Video Smoke Detection (VSD) systems have been developed to overcome many of the problems associated with smoke detection. It provides solutions for previously unsolvable fire detection scenarios, working externally as well as internally and represents a true technological breakthrough in fire detection.
Video Smoke Detection is based on the computer analysis of video images provided by standard modern CCTV cameras. VSD automatically identifies the particular motion patterns of smoke and alerts the system operator to its presence in the shortest time possible. This enables a fast response to a potential fire, saving valuable time even in voluminous areas or where a high airflow may be present.
In applications ranging from turbine halls to historic buildings, road tunnels, rail depots, warehouses, shopping malls, aircraft hangars and many others, Camera-based fire detection system has become established as the leading edge technology in the field of fire protection
Fire
safety professionals constantly seek the benefits of early warning of potential
fires. In a perfect world it would be possible to place hundreds of smoke
detecting sensors above and around any items or areas at risk. This would
certainly enable a fast response to a potential fire, saving valuable time even
in voluminous areas or where a high airflow may be present. Of course such a
dream is not possible from a practical or financial point of view.
Video smoke detection technology makes this dream a reality.
Video smoke detection technology makes this dream a reality.
How does VSD work?
Video smoke and flame detection is performed by a software algorithm running on Visual Signal Processors (ViSPs) that implement parallel processing engines in hardware. Video images are analyzed in real time by applying digital image processing techniques that allows smoke and flames to be detected with a high degree of confidence. The video image is continually monitored for changes and false alarms are eliminated by compensating for camera noise and acquiring knowledge of the camera view over time.
Multiple zones can be defined for a camera view in which smoke and flames are to be detected. Each zone has a set of parameters that provide complete control over the detection algorithm. These parameters are configured individually for each zone in order to cater for a wide variety of application scenarios. It is also possible to combine information from multiple cameras to enhance the detection process.
Stemming from many years of research and development several complex statistical and geometrical measurements are made on the video image data from each zone as dictated by the control parameters. This is made possible by the parallel digital signal processing capabilities of the hardware. The scale of parameter settings is such that it is possible to detect smoke ranging from slow emerging faint smoke through to dense smoke plumes that are produced in a short period of time.
Once the measurements have been made from the video image data, a set of rules can be applied to determine if they characterize smoke or flames. The rules can also be tuned to meet the specific application requirements to complete a robust and successful detection algorithm.
Video smoke and flame detection is performed by a software algorithm running on Visual Signal Processors (ViSPs) that implement parallel processing engines in hardware. Video images are analyzed in real time by applying digital image processing techniques that allows smoke and flames to be detected with a high degree of confidence. The video image is continually monitored for changes and false alarms are eliminated by compensating for camera noise and acquiring knowledge of the camera view over time.
Multiple zones can be defined for a camera view in which smoke and flames are to be detected. Each zone has a set of parameters that provide complete control over the detection algorithm. These parameters are configured individually for each zone in order to cater for a wide variety of application scenarios. It is also possible to combine information from multiple cameras to enhance the detection process.
Stemming from many years of research and development several complex statistical and geometrical measurements are made on the video image data from each zone as dictated by the control parameters. This is made possible by the parallel digital signal processing capabilities of the hardware. The scale of parameter settings is such that it is possible to detect smoke ranging from slow emerging faint smoke through to dense smoke plumes that are produced in a short period of time.
Once the measurements have been made from the video image data, a set of rules can be applied to determine if they characterize smoke or flames. The rules can also be tuned to meet the specific application requirements to complete a robust and successful detection algorithm.
Product
FireVu is an advanced embedded Video Smoke
Detection (VSD) server designed to operate over an IP network. For this,
mathematical algorithms it is capable of determining the presence of smoke
within each of its four available analog camera inputs (PAL or NTSC). Operators
can be alerted either remotely over the system’s network or local to the unit
via relay outputs.Each camera image can have up to 16 fully independent, configurable zones, allowing the user complete flexibility on setting up the areas to be protected with their required sensitivity levels. System configuration is carried out via a series of web pages using a browser such as Internet Explorer, while system monitoring and reviewing is carried out by Observer client software.
All alarm events are recorded to disk with configurable pre and post event video, allowing the operator to witness (and download) the event, including who or what created it.
The system is a 19” rack-mountable unit, utilizing in-house manufactured Visual Signal Processors (ViSPs) to process the images.
Each unit possesses 16 configurable relay outputs and can accept up to 16 alarm inputs. Numerous servers can be joined to a network to create a multi-camera system for larger installations.
Benefits
It’s
fast.... it detects smoke at the source of the fire.
- It’s unaffected by high air movement. It will sense smoke movement patterns just as quickly in high airflow as it does in no airflow environments.
- It can detect all types of smoke. Conventional detectors respond more quickly to certain types (colors) of smoke than others – VSD responds to the movement patterns typical of any color smoke.
- It can use traditional security cameras that may already be existing at the facilities needing protection.
- It gives visual verification of the alarm allowing a more immediate response to fire event.
Application
Case
Study – Power Generation:
Here is a good example of where video smoke detection might solve a problem. Fire protection is difficult for Turbine Generators in the Power Generation industry. Typically these turbine generators are in large open areas with really high ceilings. Stratification effects from high ceilings, dilution of the smoke in the large open area and unpredictability from the high airflow in the space. Conventional smoke or heat detection will just take too long to operate.
Video Smoke Detection can solve the problem. It will detect the smoke at the source of the fire (typically coming from within the generator somewhere) and doesn’t wait for smoke or heat to reach the detectors mounted all the way at the ceiling.
Here is a good example of where video smoke detection might solve a problem. Fire protection is difficult for Turbine Generators in the Power Generation industry. Typically these turbine generators are in large open areas with really high ceilings. Stratification effects from high ceilings, dilution of the smoke in the large open area and unpredictability from the high airflow in the space. Conventional smoke or heat detection will just take too long to operate.
Video Smoke Detection can solve the problem. It will detect the smoke at the source of the fire (typically coming from within the generator somewhere) and doesn’t wait for smoke or heat to reach the detectors mounted all the way at the ceiling.