According to the reports of not-for-profit organization Gun Violence Archive, the year 2018 has seen 323 mass shooting incidents as of November 28 in the United States. This number is 346 for the year 2017 and 382 for 2016 (more statistics are available here), with “mass shooting” defined as cases where four or more people are shot or killed in the same time period and location. While definitions of mass shooting vary with organizations in the US, the count of over 300 incidents per year, or about once per day on average, is simply alarming. It raises public safety concerns, ignites debates and protests, which in turn lead to public unrest and potentially more violence, and increases costs for governments from the regional to federal level. Most importantly, the loss of lives demands not only improvement in post-incident handling and investigation, but also new prevention technologies. Gunshot Detection Solutions AI weapon detection offers a more efficient alternative to prevent active shooting There are several gunshot detection solutions in the security market, commonly used by law enforcement agencies to detect and locate gun fires. These systems function based on acoustic recordings and analyses and often in combination with signals detected by sensors of the optical flash and shockwave when a gun is fired. However, gunshot detection by nature dictates that the law enforcement can only react to a shooting incident that has occurred. With fast action, law enforcement can prevent the incident from escalating, but lives that are lost cannot be recovered. With the development of artificial intelligence in object recognition, AI weapon detection offers a more efficient alternative to prevent active shooting: AI can visually detect guns based on their shapes before they are fired. The AI is trained to recognize firearms in different shapes, sizes, colors, and at different angles in videos, so that the AI weapon detector can be deployed with existing cameras systems, analyze the video feeds, and instantly notify security staff when a gun is spotted. Comparison of the advantages for law enforcement and public security agencies Legacy gunshot detection using sensors AI weapon detection Reactive measure: detect after guns have been fired Proactive measure: detect before guns are fired Time to action: within 1 second Time to action: within 1 second Unable to provide visual data about shooter(s) Can provide data about shooter(s) based on the camera recording: clothing, luggage (backpack, handbag, etc.), facial features, vehicle Unable to track the location of the shooter(s) before and after shooting because of the lack of sound Can track the shooter(s) using AI Person & Vehicle Tracking, AI Face Recognition, and AI License Plate Recognition False detection caused by similar sound such as fireworks and cars backfiring Minimal to no false detection, as AI can distinguish different types of handguns and rifles from normal objects (umbrella, cellphone, etc.) Require physical deployment of gunshot detection sensors Can be used with existing camera systems, do not require special hardware Complicated to deploy, require highly trained professional Easy to deploy as an add-on to existing video surveillance system - Can integrate with gun-shot detection to create a “double knock” audio and video active shooter alert system Gun-Shot Detection Advantages In addition to advantages for law enforcement and public security agencies, this type of visual-based pre-incident detector has three-fold advantages for the public: Save lives by spotting the shooter before the shooting event. Minimize the chaos entailing an incident: panic and chaos caused by a shooting incident often adds to injury, as people run, fall, trample on others… With an AI weapon detector, when a gun is spotted, the system sends an alert to security staff, who can quickly control the situation in an organized manner and apprehend the intending shooter. Can be added as a SaaS (Security as a Service) component to small business and home surveillance systems, e.g., intrusion detection alerts (home invasion incidents with firearms number over 2500 per year nationwide). For a complete active shooter detection system, video-based AI detector can operate in conjunction with gunshot detectors for enhanced security. Traditional X-ray based weapon detection or metal detection entrance systems are complicated and expensive; with AI video technology, active shooter detection system can be cost-effective, and after all, what price tag can one put on a life? Written by Paul Sun and Mai Truong, IronYun
With the ever-growing availability of video data thanks to the low cost of high-resolution video cameras and storage, artificial intelligence (AI) and deep learning analytics now have become a necessity for the physical security industry, including access control and intrusion detection. Minimizing human error and false positives are the key motivations for applying AI technologies in the security industry. What Is Artificial Intelligence? Artificial intelligence is the ability of machines to learn from experience using a multi-layer neural network, which mimics the human brain, in order to recognize items and patterns and make decisions without human interference. The human brain is estimated to have 86 billion neurons; in comparison, the newest Nvidia GPU Volta has 21 billion transistors (the equivalence of a neuron), which offers the performance of hundreds of CPUs for deep learning.AI can learn continuously 24 hours per day every day, constantly acquiring, retaining and improving its knowledge In addition, unlike humans, AI can learn continuously 24 hours per day every day, constantly acquiring, retaining and improving its knowledge. With such enormous processing power, machines using Nvidia GPU and similar chips can now distinguish faces, animals, vehicles, languages, parts of speech, etc. Depending on the required complexity, level of details, acceptable error margin, and learning data quality, AI can learn new objects within as fast as a few seconds using Spiking Neural Network (SNN) to a few weeks using Convolution Neural Network (CNN). While both SNN and CNN offer advantages and drawbacks, they outperform tradition security systems without AI in terms of efficiency and accuracy. According to the research reports of MarketsandMarkets, the market size of perimeter intrusion detection systems is projected to increase from 4.12 billion USD in 2016 to 5.82 billion USD in 2021 at a Compound Annual Growth Rate (CAGR) of 7.1%. Meanwhile, the predicted market of AI in security (both cyber security and physical security) will grow from 3.92 billion USD in 2017 to 34.81 billion USD by 2025, i.e., with an impressive CAGR of 31.38%. Legacy Perimeter Intrusion Detection Systems Legacy perimeter intrusion detection systems (PIDSs) are typically set up with the following considerations: Geographical conditions: landscape, flora, fauna, climate (sunrise, sunset, weather conditions, etc.), whether there are undulations in the terrain that would block the field of view of cameras Presence or lack of other layers of physical protection or barriers Integration with other systems in the security network: camera, storage, other defensive lines (door, lock, alarm, etc.) Types of alarm triggers and responses System complexity: intrusion detection with various types of sensors, e.g., microwave sensors, radar sensors, vibration sensors, acoustic sensors, etc. Length of deployment Local regulations: privacy protection, whether the cameras/sensors must be visible/hidden/buried, etc., electromagnetic interferences that may affect other systems such as oil rigs or power plants Human involvement: on-site personnel arrangement, human monitoring, human action in response to alarms AI object detection can easily distinguish different types of people and objects Pain Points In Intrusion Detection Systems And Benefits Of AI The conditions listed above correspond to certain requirements of an intrusion detection systems: minimal false alarm, easy setup and maintenance, easy integration, and stable performance.AI by nature is designed to learn, adapt itself and evolve to work in multiple conditions: it should be integrated with existing video recording systems Minimal false alarms: False alarms lead to increased cost and inefficiency but are the main problem of PIDSs without AI technology, where animals, trees, shadows, and weather conditions may trigger the sensors. AI object detection can easily distinguish different types of people and objects, e.g., in a region set up to detect people, a car driving by, a cat walking by, or a person’s shadow will not trigger the alarm. Therefore, the amount of false alarms can be reduced by 70% to orders of magnitude. Easy setup and maintenance: Legacy PIDSs without AI must account for terrain, line of sight of cameras, sensor locations; any changes to the system would require manual effort to recalculate such factors and may disturb other components in the system. In contrast, AI PIDSs enable the system administrator to access the entire system or individual cameras from the control room, configure the region and object of interest in the field of view of cameras within minutes, and adjust with ease as often as necessary. Computing knowledge and even specific security training are not required to set up a secured PIDS with AI because AI PIDS is designed to relieve humans from knowing the inner working of machines. Easy integration with complementary technologies: Legacy PIDS without AI relies on physical technology, which are often proprietary and require complete overhaul of systems to function smoothly. On the other hand, AI by nature is designed to learn, adapt itself and evolve to work in multiple conditions, so AI PIDS is easily integrated with existing video recording (camera) and storage (NVR) systems. AI also eliminates the need for physical wireless or fiber-based sensors; instead, it functions based on the videos captured by cameras. Furthermore, AI enables easy and instantaneous combinations of multiple layers of defense, e.g., automatic triggering of door lock, camera movement focusing and access control as soon as a specified object is detected in the region of interest, all set up with a click of a button. Stable performance and durability: Legacy PIDS without AI requires complicated setup with multiple components in order to increase detection accuracy. More components mean a higher probability of malfunction in the system, including exposure to damages (e.g., sensors can be destroyed) and delay in detection, while human monitoring is inconsistent due to human fatigue (studies have shown that a person can concentrate in mundane tasks for only up to 20 minutes, and the attention span decreases even more rapidly when humans are faced with multiple items at once, e.g., multiple camera monitoring screens). AI significantly reduces, if not completely eliminates the need for human involvement in the intrusion detection system once it is set up. In addition, AI reduces the risk of system malfunction by simplifying the hardware sensors needed. Minimizing human error and false positives are the key motivations for applying AI technologies in the security industry Additional Benefits Of AI In Intrusion Detection Artificial Intelligence is undeniably reshaping every business and weaving into every aspect of daily life Maximal detection capability: The most advanced AI intrusion detection system today provides an all-in-one solution to distinguish any combination of alarm-triggering criteria beyond perimeter protection. Using AI, the system administrator can configure as many zones with different settings and object of interests as necessary, which include detections for specific colors or attributes (e.g., person not wearing the required uniform or carrying food/drink), numbers and dwell time (e.g., group of more than 5 people loitering), or movements (e.g., cars moving faster than the speed limit). In addition, AI can accurately pinpoint the location of event occurrence by displaying the camera that records the event in near real time, i.e., with few-second delays. Lower security operation cost: By minimizing the number of false positives and human involvement while maximizing ease of use and stability, AI intrusion detection systems significantly decrease the total cost of ownership. Companies can reduce the large security personnel overhead and cost of complicated and expensive legacy PIDS systems. McKinsey Global report in June 2017 shows that proactive AI adopters can realize up to 15% increase in profit margin across various industries. Artificial Intelligence is undeniably reshaping every business and weaving into every aspect of daily life. In security, legacy systems are giving way to AI-based systems, and the first enterprises to adopt AI-based systems will soon, if not immediately, benefit from such investment. By Paul Sun, CEO of IronYun and Mai Truong, Marketing Manager of IronYun
Artificial intelligence and deep learning are poised to transform how video images are used and managed. In today’s surveillance systems, video from more and more cameras leave operators at risk of drowning in data, requiring hours of manual effort to track assets or persons of interest. They need more intelligent systems. Among the new tools is use of neural networks to create video analytics systems that are trained, not programmed. In effect, the systems have the ability to “learn” based on how they are used over time. IronYun is introducing an artificial intelligence (AI) appliance at ISC West that applies AI-based video search and video mining capabilities to enterprise applications. CityEyes deep learning video analytics are incorporated into IronYun’s CAC-AI appliance built for the surveillance market. CAC-AI combines artificial intelligence software and hardware video search capability for fast, efficient search of video objects stored in an external network video recorder or storage device. Cloud Analytics Centre Artificial Intelligence CAC-AI stands for Cloud Analytics Centre Artificial Intelligence. CityEyes is a private cloud software platform for enterprise, government and many small- and medium-sized businesses (SMBs). “Using a private cloud solution protects data from hacking and unauthorized access,” says Paul Sun, President and CEO of IronYun. “It also avoids the high bandwidth cost of continuously sending video traffic to a public cloud, and there is a lack of broadband infrastructure in many locations.” CityEyes has integrated more than 15 video analytics applications in an all-in-one video operating system CityEyes has integrated more than 15 video analytics applications in an all-in-one video operating system. The latest CityEyes AI deep-learning-based video search appliance is plug-and-play to leading DVR/NVR systems for quick and easy deployment, connecting via a LAN Ethernet cable. The appliance downloads files from the DVR/NVR and performs AI-based object detection and recognition. Extracted image metadata is then stored in the CAC-AI for fast retrieval and viewing. Video Search And Object Detection Engine A high-performance graphics processing unit (GPU) provides fast video search and mining, significantly increasing operator productivity and saving time compared to operators needing to manually inspect and identify objects of interest. The search engine allows objects of interest to be found and identified amid hours of video data; in effect, like locating the needle in a haystack. More intelligent video searches can find relevant video in seconds. They can quickly identify objects (car, bus, luggage, dog, cat, etc.) and persons (male, female, age, person with hat, etc.). IronYun’s AI object detection engine is based on natural language input. Video searching is based on intuitive, natural language and can be compared to the information that might be entered in a Google search. Inputs might include a description of a person, face, car, bus, motorcycle, a color or a time. Identifiable objects are continuously added as the deep learning engine is trained over time. In scene mode, numbers of objects (but not color) can be specified (such as a scene with four cars, or a scene with one car and two people). Video searching is based on intuitive, natural language and can be compared to the information that might be entered in a Google search Reduced Long-term Storage Costs Because video metadata takes up much less storage than unstructured video data; there is potentially an up to a 100-to-1 reduction in long-term storage costs (for longer than 30 days). Using the AI deep learning object-identifying capability, only the video metadata with relevant objects or persons will be archived for long-term storage and future forensic applications. Two series of the new appliance are available: The CAC-AI-110 series for small- to medium-sized enterprises, supporting up to 12 IP cameras; and the CAC-AI-510 series for clients needing to monitor more than 64 IP cameras. At ISC West, the IronYun AI solutions will be demonstrated at Booth #18129 and at IronYun partner booths: Jenne (distributor), NVIDIA, Promise Technology and QNAP. IronYun, founded in 2009, specializes in cloud and big data video search solutions, deployed successfully by many government and enterprise customers, providing reliability 24/7/365. Worldwide offices are in the USA, Japan, Taiwan, Korean, Thailand, Singapore, Malaysia and China.
Again in 2016, the most well-trafficked articles posted at SourceSecurity.com tended to be those that addressed timely and important issues in the security marketplace. In the world of digital publishing, it’s easy to know what content resonates with the market: Our readers tell us with their actions; i.e., where they click. Let’s look back at the Top 10 articles we posted in 2016 that generated the most page views. They are listed in order here with the author’s name and a brief excerpt. 1. Why Hikvision Is Suddenly Front-Page News: The Company Responds to Security Concerns [Ron Alalouff] It is perhaps [Hikvision’s] spectacular growth that has fueled some of the claims and concerns about the company, most recently in the UK in a front-page article in The Times. While highlighting the company’s success – in the UK it has sold more than a million cameras and recorders installed at sites such as government buildings, airports and sports stadiums – the article questioned whether there is sufficient oversight of the security implications of foreign involvement in critical infrastructure. 2. Tyco and Johnson Controls Merger Driven by Convergence of Security with Smart Building Technology [Larry Anderson] This week, Johnson Controls and Tyco have announced their merger into one company with annual revenue of $32 billion. The new Johnson Controls will be almost a direct reflection of one of the industry’s biggest trends – the move toward technology convergence and smart buildings. 3. Weaponized Robots? Military and Police Response Uses for Robots on The Rise [Randy Southerland] The era of the “killer robot” hasn’t arrived, exactly, but it may not be far off. Police and the military have been using these machines for decades now to disarm bombs and provide reconnaissance in areas where it would be risky to send officers or soldiers. Police and the military have been using these machines for decades now to disarm bombs and provide reconnaissance (Image credit: Antonio Scorza / Shutterstock.com) 4. Security Industry Speculates As Honeywell-UTC Deal Falls Through [Larry Anderson] In a year of mega-deals impacting the security marketplace, one of the big news stories recently was a deal that did not happen – between giants Honeywell and United Technologies (UTC). Financial news pages have been full of the back-and-forth between these two companies. It seems Honeywell wanted to merge with UTC, but UTC declined because of “insurmountable regulatory obstacles and strong customer opposition.” So the deal is off, at least for now. 5. Home Automation: A Growth Area for The Security Industry? [Ron Alalouff] Despite the market entry of some big names such as Google’s Nest, Apple’s HomeKit, and telecommunications giants AT&T and Deutsche Telekom, are we really on the threshold of a home automation revolution? Not quite, according to market intelligence firm Ovum. 6. Bosch-Sony Partnership Amounts to A New Variation On M&A [Larry Anderson] Might there be more such partnerships to come as the number of companies serving the video surveillance market adjusts to its size? Might “softer” consolidation like the Bosch-Sony deal be the next big thing and even slow down the pace of mergers and acquisitions? Time will tell, but it’s clear the benefits of such an approach might be attractive to other companies, too. Bosch will handle the sales and marketing globally for all of Sony’s video surveillance products (outside of Japan) 7. Pelco By Schneider Electric CEO Sharad Shekhar To Revive Pelco Global Video Security Business [Deborah O’Mara] Pelco has made significant investments in key vertical markets, including oil and gas, gaming and casinos, Safe Cities, and airports and seaports, and [the company] will see significant focus on product and business development in these markets. [Pelco] will look to further engage customers in these spaces by focusing not just on products, but on solutions that will solve security and operational challenges. 8. Deep Learning Technology Applications for Video Surveillance [Paul Sun] Although deep learning has been applied to many industries with breakthrough results compared to legacy systems, not all applications are suitable for deep learning. In the field of video surveillance, several applications stand out that can benefit from deep learning. 9. Electronic Locks Prove a Worthwhile Investment for The Security Industry [Michael J. Mahon] Mechanical locks and keys date back thousands of years and have undergone many changes, but the industry’s transition to electronic locks might be the most important, lasting, and surprisingly affordable security and safety change of all. The objective behind the creation of locks so long ago remains: to control a value on the other side of a door. But the security industry as a whole is migrating from the perceived “cheaper” and historical mechanical lock to the newest technology of electronic locks. 10. Understanding Starlight Camera Technology and Low-light Applications in The Security Industry [Alyssa Fann] Starlight cameras are the latest products security companies are adding to their product line-ups, each camera boasting the most comprehensive ability to make darkness visible. While low-light surveillance capabilities have been around on the market for some time, starlight camera technology is redefining low-light surveillance to new levels. See the full coverage of 2016/2017 Review and Forecast articles hereSave Save