Download PDF version Contact company

Intrusion alarm systems are currently facing a growing number of potential error sources in the environment. At the same time, alarm systems must comply with increasingly demanding legal requirements for sensors and motion detectors. As a future-proof solution, detectors equipped with Sensor Data Fusion technology raise the level of security while reducing the risk of cost- and time-intensive false alarms. This article provides a comprehensive overview of Sensor Data Fusion technology.

Anti-masking alarms

A cultural heritage museum in the South of Germany for decades, the installed intrusion alarm system has provided reliable protection on the premises. But suddenly, the detectors trigger false alarms every night after the museum closes. The system integrators are puzzled and conduct extensive tests of the entire system.

When they finally identify the culprit, it’s unexpected: As it turns out, the recently installed LED lighting system in the museum’s exhibition spaces radiates at a wavelength that triggers anti-masking alarms in the detectors.

Not an easy fix situation, since a new lighting system would prove far too costly. Ultimately, the integrators need to perform extensive detector firmware updates and switch to different sensor architecture to eliminate the error source.  This scenario is by no means an isolated incident, but part of a growing trend.

Need for reliable detector technology

Legal requirements for anti-masking technology are becoming stringent in response to tactics by criminals

The number of potential triggers for erroneous alarms in the environment is on the rise. From the perspective of system operators and integrators, it’s a concerning development because every false alarm lowers the credibility of an intrusion alarm system. Not to mention steep costs: Every false call to the authorities comes with a price +$200 tag.  

Aside from error sources in the environment, legal requirements for anti-masking technology are becoming more stringent in response to ever more resourceful tactics employed by criminals to sidestep detectors. What’s more, today’s detectors need to be fortified against service outages and provide reliable, around-the-clock operability to catch intruders in a timely and reliable fashion.

Sensor Data Fusion Technology

In light of these demands, one particular approach has emerged as a future-proof solution over the past few years: Sensor Data Fusion technology, the combination of several types of sensors within one detector – designed to cross-check and verify alarm sources via intelligent algorithms – holds the keys to minimising false alarms and responding appropriately to actual alarm events.

This generation of detectors combines passive infrared (PIR) and microwave Doppler radar capabilities with artificial intelligence (AI) to eliminate false alarm sources without sacrificing catch performance.

Motion detectors equipped with Sensor Data Fusion technology present a fail-proof solution for building security

It’s not about packing as many sensors as possible into a detector. But it’s about including the most relevant sensors with checks and balances through an intelligent algorithm that verifies the data for a highly reliable level of security. The result is the highest-possible catch performance at the minimum risk for erroneous alarms,” said Michael Reimer, Senior Product Manager at Bosch Security Systems.

Motion detectors with sensor data fusion

Looking ahead into the future, motion detectors equipped with Sensor Data Fusion technology not only present a fail-proof solution for building security. The comprehensive data collected by these sensors also unlock value beyond security: Constant real-time information on temperature and humidity can be used by intelligent systems and devices in building automation.

Integrated into building management systems, the sensors provide efficiency improvements and lowering energy costs

Integrated into building management systems, the sensors provide the foundation for efficiency improvements and lowering energy costs in HVAC systems. Companies such as Bosch support these network synergies by constantly developing and optimising intelligent sensors.

On that note, installers must be familiar with the latest generation of sensor technology to upgrade their systems accordingly, starting with a comprehensive overview of error sources in the environment.

Prominent false alarm triggers in intrusion alarm systems

The following factors emerge as frequent triggers of false alarms in conventional detectors:

  • Strong temperature fluctuations can be interpreted by sensors as indicators of a person inside the building. Triggers range from floor heating sources to strong sunlight. In this context, room temperatures above 86°F (30°C) have proven particularly problematic.
  • Dust contamination of optical detectors lowers the detection performance while raising susceptibility to false alarms.
  • Draft air from air conditioning systems or open windows can trigger motion sensors, especially when curtains, plants, or signage attached to the ceilings (e.g. in grocery stores) are put in motion.
  • Strong light exposure directly on the sensor surface, e.g. caused by headlights from passing vehicles, floodlights, reflected or direct sunlight – all of which sensors may interpret as a flashlight from an intruder.
  • Extensive bandwidth frequencies in Wi-Fi routers can potentially confuse sensors. Only a few years ago, wireless routers operated on a bandwidth of around 2.7GHz while today’s devices often exceed 5GHz, thereby catching older detectors off guard.
  • LED lights radiating at frequencies beyond the spectrum of visible light may trigger sensors with their infrared signals.

Regarding the last two points, it’s important to note that legislation provides clear guidelines for the maximum frequency spectrum maintained by Wi-Fi routers and LED lighting.

Long-term security

But the influx of cheap and illegal products in both product groups – products that do not meet the guidelines – continues to pose problems when installed near conventional detectors. For this reason, Sensor Data Fusion technology provides a reliable solution by verifying alarms with data from several types of sensors within a single detector.

Beyond providing immunity from false alarm triggers, the new generation of sensors also needs to comply with the current legislature. These guidelines include the latest EN50131-grade 3, and German VdS class C standards with clear requirements regarding anti-masking technology for detecting sabotage attempts. This is exactly where Sensor Data Fusion technology provides long-term security.

Evolution of intrusion detector technology

Initially, motion detectors designed for intrusion alarm systems were merely equipped with a single type of sensor; namely passive infrared technology (PIR).

Upon their introduction, these sensors raised the overall level of building security tremendously in automated security systems. But over time, these sensors proved limited in their catch performance. As a result, manufacturers began implementing microwave Doppler radar capabilities to cover additional sources of intrusion alarms.

First step detection technology

In Bosch sensors, engineers added First Step detection to trigger instant alarms upon persons entering a room

Over the next few years, sensors were also equipped with sensors detecting visible light to catch flashlights used by burglars, as well as temperature sensors. In Bosch sensors, engineers added proprietary technologies such as First Step detection to trigger instant alarms upon persons entering a room.

But experience in the field soon proved, especially due to error sources such as rats and other animals, that comprehensive intrusion detection demands a synergetic approach: A combination of sensors aligned to cross-check one another for a proactive response to incoming signals.

At the same time, the aforementioned bandwidth expansion in Wi-Fi routers and LED lighting systems required detectors to implement the latest circuit technology to avoid serving as ‘antennas’ for undesired signals.

Sensor data fusion approach

At its very core, Sensor Data Fusion technology relies on the centralised collection of all data captured by the variety of different sensors included in a single detector. These data streams are directed to a microprocessor capable of analysing the signals in real-time via a complex algorithm. This algorithm is the key to Sensor Data Fusion.

It enables the detector to balance active sensors and adjust sensitivities as needed, to make truly intelligent decisions regarding whether or not the data indicates a valid alarm condition – and if so, trigger an alarm.

Advanced verification mechanisms

The current generation of Sensor Data Fusion detectors, for instance from Bosch, feature advanced verification mechanisms, including Microwave Noise Adaptive Processing to easily differentiate humans from false alarm sources (e.g. ceiling fans or hanging signs).

For increased reliability, signals from PIR and microwave Doppler radar are compared to determine whether an actual alarm event is taking place. Additionally, the optical chamber is sealed to prevent drafts and insects from affecting the detector, while the detector is programmed for pet and small animal immunity.

Sensor cross-verification

Further types of sensors embedded in current and future generations of Sensor Data Fusion detectors include MEM-sensors as well as vibration sensors and accelerometers.

Ultimately, it’s important to keep in mind that the cross-verification between sensors serves to increase false alarm immunity without sacrificing the catch performance of actual intruders. It merely serves to cover various indicators of intrusion.

Protecting UNESCO World Cultural Heritage in China

Intelligent detectors equipped with Sensor Data Fusion are protecting historic cultural artifacts in China from theft and damage. At the UNESCO-protected Terracotta Warriors Museum site, one hundred TriTech motion detectors from Bosch with PIR and microwave Doppler radar technology safeguard the invaluable treasures against intruders.

To provide comprehensive protection amid the specific demands of the museum site, the detectors have been installed on walls and ceilings to safeguard the 16,300-square-meter museum site.

To ensure an optimal visitor experience without interference from glass walls and other barriers, many detectors are mounted at a height of 4.5 meters (15 feet) above ground under the ceiling. Despite their height, the detectors provide accurate data around the clock while exceeding the performance limits of conventional motion detectors, which clock out at a mere 2 meters (6 feet) catchment area.

Integrated video systems

The site also presents additional error sources such as large amounts of dust that can contaminate the sensors, as well as visitors accidentally dropping their cameras or mobile phones next to museum exhibits.

To distinguish these events from actual criminal activity, the intrusion alarm system is integrated with the museum’s video security system. This allows for verifying alarm triggers with real-time video footage at a fast pace: In the case of an actual alarm event, the system alerts the on-site security personnel in the control room in less than two seconds.

Added value beyond security

Sensor Data Fusion technology provides a viable solution for the rising number of error sources in the environment

As of today, Sensor Data Fusion technology already provides a viable solution for the rising number of error sources in the environment while providing legally compliant building security against intruders. In light of future developments, operators can leverage significant added value from upgrading existing systems – possibly without fundamentally replacing current system architecture – to the new detector standard.

Added value how? On one hand, the detectors can integrate with access control, video security, voice alarm, and analytics for a heightened level of security. These synergetic effects are especially pronounced on end-to-end platforms like the Bosch Building Management system.

On the other hand, the data streams from intelligent detectors also supply actionable intelligence to building automation systems, for instance as the basis for efficiency improvements and lowering energy consumption in HVAC systems.

New backward-compatible detectors

Bosch will release a new series of commercial detectors by end of 2021, based on the latest research on risk factors for false alarm sources in the environment and line with current legislation and safety standards. Throughout these developments, installers can rest assured that all new detectors are fully backward compatible and work with existing networking/architecture.

With that said, Sensor Data Fusion technology emerges as the key to more secure intrusion alarm systems today and in the future.

TriTech detectors from Bosch

For reliable, fail-proof alarms the current series of TriTech detectors from Bosch relies on a combination of different sensor data streams, evaluated by an integrated algorithm. These Sensor Data Fusion detectors from Bosch combine up to five different sensors in a single unit, including:

  • Long-range passive infrared (PIR) sensor
  • Short-range PIR sensor
  • Microwave sensor
  • White light sensor
  • Temperature sensor

Equipped with these sensors, TriTech detectors are capable of detecting the most frequent sources of false alarms; from headlights on passing cars to a mouse passing across the room at a 4.5-meter distance to the detector. What’s more, TriTech detectors provide reliable performance at room temperatures above 86°F (30°C) while fully guarding against actual intrusion and sabotage attempts from criminals.

Download PDF version Download PDF version

Author profile

Michael Reimer Senior Product Manager, Bosch Security Systems

Michael Reimer has been with Bosch since 2006. He started in the Regional Marketing group in NA for Intrusion products. Then he moved into the BU in the product manager role for intrusion sensors. He subsequently also took over the premises wireless portfolio and became a Senior product Manager, where he has been since. Prior to Bosch he worked for Leica Microsystems as a product manager for analytical instruments serving several industries including petrochemical, food and beverage, automotive, healthcare, etc. He graduated from the State University of New York at Buffalo in 1992 with departmental honors in a Bachelor of Science. He resides in New York state in the USA with his family of 4 children and wife of 22 years.

In case you missed it

The EU called for a ban on police use of facial recognition but not commercial use. Why?
The EU called for a ban on police use of facial recognition but not commercial use. Why?

Recently, the European Parliament called for a ban on police use of facial recognition. In the US, too, some cities have restricted police use of facial recognition. The first question that comes to mind is - why ban police from using technology that is allowed to private companies? Point of difference The key difference between the way police use facial recognition and the way commercial facial recognition products work is that: The police get a picture of a suspect from a crime scene and want to find out: "Who is the person in the picture?" That requires as wide a database as possible. Optimally - photos and identities of all the people in the world. Commercial facial recognition products such as those used by supermarkets, football stadiums, or casinos answer different questions: "Is the person in the picture on the employees' list? Is the person in the picture on a watch-list of known shoplifters?" To answer these questions doesn't require a broad database but rather a defined list of employees or a watch-list of specific people against whom there is an arrest warrant or a restraining order. Use of facial recognition AnyVision helps organisations leverage facial recognition ethically to identify known persons of interest "Facial Recognition Apps Should Be Provided to the Police with an Empty Database". This is exactly the subject of the open letter sent by AnyVision, to the British Biometrics and Surveillance Camera Commissioner, Prof. Fraser Sampson, titled: "Facial Recognition Apps Should Be Provided to the Police with an Empty Database". AnyVision recently raised $235M from Softbank and another leading VCs is a visual AI platform company that helps organisations across the globe leverage facial recognition ethically to identify known persons of interest, including shoplifters, felons, and security threats. Ethical use of facial recognition AnyVision CEO Avi Golan wrote, "The ethical use of facial recognition is a thorny one and requires a nuanced discussion. Part of that discussion has to explain how facial recognition works, but, just as important, the discussion must also involve how the technology is used by police departments and what checks and balances are built into their processes.” “We recommend building their watchlists from the ground up based on known felons, persons of interest, and missing persons. Some facial recognition solution providers have scrapped billions of photos and identities of people from social networks, usually without their consent." "Unfortunately, this method of facial recognition has justifiably angered privacy groups and data protection agencies around the globe and damaged the public trust in accuracy and reliability of facial recognition systems.” Preventing invasion of citizen’s privacy We believe an unjustified invasion of citizens' privacy can be prevented, false arrests can be reduced" “We believe that lists of suspects should be limited and justified. In this way, unjustified invasion of citizens' privacy can be prevented, false arrests can be reduced and public confidence in technology can be increased.” Golan added: "AnyVision is willing to share its industry insights and best practices from our vast research experience with leading global players, including name-brand retailers, global hospitality and entertainment companies, and law enforcement agencies from around the world.” Balancing public order and crime prevention “If the regulations set forth by Surveillance Camera Code of Practice are committed to the principles outlined above, then law enforcement agencies can strike the right balance between the need to maintain public order and prevent crime with the rights of every person to privacy and non-discrimination before the law." Recently Clearview AI CEO told Wired; the company has scraped 10 billion photos from the web - 3 times more than was previously known.

Dahua Technology shows how intelligent cameras enhance safety in nursing homes
Dahua Technology shows how intelligent cameras enhance safety in nursing homes

Patient falls in nursing homes are a serious problem. In the United States, for example, around 1,800 elderly people, living in nursing facilities, die each year from injuries related to falls, according to the Nursing Home Abuse Center. Those patients who survive their injuries often have a reduced quality of life and suffer some form of permanent disability. Rise in nursing home patient falls Figures show that between 50% and 75% of nursing home residents suffer falls each year, twice the chances of falling when compared to seniors who live in a regular residential community. It has been a prevalent challenge to detect falls quickly and effectively, especially when these occur in residents’ bedrooms. In the United Kingdom, the Care Quality Commission has recognised that the use of CCTV may be one of the best ways to ensure safety and quality of care. However, using video surveillance also brings into question other security issues, such as privacy and data protection. Dahua’s WizMind technologies WizMind embraces human-based AI (Artificial Intelligence), for a whole host of applications across verticals This is where Dahua Technology’s WizMind technologies come into play. WizMind embraces human-based AI (Artificial Intelligence), for a whole host of applications across verticals, such as retail, energy, finance, transportation and of course, health and social care. Specific to the health and social care sector are deep-learning algorithms, to protect the privacy of the face and body in real-time, and stereo analysis, which combines dual-lens cameras with three-dimensional scene analysis, in order to detect sudden physical movement, such as falls. Stereo video analysis The growth of AI applications has enabled the greater availability of 3D scene analysis solutions, thereby enabling objects and people to be analysed in three dimensions. Dahua Technology’s stereo analysis uses two lenses, in order to capture separate images of the same scene. It then computes the ‘optical parallax’ of spatial points in the two images, providing 3D information of the scene. The stereo vision mimics the depth of view that comes from humans having two eyes, known as binocular vision. Combined with deep-learning algorithm Combined with a deep-learning algorithm, stereo analysis can recognise event patterns, such as falls and other movement-based behaviours, such as people approaching, the detection of an abnormal number of people in an area, and violent behaviour. In nursing and care homes, stereo analysis cameras can help staff monitor residents, in case of emergency and respond to residents’ problems, such as tripping and falls. The cameras can view all three dimensions of subjects and together with its deep-learning algorithm, can immediately alert staff to any unusual or sudden movement, such as would be evident in a fall. Cameras in communal areas and bedrooms With cameras situated both in communal areas and in bedrooms, the staff is able to respond quickly to incidents With cameras situated both in communal areas and in bedrooms, the staff is able to respond quickly to incidents, which may otherwise stay undiscovered for hours. An example of such a scenario is a nursing home in Singapore, which has a capacity of around 400 beds and is divided into 14 separate living environments, with each designed to be a home-like living area. Dahua cameras with intelligent fall detection technology Dahua cameras, such as IPC-HDW8341X-BV-3D with intelligent fall detection technology were installed, including the provision of 167 stereo analysis cameras inside each bedroom. These trigger an alarm, in the case of incidents, such as a fall, allowing immediate response by staff. Not only does this enhance the well-being and safety of residents, but it also can reduce the nursing home’s labour costs. In addition, Stereo Analysis can also be applied in other application scenarios. An underground unmanned bicycle parking garage in Amsterdam, for instance, has installed Dahua Technology’s behaviour analysis cameras, to detect abnormal events and prevent accidents, such as people tripping and falling, or suspicious individuals wandering around the area. Privacy Protection 2.0 technology While monitoring their situation inside the nursing home, Dahua also adopts Privacy Protection 2.0 technology that features masking of human face and body, to protect the residents’ privacy. It involves the restriction of what can be seen in video images and applies equally to live, and recorded images. Digital masking takes place on the front-end device (e.g. network camera). Dahua’s Privacy Protection 2.0 provides real-time occlusion of the body and face and enables users to access recorded videos, without having to overlay faces with mosaic masks. It also offers additional occlusion options, such as irregular polygons, mosaics and coloured blocks, and allows code exporting based on specified targets, ensuring the privacy of subjects. Privacy and security in evidence collection Stereo video analysis and privacy protection come into their own in nursing homes and healthcare facilities Benefits offered include non-pixelated human targets, allowing for privacy and security in evidence collection. The technology also allows for face and human attributes analysis, without breaching people’s privacy, making it ideal for nursing homes. Stereo video analysis and privacy protection come into their own in nursing homes and healthcare facilities. It allows the close monitoring of residents or patients to help ensure their well-being and safety, while at the same time protecting the privacy of often vulnerable individuals. Dahua TechMonth As part of the Dahua TechMonth, this blog highlights how Dahua’s stereo analysis technology, combined with privacy protection, can provide a valuable tool to help staff respond to incidents quickly and efficiently, including falls, without infringing on people’s data protection rights. In the next blog, Dahua Technology will be discussing the WizMind application of human metadata, enabling users to maximise situational awareness and analysis of events. 

Eagle Eye’s Uncanny Vision deal highlights value of combining AI and cloud
Eagle Eye’s Uncanny Vision deal highlights value of combining AI and cloud

The trend of video customers moving to the cloud has reached a tipping point. At the same time, artificial intelligence (AI) is being adopted on a massive scale. Combining the two trends adds a higher level of value than either component individually. Merging the power of AI and the cloud is a driving force behind cloud surveillance company Eagle Eye Networks’ acquisition of Uncanny Vision, an AI and video analytics company headquartered in Bangalore, India. Expensive AI resources Cloud systems empower customers to leverage AI without having to install and program complicated and expensive hardware, in effect stripping away the barriers to entry that customers face when seeking to embrace AI. The cloud also enables customers to share expensive AI resources. One of the key components is ease of deployment – click, click and turn on the AI for any camera" Simplicity of implementation is crucial to the combined value proposition of Eagle Eye Networks and Uncanny Vision. “One of the key components is ease of deployment – click, click and turn on the AI for any camera (in a cloud system),” says Dean Drako, Eagle Eye Networks CEO. There is also a benefit of having AI systems networked, enabling 25 banks to perform facial recognition of customers from a single cloud-based system, he adds. A transition is also under way in the perception of AI. Video surveillance applications While previously it was seen as an add-on to surveillance systems, now it is seen as a very desirable feature on any system. “Centralised management of the cloud benefits the AI database,” says Drako. “In a project built around licence plate recognition (LPR), for example, all the data goes up to the cloud into a single database, and the customer can get a mobile view of everything going on across the world. You can’t do that without the cloud. And AI for LPR is more accurate.” Uncanny Vision’s targeted focus on AI for video surveillance applications was one factor that attracted Eagle Eye Networks to make the acquisition, says Drako. In contrast, some other companies have embraced broader applications of video AI. Uncanny Vision also has more customers using their system in real-world applications than competitors. Finally, the acquisition will help to expand Eagle Eye Networks’ presence in the LPR market, where Uncanny Vision is especially strong. Improving business operations The 60 employees at Uncanny Vision are mostly engineers and programmers Uncanny Vision’s deep learning algorithms enable recognition, identification, and prediction, improving business operations, customer service, and site safety. Applications include smart parking, retail, smart cities, ATM monitoring, worker safety and perimeter security. The 60 employees at Uncanny Vision are mostly engineers and programmers. “These guys understand how to translate AI algorithms to run very efficiently on various types of hardware,” says Drako. “They optimise how they get the code to run so we can implement in the cloud cost-effectively. They do it at a modest cost to make it more accessible. They understand how to deploy software for high performance on low-cost hardware.” For Uncanny Vision, the new ownership provides more reach. “We have a huge channel and a huge brand,” says Drako. “They are strong technical guys who need a sales and solution channel.” Video analytics solutions Even in light of the acquisition, Eagle Eye Networks will continue to provide a selection of third-party AI and video analytics solutions to customers. Use of AI and video analytics is specific to the application and business needs of each customer. Use of AI and video analytics is specific to the application and business needs of each customer In addition to AI functionality, systems need a ‘business logic’ component that drives how that capability is integrated into a system. System needs vary widely by vertical market, and many third-party vendors are focused on a specific vertical and how AI can benefit that market. Recurring monthly revenue “Third parties can provide analytics and the business logic, which is different for a factory, an office building or for a drive-thru restaurant,” says Drako. “The market is looking for many solutions, and one company couldn’t own a majority of them.” To ensure flexibility, Eagle Eye Networks will accommodate third party solutions, deploy their own analytics, or leverage analytics embedded in cameras. For Eagle Eye Networks’ dealer and integrator customers, the expansion into AI presents a new opportunity for recurring monthly revenue (RMR) and provides greater value to customers. Drako says the impact of the acquisition will be global as AI applications grow in popularity worldwide.