The recent advances in video analytics technology are revolutionizing security and facilitating the ability to turn video data into useful information for fast, accurate and proactive security management. Optimize reactive investigation When it comes to security, speedy response is essential. While video surveillance has always been a key resource for security organizations and police units, traditionally timing hasn’t been the strong suit of this medium. Watching video from surveillance cameras is time-consuming and tiring, making it difficult for viewers to focus and to identify threats as they develop. In fact, Accenture estimates that, after twenty minutes of reviewing surveillance footage, 95% percent of incidents are likely to be missed, while 98% of footage is never viewed. With video analytics based on Video Synopsis® technology, investigators can overcome the limitations of timing that have inhibited their reliance on video footage in the past. The ability to watch hours of video in minutes and to see all video events and objects simultaneously, means that a single investigator can function as many. According to Hartford, CT Police Chief James Rovella “this is imperative, because we can't have 30 people sitting, watching cameras” to quickly find targets and identify suspects. Furthermore, because Video Synopsis indexes and classifies all the objects in the original footage, the investigator can apply filters to focus search criteria when looking for specific targets. This also helps in cases when there is no known suspect, because the investigator can rapidly review footage to identify potential perpetrators. Suspicious behavior can be identified using heat maps, as well, which can be applied to detect loitering and movement in restricted areas. Adopt proactive investigation Oftentimes, the best course of action for security teams is to handle events as they unfold, and it’s not enough to simply review the footage. Today’s video analytics solutions offer real-time alerts for: Improving situational awareness Updating security personnel to suspicious behavior Analyzing complex scenes quickly and effectively This helps maintain safety and quickly restore security when it is disrupted. In addition to real-time notifications, video analytics solutions can also offer statistical reporting, to give a high-level overview of activity and events in videos, enabling investigators to: Automatically schedule reports to share work progress Easily present investigation results in an organized manner Identify key trends over time with statistics All these lead to more proactive case management and more effective communication for security teams. But this isn’t the only way video analytics helps manage investigations more effectively, it also provides the tools to keep all security personnel informed and focused. The ability to quickly drill down to the exact details needed to solve a case, without tediously having to filter through extraneous data and footage, enables security teams to streamline their operations and work efficiently. While we don't often have the opportunity to view a video investigation side-by-side using different techniques, one thing that we do see from time to time is re-investigating offloaded video for cases that have been archived as unsolved. Such cases can be solved faster by applying video analytics based on Video Synopsis. Though on first glance you might think video could slow down investigative work, with advances in Video Synopsis and analytics, video has become an invaluable resource for solving crimes quickly and effectively, on the reactive and proactive level. Is the industry ready for the next level? Stay tuned for my thoughts on predictive video analytics.
Typically, the words video surveillance have a governmental and security connotation. And hearing those words in the context of home-based elderly care, seems a bit harsh: What happened to respecting the elderly’s personal dignity – not to mention privacy? You’d be surprised with the answers: According to National Aging in Place Council, 90 percent of older adults would prefer to age in place rather than move to senior housing. According to CDC, aging in place is the ability to live in one’s own home and community safely, independently, and comfortably, regardless of age, income, or ability level. And, when weighing the pros and cons of aging in place, what are a few cameras – to which you can quickly acclimate – compared to living independently in one’s own home? Many adjustments must be made to turn the desire of aging in place to a safe and sustainable reality for the elderly community. Changes vary and whether it’s making the 10 changes the Washington Post proposes or implementing the 7 suggestions provided by AARP, these adjustments are just one angle of ensuring successful aging in place in the best possible way. Analyzing this issue from a different angle takes us back to video surveillance which, in light of the above, should now sound less controversial. In fact, the connotation should now be protection, personal integrity and quality of life. When you take video surveillance and add video analytics, you can see the clear advantage of a cost-efficient, time saving and easily implemented solution for aging in place. For example, consider the case of an elderly parent, who is independent and wishes to live happily in his or her home, yet tends to forget to turn off the burners on the stove after making breakfast, or forgets to take medication twice a day. By applying home Video Synopsis® and analytics to IP cameras installed at your parent’s home, you can receive real-time alerts that you define, review your parent’s day in just minutes and ensure their quality of life is maintained with minimal interference and hassle. The ability to remotely check on your parents while remaining sensitive to their privacy, and of staying close to them from afar, is a game changer. And, if your parent lives with a caregiver, monitoring the service and ensuring proper behavior is essential for your parent’s well being. There are additional angles to home video analytics that go beyond safety and physical well being. Connecting other sensors in the house to video analytics takes aging in place safely to aging in place smartly. More on that in the future.
How do you effectively monitor video from the numerous cameras spread across an airport when, according to ACI, the traffic of the world’s 20 busiest air passenger hubs grew 4.7% in 2016, with over 1.4 billion passengers passing through their airports in 2016? How do you streamline operations when year-over-year growth for 2016, compared to 2015 is as follows? Total passengers: +5.6% Total international passengers: +6.6% Total cargo (includes mail): +3.3% Total international freight: +4.3% Total aircraft movements: +2.3% How do you maintain security and safety in today’s reality (and these are just a few examples…)? March 2017 Île-de-France attacks 2016 Atatürk Airport attack 2016 Brussels bombings With a continuous increase in passenger volume, strict requirements from governments and homeland security, and continuous terrorist threats in the background, it’s fortunate for airports that video analytics technologies have reached a whole new level. By using video analytics, airports can gain control over security and operational management without having to allocate huge resources to the matter. Coupled with Video Synopsis®, airports now have bionic eyes and brains to assist with achieving security and safety, alongside compliance and efficiency across the airport. With thousands of cameras already installed in airports, video analytics based on Video Synopsis enables rapid review of huge amounts of data for enhanced security, while extracting useful statistical information to improve operational performance, save money, gain business insights and identify key trends over time. For airports, the range and variety of use cases covered by video analytics is huge: from tracking objects, managing queues and crowds, identifying unattended bags, monitoring passenger flow, controlling restricted areas and counting objects, to reducing risk and mitigating liability, optimizing staff performance, enhancing passenger satisfaction and improving the airport’s retail environment. And the list carries on and on. So much takes place behind the scenes before you can truly wish someone bon voyage. Putting video analytics to play is the most effective and reliable way for ensuring safe and pleasant travels.
Universities, colleges and schools are constantly challenged with how to ensure the safety and wellbeing of students and staff. According to Campus Safety, the majority of campuses believe video surveillance is the answer to their security needs. In fact, more than 9 in 10 campuses have installed surveillance cameras, and 79% of the campuses without cameras plan to install them in the next 3 years. On top of managing campus security, many educational institutions function as a mini-city alongside a profitable business, entailing various additional challenges. Not to underestimate the importance of security and its connection video surveillance cameras, but that’s a no brainer. The more intriguing questions would be: 1. Can the video from the campus cameras be used more effectively, enhancing security? 2. Can the same video from the cameras be used for additional applications beyond security? One solution addresses both questions: video analytics. To answer question #1, by using video analytics based on Video Synopsis®, campuses can review hours of video in just minutes, while applying sophisticated search filters to quickly find what they’re looking for. With the ability to review video rapidly, institutions can cover their entire campus – indoors and outdoors – with cameras, ensuring full coverage and control at all times. After all, what’s the point of a surveillance camera without an effective way to make use of what the camera is recording. The answer to question #2 requires keeping an open mind: the right video analytics solution can use the same video from campus cameras for other purposes than security. Without having to install additional software. How? The required video footage is processed only once and then manipulated per demand for various applications. When dealing with theft or attack on campus, the security department would review the relevant video and by applying Video Synopsis could achieve faster time-to-target with accurate investigation results, while managing future events proactively. Then, using the same video analytics software other stakeholders in the institute could generate statistical reports, enabling them to understand if and where there is a liability issue, such as a slippery path, lack of light, crowded exit, intruder, lack of privacy, etc. From a business perspective, this is where applying video analytics can be a real game changer: using the same video data to improve operations across campus, monitoring relevant activities, ensuring student satisfaction, gaining insights for future expansion of the campus, etc. Market experts believe that security technology for campuses will become even stronger than it was in 2016. And, with video analytics playing a key role, security is just the tip of the iceberg.
On the heels of the WannaCry ransomware crisis that had organizations worldwide reeling, we decided to take this opportunity to talk about how to protect your VMS and video analytics systems against cyber vulnerabilities. While the WannaCry attack did not affect IP cameras, VMS systems are not immune to security issues and it is important to be aware of how VMSs and the video analytics solutions integrated to them are affected by cyber threats. GenX security solutions has recently reported about the arrest of two London based individuals who were suspected of hacking into network video recorders in Washington D.C. just days before President Trump’s inauguration. Effectively, this hack disabled 123 of 187 network video cameras from recording, preventing video surveillance of most of the city until the recorders could be taken offline for the malicious software to be removed. Beyond these very practical threats to physical security, hacking into network based camera systems could offer back door access to wider corporate networks, posing even larger scale privacy and data security risks. To prevent these types of attacks, make sure to use a dedicated server for surveillance systems instead of putting company information on the same server you use for your VMS. Today, some forward-thinking video surveillance systems are built with cyberattacks in mind, and include additional functionality to protect against these threats. However, Security Today explains that, as the industry transitions from analog to IP cameras, not all camera manufacturers have built in protection against cyber threats. This could be because when IT safeguards are added after the actual installation of the video surveillance system, then the performance of the network could be irreparably damaged. Moving forward, VMS systems with IP cameras are likely to become more robust, with built-in protections against these types of attacks. But what does all this mean for your video analytics solution connected to the VMS? The most important thing to know is that, if you VMS has been hacked, the main practical application that might affect your video analytics activities is simply that, when your VMS stops recording video, your video analytics solution will not have video to analyze and process. Beyond that, any sophisticated video analytics system you use should: Provide you with password protected access and a limited IP address range, to prevent hackers from accessing sensitive information Implement its processing units to the VMS architecture as stand-alone components, so that even if a VMS lacks sufficient protection, risks to the video analytics platform are mitigated Protect you in all scenarios, so that even when the analytics processing software is based on video file handling and not VMS, you are fortified against attacks In today’s day and age, no one is 100% safe from cyber threats, but by taking the proper precautions and using intelligent video analytics platforms, you can keep your video data safe, even when you’re VMS has come under attack.
In my last blog post, I talked about the cost efficiency of GPU-powered video analytics, and how a major advantage of GPU processing is the enablement of deep learning techniques. In today’s post, I’d like to delve deeper into what deep learning is and what it enables video analytics solutions to achieve. Deep learning techniques use deep neural networks (DNNs) to train computer systems, imitating the way a human is taught and learns. Historically, deep learning has been possible since the 80s, but it took until now to really gain traction in video analytics because CPU-based processors were too slow for training neural networks effectively. Today, deep learning, running on GPUs, can be used for efficiently detecting, classifying and recognizing features and objects in video. These capabilities have transformed the video analytics industry by allowing security applications to work out-of-the-box on a broad spectrum of scenarios. Increased coverage and cost-efficient processing allows systems to continuously process more cameras and aggregate metadata over time, making video more accessible. This, in turn helps users to gain deeper insights from previously unused video. Beyond video analytics, deep learning techniques “are crucial to unleashing improvements in robotics, autonomous drones, and, of course, self-driving cars” (Source: Why Deep Learning is Suddenly Changing Your Life). Deep learning is a great development tool because it can complete many activities simultaneously. Multiple algorithms were once needed to compute different aspects of video analysis, but deep learning can solve many problems at once and, as it learns more, it becomes more equipped to solve more complex problems over time. The main challenge of deep learning is the large amount of annotated data required for effective training. The annotation process often involves labor intensive and repetitive manual work. It is often worthwhile to invest in annotation tools and in automatically generating annotation proposals. In addition, there is significant research in the field of unsupervised learning that will alleviate the need for manual annotation. Here are some other challenges to consider when adopting deep learning: While it’s beneficial for the system to solve problems independently, this means there is less visibility into how the problem was solved If the system isn’t exposed to a broad enough variety of data, it could reach wrong, often unexpected conclusions The GPU-processing needed to enable deep learning can be demanding and expensive to run The technology is rapidly evolving, so developers need to follow academic research and frequently re-assess their algorithms (agile) It is clear that the benefits of deep learning in video analytics, and many other fields, greatly surpass the challenges. It will be interesting to see how the technology develops as processing and automation technology improve. Perhaps in the future, systems will be so well-trained machines will be able to predict and interpret unfamiliar scenarios independently, and help provide further insight for improving security, business intelligence and quality of life. If you’re attending the GPU Technology Conference this week, you can learn more about Leveraging Deep Learning and GPUs to Accelerate Surveillance Video to Insight in a session with my colleague, Amit Gavish, BriefCam General Manager of Americas.
Anyone familiar with the ins and outs of hospital management understands that the security and operational challenges of hospitals are enormous. With thousands of patients, staff members, and visitors entering and circulating the hospital every day, there is much information to monitor and process. While many hospitals know that they need more effective methods for maintaining a safe and efficient environment, most hospitals lack the tools to manage their security and operational needs. One major setback many hospitals face is that they capture hours of video surveillance, but don’t have the resources to efficiently monitor and review the recordings. While this footage could be used to extract useful information and understand vulnerabilities and inefficiencies in the day-to-day hospital operations, petabytes of video data go to waste every day because there is no way of quickly and effectively reviewing all the footage. Video Synopsis® technology offers a smart and reliable video analytics solution for finding targets faster and enabling efficient monitoring. This makes it an ideal solution for maintaining hospital security and operations, facilitating hospitals to: Increase overall security Ensure patient and personnel safety Comply with procedures and regulations Mitigate false liability claims Improve operational management Optimize commercial operations The ability to easily manipulate video data with filters, makes it comfortable for anyone responsible for reviewing the data to find necessary information, detect anomalous behavior, and proactively prevent inefficiencies. We can see the profound impact of video analytics on hospitals by looking back at the Forbes interview with Director of Police, Security and Outside Services at Mass General Hospital, Bonnie Michelman, who anticipated how video analytics could influence hospitals, by combining video and analytics to identify risk situation, crowd control, unattended packages, abnormal traffic flow and suspicious loitering in restricted areas. Today, Mass General Hospital has implemented a video analytics strategy and is leveraging their video data to improve security and operations across the hospital. And it doesn’t stop at hospitals: As video analytics and Video Synopsis technology become more advanced, the types of organizations they can help will become more varied, leading to impactful results for many businesses and institutions.
ISC West 2017 was impressive, with many interesting products and new technologies – where GPU and deep learning took first place in prime time. Participating at NVIDIA’s booth and getting a first glimpse into exciting innovations, certainly highlighted the potential of video analytics powered by GPU and deep networks. With the ability to effectively process highly parallel computing tasks, such as video and graphics, today’s availability of GPU accelerates the process of deep learning, enabling real advancements, which until today could only be imagined. By applying GPU-based deep learning techniques to video analytics solutions, the market can expect faster processing of video alongside richer metadata. This combination will enhance the quality of object extraction and provide new applications that will be beneficial across many more verticals and use cases. Video analytics solutions, strengthened by deep learning, enable covering an entire scene for full object tracking at the highest level. Cost-efficient subscription-based cloud services for home and SMBs, trends over time, connecting to other applications, implementation with small appliances, cross camera search and family member identification are just some examples of possibilities the future holds. Furthermore, we can expect to see performance and accuracy improvements in: Video search, alerts and statistics Scene coverage for occupancy, crowd management and queue control Cross camera search and re-entry of objects Metadata aggregation over time and trending What’s clear from ISC West, is that expectations from deep learning are high – and rightfully so. GPU-based deep networks particularly facilitate making sense of actual video content. This means video can be searched by the content that is actually displayed in the video. Video remains the strongest sensor and metadata is still king. Leveraging deep learning capabilities, Video Synopsis® and analytics can deliver more value to various markets, from law enforcement and security to safe and smart cities, campuses and retail. Interested in learning more about GPU processing for video analytics? Check out CTO Tom Edlund’s latest blog post about cost efficient video processing using GPUs.
The video analytics industry is constantly producing new and innovative solutions to provide deeper insight and derive more useful applications from video. These new capabilities often require more compute power. GPUs (Graphic Processing Units), if used correctly, can accelerate video processing and reduce costs. Therefore, many platforms are now adding GPUs to offload the CPUs (Central Processing Units) processing. Recently, this trend has been accelerated by the wide adoption of Deep Neural Networks (DNNs) to analyze images and videos. GPUs were originally designed to optimize rendering-to-display devices and enabled the rapid advancement of the computer game industry. Today, GPUs are also used for General-purpose computing (GPGPU) using higher level frameworks such as OpenCL or CUDA. GPUs excel in repeated parallel computations of large data (aka Single Instruction Multiple Data, or SIMD) and are ideal for DNNs and many image processing algorithms. Also, GPUs have dedicated HW for video decoding and encoding. Considering these advantages, it may seem straightforward to run your video analytics on GPU and improve performance. This is true if most of your computations are done by large/deep DNNs or run full frame processing at high resolutions. However, video analytics are often highly optimized and limit the computations to small regions of interest and lower spatial and temporal resolutions, making it difficult to reach high utilization of the GPU. In such cases, you will need to invest more in your system architecture to fully utilize the GPU by using technologies such as batching and buffering. If you consider porting a video analytics engine from CPU to GPU you should ask yourself the following: Do I use DNNs for most of the computations today or am I planning to in the future? Are my computer vision algorithms GPU friendly (e.g. data size and parallel computations)? Where do I deploy my processing? Edge devices, laptops and workstations are ideal for GPUs, while its harder to reach cost effectiveness on local or cloud servers. Every organization’s video processing needs are unique, and the answers to these questions should help give you an idea as to whether moving to GPU processing might be worth considering for you. If you’re looking to gain deeper insight about running video processing on GPU, you are invited to join my talk on April 6th at 2:00pm at NVIDIA’s ISC West booth #20075.
Last week, I talked about how small and medium sized businesses (SMBs) face large challenges and whether they are getting value from their video recordings. This week, I want to ask the same question for homeowners. Are they getting their videos worth in the home? Ask anyone in the industry, and they’ll tell you that IP cameras are one of the fastest growing categories in consumer electronics, both as a stand-alone single point camera solution, or part of a monitored home security offering. SDM presents great perspectives on the role of IP cameras in the residential market in this article. The list of reasons why consumers buy a security camera is long and wide, but a common theme for the purchase is peace of mind. A security camera should be able to fulfill this promise because it allows people to: Know what’s going on in their home Gain a sense of security Be alerted when something goes wrong And, with mobile phones, check in from anywhere, anytime… But do the cameras really fulfill all of these promises? Unfortunately, I say they don’t…. If you watch almost any commercial for a home security camera, the focus of the marketing message is on the high level critical value propositions stated above, plus more. Things get complicated when the camera technology cannot fully deliver on either the promises made by the manufacturer, or the expectations of the consumer. Motion detection capabilities in a camera do exactly what they are supposed to do…. detect motion. Unfortunately, the camera does not have the ability to understand the relevance of the motion it’s detecting, so it sends an alert accordingly. It could be the family, the pets, trees blowing in the wind, light changes, etc. They detect and alert on ALL motion, not just the motion the owner wants to know about. Upon setting up a security camera in a home, most consumers are excited to get that first alert come across the phone indicating the camera detected motion. More often than not, Mom and Dad are telling the kids to go wave at the camera. Bzzzz! Your phone notifies you motion was detected. Hurrah!! Several days, or weeks later, after getting 20, 30, and sometimes 40 or more push notifications that your family and pets have walked in front of the camera, the homeowner gets frustrated, and ends up turning the alert capability off. I saw this exact consumer behavior pattern in my prior platform, and have heard the same from other platform providers. Once notifications are disabled, one of the very core reasons a consumer bought the camera to begin with goes away, and the expected value is no longer there. Rather than detect only motion, what if the camera could detect people, animals, vehicles, or more importantly, trusted family members? What if you only got alerts when the dog got on the couch, but not when your kids walked through the living room? What if you got an alert when a burglar was actually in your home rather than a trusted family member? What if you could see a 1 minute video summary of all of the activity in the home, and if you saw something of interest, you could stop and go to the original video from earlier in the day. These capabilities alone would fulfill the implied benefits and expected value consumers expect from a camera.