, essentially wasting time to trigger the detector. Video smoke detectors have no such delay and therefore are quicker in detection resulting in less damage and threat to life. When a fire occurs, minimizing detection latency is crucial to reduce damage and save lives.

While the main purpose of video cameras is physical security analytic software allows for more enhanced applications. In the future we can expect video cameras to take on the role of building sensors, not only in calculating occupancy but sensing other characteristics such as light levels or even thermal comfort.

[an error occurred while processing this directive]
[Click Banner To Learn More]

Events	Want Ads
Our Sponsors	Resources