securitylinkindia

MassMediaLink India LLP SecurityLink India

Appointment of Independent Non-Executive Director

Halma, the FTSE 100 global group of life-saving technology companies, recently announced the appointment of Dharmash Mistry as an independent non-executive Director, effective 1 April 2021. Dharmash will also be a member of Halma’s audit, remuneration and nomination committees. Dharmash brings a wealth of experience as a venture capitalist, entrepreneur and non-executive director. He has extensive experience spanning management of digital assets, digital marketing, evaluating digital business models and driving digital transformation. Dharmash’s venture capital roles have seen him leading investments in disruptive technology companies and early stage ventures. His earlier executive career included roles with Procter & Gamble, Boston Consulting Group and Emap plc. Subsequently, he has been a partner at venture capital firms Balderton and Lakestar. Dharmash has also had a diverse portfolio career acting as a non-executive director at Dixons Retail plc, Hargreaves Lansdown plc and, currently, non-executive director at the BBC, British Business Bank and is Chair of blow LTD. Paul Walker, Chair, commented, “I am delighted that Dharmash has agreed to join the Halma Board. Dharmash brings in-depth knowledge and experience of digitalisation and developing new business models which will undoubtedly be of great value to Halma.” There are no further details to be disclosed for Dharmash Mistry under Listing Rule 9.6.13R.  

Read More

Prama Hikvision Introduces AcuSense Video Security Cameras Empowered by Deep Learning Algorithm for Varied Application Scenarios

Prama Hikvision has recently introduced its wide range AcuSense cameras empowered by the deep learning algorithm for various critical application scenarios. AcuSense technology enables security personnel to focus on human and vehicle events rather than insignificant objects, so they can act more efficiently, which helps save time and costs, while end-users can get full control of their security system anytime, from anywhere. Hikvision AcuSense products were introduced with the idea of making intelligent alarms and services available to small businesses and residential customers for the first time. A sense of safety is one of the most basic human needs, personal and property safety are integrated into that sentiment as well. And this is exactly why people install security systems in their homes and businesses. Compared to conventional sensor-based alarm systems, a surveillance system that utilizes cameras has several advantages – the ability to watch events in real-time, obtaining key data around those events, and providing solid and accurate evidence for law enforcement. By adding a touch of intelligence to cameras and video recorders, AcuSense technology makes these products a perfect choice for an accessible and intelligent security system. The magic behind it all – Deep learning algorithm As its name implies, Hikvision AcuSense technology provides accurate sensing in security hardware. Empowered by deep learning algorithms, AcuSense technology distinguishes people and vehicles from other moving objects. Focus on the right events – Human and vehicle intrusion The most common concerns in perimeter protection are trespassing and vehicle break-ins. AcuSense technology helps focus on human and vehicle events in two ways – the device will only trigger an alarm when the preset intrusion type (human or vehicle) takes place, and videos related to alarm events are sorted into human and vehicle categories for easier footage searches. Accurate alarms for humans and vehicles A video security camera would usually ‘see’ many events, ranging from people crossing a perimeter to animals that accidentally enter. What happens when a person wants to level-up his protection and get a notification when a perimeter-crossing event takes place? For most security events, he will search for video clips that captured human or vehicle activities. With AcuSense devices, this gets easier. Video clips are already sorted into the ‘human files’ and ‘vehicle files.’ Just to simply click one of these categories and use time or location data to quickly locate the clip that he wants. Compared to the conventional method which displays all video files at once, AcuSense makes searching more efficient. Users can focus on alarms triggered by humans and vehicles while false alarms triggered by small animals or other irrelevant objects are vastly reduced. Visual and auditory warning On-site response and deterrence methods using visual and customizable auditory warnings to add another layer of protection. Search targets quickly by type Video clips are sorted by human and vehicle categories, and object classification vastly improves search efficiency. Improved alarm accuracy The latest Hikvision AcuSense devices are engineered with an upgraded deep learning algorithm, which analyzes live video streams and labels them as ‘human,’ ‘vehicle,’ or ‘other events.’ Those labeled as human and vehicle will trigger alarms for security staff, while other events such as rain drops, animals, or the movement of foliage, for example, will be drastically disregarded. The result is a striking reduction in false alarms – now with an accuracy approaching 98%. In this way, security personnel can focus on genuine security issues and take action. Additionally, related videos are automatically sorted by categories for easier search. Enhanced motion detection with human/ vehicle classification Customers familiar with motion detection will appreciate the capabilities of AcuSense technology as well. Taking users’ habits into full consideration, Hikvision designed AcuSense products to integrate human and vehicle classifications with motion detection. More specifically, when motion is detected, the system analyzes whether or not it is associated with a human or a vehicle, and whether an alarm should be triggered. So, when users enable the motion detection function, they can enjoy the same level of alarm accuracy afforded by Hikvision’s AcuSense technology. Flashing light and two-way voice conversation When real-time deterrence is needed, Hikvision also offers camera models with a flashing light and auditory warning. As soon as an alarm is triggered, the built-in light flashes. Simultaneously, security personnel can communicate with the person who triggered the alarm to confirm their authorization, thanks to the built-in speaker and microphone in the camera. Of note, the latest AcuSense cameras even support customized audio tracks, which can be pre-recorded to suit various environments. Better performance in low-light environments The latest AcuSense camera lenses are equipped with an aperture reaching up to F1.4. This technology allows more light to enter the lens, for optimized image brightness, and better performance in low-light environments. Larger detection area Compared with previous AcuSense cameras, this new generation extends target classification distances from 10, 15, or 22 meters to 20, 25, or 30 meters, depending on the model. Customers can choose from 2MP, 4MP, or 4K resolutions, as well as a dome, turret and bullet housings to suit their specific installation requirements. Application Scenarios Alarm receiving center/ monitoring center Security monitoring is never an easy task, especially when it is made responsible for watching over multiple locations at the same time. AcuSense products can help ramp up efficiency and improve workflow. For burglar alarm service: Accurate alarm for human intrusion events only. For playback and video search: Quick search for human or vehicle-related video through sorted folders. Villas Whether one chooses to keep an eye on the house himself or hire a professional service provider to look after his home, there are two functions he will surely want to have: Prompt notification via smartphone: Check alarm information and view live video feed. Light and sound intruder deterrence: React to intrusion events with a flashing light and customizable siren. Factories and warehouses Factories and warehouses store high-value raw materials or commodities. Security here is crucial. However, there is usually only limited manpower to perform such tasks. AcuSense devices offer…

Read More

FIRE INCIDENT IN A HOSPITAL

ANIL PURI CMD, APS GROUP A thought leader and an action catalyzer rolled into one – Anil Puri is a rare combination of a visionary, and one who has mastered the art of strategic and tactical thinking to the core. He has been using this combination to seed new ideas and to lead them to their implementation onground. This has been a consistent feature of his career. He has rich experience of approximately 35 years in corporate in diverse domains & from functional managerial level to apex as chairman of a corporate group. His acumen for handling crisis management has prompted him to share his exclusive and niche experiences. Here he will be discussing the topic of Disaster Management which has been one of his favorite subjects. In the series of the articles on Disaster Management, the fire incident of Dec 2011 in AMRI Hospital, Kolkatta has been picked up as a classical case to drive home the key and essential issues.   INTRODUCTION Socio-economic variables depict a high concentration of population in the cities in terms of density per house. Kolkata has the highest number of persons per household (11 person/ household) (IRAD Report, 2013) which renders it in most vulnerable situation due to this kind of fire outbreak. Advanced Medicare and Research Institute (AMRI) is a private hospital chain jointly promoted by the R. S. Goenka led Emami Group, the S. K. Todi led Shrachi Group of companies, and State Government of West Bengal in 1996. The hospital chain has its head office and 6 branches in Kolkata, West Bengal, India, and 6 branches in Bangladesh. AMRI Hospital is ISO 9001:2000 certified, and is located in a densely populated area of at Dhakuria in South Kolkata. SEQUENCE OF EVENTS I n the early hours of the morning on December 9, 2011, a massive fire broke out at annex building of AMRI Hospital Dhakuria, Kolkata. The fire was first noticed by local residents at around 2.30 am. Fire Control Room, Kolkata was informed about the incident at 4.10 am which responded immediately and the fire services arrived at the site within 20 min. Though the fire was primarily restricted within the basement of the hospital, but the poisonous smoke was sucked by air conditioning ducts that carried it through the rooms and the corridors of the seven-story centrally air conditioned hospital. Entire hospital building was filled with thick pile of smoke, caused tremendous suffocation for all the indoor patients. Ninety people choked to death, many of them are in their sleep or were not in condition to even escape. Among the list of dead persons, there were nationals from other countries and states within India. There were victims from Bangladesh, Bihar, Tripura and two nurses from Kerala. As reported by the media, local people noticed the fire at hospital building around 2.30 am and tried to enter the hospital building for rescue. The relatives of the patients, who were waiting outside the hospital overnight also tried to help the trapped patients inside the hospital. The security staff of the hospital stopped the entry in mass into the AMRI annex building, and tried to douse the fire with their own available resources. Fire department rushed into action after receiving the dis-tress call at 4.10 am and reached the spot with available sophisticated firefighting equipment. Around 25 fire engines and hydraulic ladders were used for the rescue and dousing of the massive fire and smoke. It was reported by the Joint Commissioner of Police (Crime) that none of the smoke alarms got activated even when smoke started billowing out of the basement. It seems that they had been in switched off mode because they would go off at the slightest smoke and disturb the patients. The sprinklers, gas jets and other water re-leasing equipment that are meant to fight fire, were defunct and none of them went off to prevent the fire. Un-official reports are such that the basement was being used as a smokers’ corner, keeping the fire alarms in switch off mode. This was the second fire at AMRI hospital in three years. The fire services department, government of west Bengal had warned AMRI Hospital in September, 2011 about the inappropriate and dangerous use of the hospital basement. It had served a notice to the hospital authorities questioning the fact that instead of parking cars, the hospital was using its basement for storing empty and filled up LPG cylinders, torn mattresses, and wooden boxes and had converted the entire space into a storehouse. With a December 5 deadline, the hospital was allowed three months’ time to comply, but it did not. The enforcement of law is also in question. CAUSES OF FIRE INCIDENT Though the specific cause of fire could not be established, the director of the fire department in his opinion stated that the fire was most likely caused due to an electrical short circuit in the basement car park. The combustible items like empty and filled up LPG cylinders, PVC pipes, rejected mattresses and wooden boxes immediately got the flame. However, the fact is that the fire didn’t spread to the other part or level of the hospital and was confined to the basement only. As the hospital was centrally air-conditioned, the smoke started billowing out of the basement and spread fast to all the floors through the air-conditioning duct. Soon thereafter, the air-conditioners went off because of the power cut and smoke started accumulating into the hospital rooms and corridors. The centrally air-conditioned hospital didn’t have windows and glass façade walls. As a result, smoke could not be ventilated outside the building. A critical component like mechanical ventilation of centrally air-conditioned buildings was missing in the hospital building. The fire brigade later broke open the glass facade to help the gas escape, though same was too late. ROOT CAUSE ANALYSIS The basement was full with inflammable articles like paper, cotton, mattress, chemicals which amounted to blatant violation of fire safety practices.  Smoke detector and fire…

Read More

8 Networking & Security Trends to Watch Out in 2021

Shibu Paul, Vice President – International Sales at Array Networks Vulnerability is a costly affair for organizations. Every data stored within the organizations carries its own value, but without the right networking and security measure, all efforts to keep the data safe from attackers come to nought. Every year companies face new forms of threat and experts come up with new ways to fight those threats, for example, the pandemic witnessed in 2020. While the pandemic is receding in India, companies are still contemplating returning to office. Remote working is now a part of the work environment. Even new recruits are being given an option to work remotely by many. Strong networking is now necessary more than ever and 2021 is ready to witness trends in networking and security to fight threat actors. So what are the networking trends of 2021? Network automation: Applications in any organization today range from traditional to cloud-native. In situations like these, it is not easy to manage the applications. So to have speed, agility and consistency in the operations organizations resort to network automation. According to a recent survey the pandemic has boosted network automation to the top 70 percent to help organizations navigate the changes. Zero trust: Traditional security parameters are time and again proved to be ineffective with more high-tech targeting tactics. In order to fight threats at micro-level while authenticating every request to gain access into the network at every point, experts advise on implementing zero trust. By 2027 at 19.71% CAGR, the zero trust security market is projected to reach $94.35 Bn and this is the indication of the important role zero trust is to play. SD-WAN: Managing a branch of networks is not a simple task and neither is cloud connectivity. To manage several networks and for faster cloud connectivity, organizations are now resorting to a Software-defined wide area network (SD-WAN) which is a virtual WAN architecture. Experts believe that due to unforeseeable reasons by 2020 the demand for SD-WAN had reduced; however, with the new work culture like remote working or hybrid work environment the demand is expected to increase. The work processes shifting from traditional to cloud is also an indication of the possibility of SDWAN’s demand increasing. Cybersecurity mesh: To achieve scalable, flexible and reliable security, the concept of cybersecurity mesh is popular. For intensified remote working like the current times, there is a need to protect data from external and sometimes internal threats and cybersecurity mesh is the right approach. IoT and network edge: The point where an enterprise-owned network connects to a third-party network is called network edge. With the overflow of data, many data centers and devices experience strain. To remove this strain from DCs, the network edge physically moves the computation part from DCs to the edge of the network. By offloading network traffic not only can edge computing conserve the network resources, it will in turn also reduce network latency and bottlenecks. SASE: By implementing Secure Access Service Edge (SASE) organizations are revamping their network architecture. With SASE companies can now allow remote working, enable IoT endpoints and aid teleworkers. SASE is the closest solution for organizations that have distributed workforce but decentralized infrastructure as they would need a different security posture as part of that architecture. Internet of behaviors (IoB): IoB which is an extension of IoT refers to the interconnection of devices resulting in a vast variety of new data which links to the behaviour of people. Gartner predicts that by 2023 individual activities of 40% of the global population will be tracked digitally to influence behavior. To manage such a vast variety of data a strong network solution is required which would avoid the websites or the organization’s platform from collapsing. Hybrid work model: The hybrid work model existed before the pandemic hit the world, however, it became necessary and relevant with the onset of the pandemic. The key to the hybrid work model is digitalization and for a strong digitalization process, networking is of utmost importance. For a strong hybrid work environment the network products and services should be updated and state-of-the-art, hence making the work model successful with reduced risk factors.  

Read More

Avenar all-in-one 4000 Signaling Device Sets New Standards in Fire Protection

With ‘Avenar all-in-one 4000,’ Bosch has introduced a new range of signaling devices that combine visual and audible alarms in a single unit. Optionally, any fire detectors from the Avenar family can also be combined with the signaling device in one unit, creating a cost- and space-saving complete solution that significantly reduces installation and maintenance effort. The signaling devices are certified to EN54-3 and EN54-23 category C, for ceiling mounting, and W, for wall mounting. Due to IP 42 protection they are suitable for almost all indoor applications. Visual and audible alarm with minimal power consumption Complete solution through optional combination with all Avenar fire detectors. Up to 125 devices per ring bus due to innovative power concept. Simple installation by means of pre-assembly and plugin terminals. Up to 125 devices on one ring bus Avenar all-in-one 4000 features a low power consumption of 865μA, allowing up to 125 devices to be installed on just one ring bus. The devices do not require complex and expensive E-30 cabling to ensure functional integrity and uninterrupted alarming in the event of a bus failure. This is possible thanks to the integrated battery with a service life of up to 10 years. “With up to 125 devices on one ring, we are defining a new category in fire protection,” commented Sebastian Wehr, Product Manager at Bosch Building Technologies, “For planners, installers and operators, this opens up completely new possibilities and significant savings potential.” Focus on usability While developing Avenar all-in-one 4000, Bosch placed particular emphasis on ease of installation and handling as well as flexible deployment options. For example, the signaling devices can be pre-assembled and are equipped with plug-in terminals, which significantly simplifies and speeds up installation compared to screw terminals. For different areas of application, users can choose between three intensities for both visual and audible alarms. Optionally, any fire detector of the Avenar family can be combined with the signal transmitter. This allows fire detectors to be replaced separately as part of maintenance if required, even without replacing the signaling device, saving operating and maintenance costs. Wide range of applications The combination of visual and audible alarms makes Avenar all-in-one 4000 particularly suitable for use in office buildings as well as in buildings with a lot of public traffic. It is in such environments that the new alarm devices really come into their own, as the dual alarm with visual and audible signal enables all persons to be warned – including the elderly or persons with disabilities. Due to the high protection class IP 42, even demanding production environments can be secured. Avenar all-in-one 4000 is available in four versions – in combinations of red or white housing with red or white LED flashing light for visual alarm. The service life of the battery and detectors are matched to each other, so that no additional maintenance is usually required when the detector is replaced at regular intervals in accordance with the applicable standards. The new devices are integrated into Bosch’s ‘safety systems designer,’ a tool for easy planning of fire alarm systems.  

Read More

Onboard Camera for Exterior Side View Monitoring and Identification of Maintenance Needs

Optimized for the transportation industry, it complies with industry standards including EN50155 and EN45545-2. The camera is specially designed for side view monitoring on buses, trains, and transportation vehicles. It can also be used for identifying maintenance needs on rolling stock, for example, wear and tear of pantograph collector strips. It offers superior image quality in HDTV 1080p. With forensic WDR it ensures high-quality images even when there’s both dark and light areas in the scene. Plus, with Lightfinder it delivers sharp, color images in poor lighting conditions. With built-in IR illumination, it can be used for surveillance in complete darkness. Key features include: Complies with EN50155 and EN45545-2. IR illumination and EIS. Lightfinder and forensic WDR. Low latency mode. Signed firmware and secure boot. This robust product features enhanced security functionality such as signed firmware and secure boot to prevent unauthorized access and safeguard the system. For added peace of mind, shock detection sends a notification if the camera has been hit.  

Read More

EZVIZ C3N Smart Wi-Fi Camera

It’s difficult to find an outdoor wireless security camera, which works well in outdoor conditions. Due to poor Wi-Fi connectivity most wireless cameras are meant to be installed in the close proximity of the Wi-Fi internet router. To overcome the above mentioned challenges EZVIZ has come up with C3N smart wireless camera. The C3N is the ideal choice to secure one’s outdoor premises – parking areas, gardens, lawns, lobby, entry/ exit points, pathways etc. C3N is a 1080p full HD resolution wireless camera. This helps provide a super sharp, high quality video during the day as well as during the night. C3N is equipped with two built-in spotlights and two infrared (IR) lights which helps provide sharp color images even in pitch-black darkness and more than just helping produce color night time imaging. The spotlights can also be used as floodlights to brighten hidden areas around the property. The C3N has smart night mode whereby it automatically switches from black-and-white monitoring to color monitoring, turning on the spotlights when it detects human movement. The alert video will be recorded in full-color, so the user gets all the details needed. The C3N has the intelligently embedded AI algorithm which detects the motion of humans in real-time and the user will be alerted immediately on his smartphone. The C3N is powered by advanced PQ technology, which senses the actual environment and helps in automatically adjusting the image brightness to avoid overexposure. As C3N has a 2 inbuilt spot lights, the camera will automatically trigger and flash two spotlights to scare off and deter any unwanted visitors. What’s more, when the person turns their head to the flashing light source by instinct, they will be clearly recorded on camera. The C3N’s built-in noise-cancelling microphone picks up clear audio up to 5 meters (16.4 ft.) away. Now one can hear and see what’s happening in the backyard no matter where he is. The C3N’s whole metallic enclosure provides stronger protection and enhanced heat dissipation. Additionally, with an IP67 rating, it can withstand rainy, sunny, stormy, and even snowy days. C3N is empowered with advanced H.265 video compression standard, which helps to achieve the best video quality with only half the bandwidth and half the storage space compared to the previous H.264 video compression standard. The camera has built in micro SD card slot wherein a micro SD card can be inserted of up to 256GB. Key features: Full HD. Z Color night vision. Z IR night vision up to 30m. Z Digital WDR. Z AI powered person detection. Z H.265 video compression. Z WiFi 2.4GHz with dual external antennas. Z IP67 dust and water protection. Z Supports micro SD card (up to 256GB). Z Weight – 422gms. In a nutshell, C3N is the ideal choice to secure all your outdoor premises.    

Read More

BrainChip’s Success in 2020 Advances Fields of On-Chip Learning and Ultra-Low Power Edge AI

BrainChip Holdings Ltd., a leading provider of ultra-low-power, high-performance AI technology, ended the 2020 calendar year having made significant strides in the development of its technology backed by the launch of its early access program (EAP), availability of Akida™ evaluation boards, new partnerships, and expansion of its executive leadership and global facilities. The company’s EAP was launched in June targeting specific customers in a diverse set of end markets in order to ensure availability of initial devices and evaluation systems for key applications. Multiple customers have committed to the advanced purchase of evaluation systems for a range of strategic edge applications including advanced driver assistance systems (ADAS) and autonomous vehicles (AV), unmanned aerial vehicles (UAV), Edge vision systems and factory automation. Among those joining the EAP include VORAGO Technologies in a collaboration intended to support a Phase I NASA program for a neuromorphic processor that meets spaceflight requirements. BrainChip is also collaborating with Tier-1 automotive supplier valeo corporation to develop neural network processing solutions for ADAS and AV. This year, BrainChip partnered with Socionext, a leader in advanced SoC solutions for video and imaging systems, to provide a complete low-power AI edge network for vision, audio and smart transducers without the need for a host processor or external memory. The company’s partnership with Magik Eye Inc., developers of revolutionary 3D sensors that change how machines see the world, combines the best of AI with 3D sensing to provide a total 3D vision solution to customers for fast 3D object detection and recognition in applications, including robotics, automotive and emerging consumer products such as AR/ VR and others. BrainChip began shipment of evaluation boards for the Akida Neuromorphic System-on-Chip (NSoC) in November. The evaluation board availability complements the company’s Akida development environment (ADE), a robust development environment that allows potential customers to design a neural network as a Convolutional Neural Network (CNN) and utilize the ADE workflow to convert the network to an eventbased CNN or develop a native Spiking Neural Network (SNN). To support BrainChip’s growth throughout the year, the Company hired Rob Telson as Vice President of Worldwide Sales to lead commercialization efforts of the Akida Technology. He is also building an applications engineering team to best support customers and augment the company’s worldwide design, development and research groups. Todd Vierra joined the company as Director of Technical Sales, focusing on strategic customer adoption and implementation of the Akida neuromorphic processor in industries including aerospace, autonomous vehicles, medicine, cybersecurity and smart ‘edge’ devices, such as sensors and cameras. The personnel moves complement the company’s expansion with a Software Development Center in Hyderabad, India. The development center will concentrate on software and firmware developments to support Akida’s commercial implementation. “This past year saw significant progress in the development of the Akida technology in terms of both market readiness and the increase in market possibilities that the solution will provide immediate impact in,” said Louis DiNardo, BrainChip CEO, “From adding partners to opening up our Akida Development Environment and Early Access Program, we are making consistent, measurable progress in bringing AI to the edge in a way that existing technologies are not capable. During December we signed an agreement to license the Akida IP to a major Japanese semiconductor company. We look forward to continuing this momentum throughout the upcoming year and beyond.” The Akida Neural Processor technology, which is implemented in the NSoC, is a revolutionary advanced neural networking processor that brings artificial intelligence to the edge in a way that existing technologies are not capable. The solution is high-performance, small, ultra-low power and enables a wide array of edge capabilities. The Akida NSoC represents a revolutionary new breed of Neural Processing computing devices for Edge AI devices and systems. Comparisons to leading DNN accelerator devices show significantly better images/ second/ watt running industry standard benchmarks with MobileNet, MobileNet-SSD and Key Word Spotting, while maintaining excellent accuracy. The Akida NSoC is designed for use as a stand-alone embedded accelerator or as a co-processor. It includes interfaces for ADAS sensors, audio sensors, and other IoT sensors. It also has highspeed data interfaces such as PCI-Express, USB, 12S and 13C. An on-chip MPU is used to control the configuration of the Akida Neuron Fabric as well as off-chip communication of metadata. The Akida NSoC represents a scalable solution utilizing a built-in serial chip to chip connectivity to allow up to 64 devices to be arrayed for a single solution.  

Read More

Into the Future: Bosch, Playing a Major Role Towards Connected Living Spaces

With the world on the cusp of a digital revolution, it is no surprise that only intelligent buildings that perform efficiently, financially, and enhance well-being will be fit for the future. Aligned with this notion, Bosch India offers integrated connected building solutions to ensure the safety and security of lives, buildings, and assets. Bosch centers its connected building solutions around making buildings secure, more livable, and enjoyable for inhabitants. Bosch’s building technologies are made for an intelligent and smart future. Bosch developed Building Technologies are coupled with IoT solutions that provide an integrated platform for security, safety, and communication needs. The connected building solutions cover commercial and residential buildings including shopping malls, offices and urban development spaces. Smart building capabilities delivered by Bosch offer greater operational efficiencies in facilities management and new innovative services to end-users. Bosch has invested in engineering infrastructure in India and will continue to invest in the future too towards creating future-proof solutions for a better life. Many of Bosch’s communications products are locally manufactured and plans are in place to extend this to portfolios of security and safety too. Bosch developed building technologies provide an integrated platform for security, safety, and communication needs in private and public places. Bosch’s end-to-end solution for office buildings help save on costs, create a pleasant working environment, and aid towards well-being of employees. Bosch camera trainer integrated with deep machine learning can teach cameras to detect objects or situations that would have previously gone undetected. “As cities in India evolve and energy demands surge, planners, developers, utilities and governments are looking towards ‘intelligent’ buildings that operate more efficiently while keeping the inhabitants secure in these spaces. Bosch’s connected building solutions cover almost every area within a building, both residential and commercial – from the inhabitant’s safety, security and comfort. We will continue to leverage our deep domain knowledge and expertise to continue disrupting the security and building technologies space,” said Viswanatha Raju, Head – South Asia Region, Bosch Building Technologies. Bosch’s end-to-end solution for office buildings helps save on costs, create a pleasant working environment, and aid employee well-being. Bosch Camera Trainer integrated with deep machine learning can teach cameras to detect objects or situations that would have previously gone undetected. Based on examples of target objects and non-target objects, this module uses machine learning to allow users to define objects that are of interest to them or things that are critical for them and generate detectors for the same. Bosch’s video-based fire detection is the perfect answer for facilities used for industry, transportation, warehousing, and utilities such as energy to minimize detection time with low false alarm rates. Improving the rescue chain through fast detection and situational awareness protects lives and minimizes damage. Bosch additionally offers wired and wireless conference systems for meetings of all sizes that provide excellent sound quality while keeping a safe distance. Further, solutions from building technologies have numerous applications in helping to manage the current pandemic situation, in areas of social distancing, crowd management, touchless access, and touchless human skin temperature measurement.  

Read More

The Benefits of Deep Learning Driven Intelligent Video Analytics

Rahat Jain Managing Director at IDIS India In recent years, the terms ‘intelligent’ and ‘artificial intelligence (AI)’ have been applied to many different types of security systems, but with little apparent agreement when it comes to a precise definition of what AI is. This is despite the fact that 71% of security professionals report that AI video analytics already provides value to their operations or that they expect it to in the future, according to the IFSEC Global Video Surveillance Report 2020, which analyzed feedback from over 700 security respondents globally. So, it’s important to understand that not all solutions labelled as ‘intelligent’ or ‘powered by AI’ are designed to the same standard or deliver equal value. Many of the early iterations of video analytics rely on Binary Large Object (BLOB) technology. This is found on most modern IP cameras, which is why they are commonly referred to as ‘blob type’ analytics. These are formulated to detect an event such as a virtual line cross; they detect and track objects as ‘motion blobs’ and distinguish them from smaller binary objects. For many applications these are still useful. But video analytics capability has moved considerably beyond this. Today security departments can take advantage of deep learning that leverages neural networks made up of multiple layers of algorithms and advanced processing. This is now driving what is widely accepted to mean true intelligent video analytics. Deep learning engines are ‘trained’ using vast datasets of images and video footage of people, objects and vehicles. They can ‘look for’ size, shape, speed and directional information, and they continue to learn while in use. To an extent, deep learning replicates the way neurons work in the brain – it can analyze and prioritize input from video data to decide which inputs are of value, and it will notify security operatives accordingly. Deep learning’s real value comes from being able to detect suspicious activity or unusual events and eliminate those smaller binary objects that are just ‘noise’ and apply rules that meet with specific applications and operational requirements. In addition, deep learning should enable users to use metadata to search multiple camera streams to find the most accurate matches for persons or vehicles of interest within minutes. But again, some caution is needed. Deep learning video offerings can still disappoint, generally as a result of having been launched too early, before engines were fully trained and able to recognize objects reliably and accurately. Systems integrators need to exercise caution regarding claims and jargon. They need to understand which offerings and which functions will genuinely add value for their customers, and help them to increase productivity, provide useful business intelligence, and ensure they deliver RoI, long term. Overcoming the Common Challenges Caused by False Alarms The 2020 IFSEC Global Video Surveillance report cited reducing false alarms as the #1 reason for adopting AI – and for good reason. Traditional blob type analytics cameras are prone to being triggered by environmental factors such as heavy rain, snow or moving foliage, and struggle to distinguish a human presence, which may present a threat from harmless animal activity. For users, this can result in time being wasted investigating the cause of alarms, and the larger the site, or more overstretched the system operator, the worse that problem can be. ALARM OVERLOAD Alarm overload is a common problem. Operators can quickly become desensitized by false alarms and can start missing genuine threats, or even be tempted to shut off the system. Alarm receiving centers and virtual guarding firms typically increase charges for more frequent call outs and they may even withdraw monitoring services from problematic sites until cameras are re-configured or replaced. This can result in organizations needing to draft in additional security officers, to maintain protection, or risk leaving gaps in security. Over time, many organizations find it unfeasible to maintain systems that are prone to false alarms. The solution? By moving to deep learning-based analytics, customers can attain improved situational awareness, with highly accurate AI-assisted notifications for intrusion, object, loitering, and unusual event detection. Security operators will be better able to manage everyday events, and respond to more serious threats and emergencies. In short, safety and security are enhanced by better detection and verification. ELIMINATING OPERATOR FATIGUE AND INCREASING EFFICIENCY Unlike human brains deep learning engines don’t get tired. They can constantly monitor multiple camera streams in search of suspicious behavior, maintaining performance levels even in the busiest scenes such as retail malls, logistics centers, higher education settings and outdoor spaces. Relying on human operators to monitor multiple cameras means hiring enough staff to cope and allowing for regular breaks to ensure they stay alert. Using AI-assisted notifications free-up operators from having to constantly monitor multiple camera streams and video walls. Instead, they can respond quickly and flexibly, and not just from the control room. They can configure alarms to be received to client software, and on mobile devices such as smartphones and tablets, giving the ability to verify and respond to events on the move. Improving the ability of security managers to oversee security operations away from the control room – by giving them more accurate information along with powerful VMS functionality and tools – lets them better manage incidents on the ground and direct their teams. The latest generation of AI-assisted tools can transform the work of security teams. Today’s truly smart video technology can allow security provision to be better focused, with officers being re-deployed to more important tasks that add greater value to their roles, for example giving them time to engage with the people they are helping to safeguard rather than remaining unseen in the control room. And strategically, heads of security can interpret and use accurate real-time and historical data to drive more informed decision-making, to better mitigate risk across their enterprise. Speeding Up Investigations with The Power of Metadata Deep learning and intelligent video analytics capture metadata even when analytics rules are not applied, meaning that users can benefit from advanced…

Read More