VCA Technology joins NVIDIA Metropolis Partner Program
London — 12th May 2021 — VCA Technology, one of the leading developers of Video Analytics with over 500,000 channels installed worldwide, today announced it has joined NVIDIA Metropolis, a program designed to nurture and bring to market a new generation of applications and solutions that make the world’s most important spaces and operations safer and more efficient with advancements in AI vision. Being part of the Metropolis program will ensure that VCA continues to be at the forefront of AI-based analytics solutions.
VCA has recently launched a new line of deep learning based analytics, building on its years of experience in public safety, retail and traffic analytics. Sold through its global partners, VCAcore provides outstanding performance in a range of environments. Key to its goal to provide the most cost effective solutions is the optimization of its software with NVIDIA TensorRT which speeds up deep learning inference while reducing the runtime memory footprint for convolutional and deconv neural networks.
The inference optimizations in TensorRT help run AI models in real-time with high performance, a key requirement in edge applications like intelligent video analytics, robotics, healthcare, etc. Running on NVIDIA GPU-accelerated servers/workstations or the NVIDIA Jetson edge AI platform, it is now possible to bring more AI computation at the edge, giving VCA Technology customers a significant increase in channels for their applications.
NVIDIA Metropolis makes it easier and more cost effective for enterprises, governments, and integration partners to leverage world-class AI-enabled solutions to improve critical operational efficiency and safety problems. The NVIDIA Metropolis ecosystem contains a large and growing breadth of partners who are investing in the most advanced AI techniques, most efficient deployment platforms, and use an enterprise-class approach to their solutions. Partners have the opportunity to gain early access to NVIDIA platform updates to further enhance and accelerate their AI application development efforts. Further, the program offers the opportunity for partners to collaborate with industry-leading experts and other AI-driven organizations.
“Joining the NVIDIA Metropolis program is a further endorsement of our AI-based developments.” said Kevin Waterhouse, MD of VCA. “Working alongside the NVIDIA team and the partners in this program will collectively provide outstanding solutions to our respective areas of interest.”
About VCA Technology
VCA Technology, founded in 2007, has over 50 global technology partnerships that provide security and business intelligence solutions to protect and grow firms’ understanding of the threats facing their businesses. Deployed worldwide in excess of 500,000 video channels, VCA Technology’s analytics solutions accurately capture data to help a diverse range of businesses and organisations achieve a greater understanding of the behaviour of people who work or visit their premises. VCA Technology provides security personnel with a powerful tool to detect and combat theft and other criminal activity, as well as an opportunity for installers, remote monitoring centres and end-users to work together to reduce the time consuming and costly impact of false alarms. For more information about VCA Technology, please visit vcatechnology.com.
Pose Estimation enables VCA to utilise a Deep Learning people tracker which only detects and classifies people in the scene / camera view and so is able to ignore the noise which would generate false alarms. Typically noise is created by moving doors, shadows, illumination change, standard video analytic object trackers suffer significant false alarms in this type of environment . The DL people tracker generates additional metadata on a person’s joint positions, this not only enhances tracking accuracy but can also be used for additional value add algorithms, such as face detection or slip trip and fall. In these challenging times a technology that offers tripartite solutions incorporating, security, health and safety and business intelligence solutions/ features has been perceived by many customers to be a convincing argument when deciding on budget expense.
Kevin Waterhouse, Managing Director of VCA Technology commented on the update:
“VCAcore is at the heart of our products; providing a modular, cross-platform engine that unleashes the true power of networked video. This update makes it even more unique as we can now offer key verticals not only improved functionality and applications, but business intelligence to save time. We have listened to our customers and delivered this update that really supports them in their new operating environment. From helping deliver more precise forensic searches to providing support to those operating in real or virtual environments, this programme is going to be a real game-changer.”
The new update is available from October 1st.
For more information, please visit:
About VCA Technology VCA Technology, founded in 2007, has over 40 global technology partnerships that provide security and business intelligence solutions to protect and grow firms’ understanding of security threats facing their businesses.
Deployed worldwide in excess of 500,000 video channels, VCA Technology’s analytics solutions accurately capture data to help a diverse range of businesses and organisations achieve a greater understanding of the behaviour of people who work or visit their premises. VCA Technology provides security personnel with a powerful tool to detect and combat theft and other criminal activity, as well as an opportunity for installers, remote monitoring centres and end-users to work together to reduce the time consuming and costly impact of false alarms.
View video of the advanced people tracker
VCA Development Team Delivers Ground Breaking New Features
VCA releases 1.4 Latest Software With New Features and Improvements
Product update includes new cutting-edge features that provide vastly superior people tracking using pose estimation techniques and provides enhanced capabilities to assist in post event and forensic searches.
VCA Technology has today released VCAcore 1.4 to the market, delivering brand new functionality to optimally support operations in retail, traffic and security markets. The new functions to the flagship engine not only enhance security operational aptitude but also provides operators with enhanced business intelligence. Key features include:
Advanced People Tracker
Our new GPU based advanced people tracker, enables our partners to develop applications and projects that seek to leverage highly accurate people detection and occupancy management solutions, particularly suited to retail and indoor applications.
The advanced people tracker, powered by AI Pose Estimation techniques, tracker provides robust human detection, highly resilient to common issues like reflections, shadows and environmental difficulties such as moving doors and signage. Setup is calibration-free and designed to utilise existing IP cameras; a fundamental advantage over many existing retail solutions. No need for custom cameras, proprietary sensors, nor specific fields of view!
Deep Learning Filter
An upgrade on previous functionality, 1.4 now offers an added layer of analytics using Deep Learning that removes the need for calibration, minimises false alarms, is lightweight, cost effective and evaluates up to 250 objects per second.
Colour filter
Enables integration partners to implement colour specific, post event analysis and reporting. This allows users to run searches by extracting metadata focusing on specific colours featuring in certain timeframes, areas etc. When executed in conjunction with the new deep learning people tracker, enhanced search functionality is achieved thanks to additional metadata for specific points of reference, allowing operators to search for particular coloured items of clothing, such as white trousers or red jumper.
Hardware monitoring (GPU & CPU)
Manages and creates alerts on the host system hardware to ensure the CPU/GPU is not overloaded. When supporting increasingly sophisticated AI and deep learning applications, alerts such as this help reduce instances of downtime and even eradicate it thanks to defined parameters.
Scheduling
System arming and disarming can now be scheduled for specific days and times. Schedules can also be incorporated within a rules configuration to give the operator a more defined and automated alter configuration.
Kevin Waterhouse, Managing Director of VCA Technology commented on the update:
“VCAcore is at the heart of our products; providing a modular, cross-platform engine that unleashes the true power of networked video. This update makes it even more unique as we can now offer key verticals not only improved functionality and applications, but business intelligence to save time. We have listened to our customers and delivered this update that really supports them in their new operating environment. From helping deliver more precise forensic searches to providing support to those operating in real or virtual environments, this programme is going to be a real game-changer.”
The new update is available from October 1st.
For more information, please visit:
About VCA Technology VCA Technology, founded in 2007, has over 40 global technology partnerships that provide security and business intelligence solutions to protect and grow firms’ understanding of security threats facing their businesses.
Deployed worldwide in excess of 500,000 video channels, VCA Technology’s analytics solutions accurately capture data to help a diverse range of businesses and organisations achieve a greater understanding of the behaviour of people who work or visit their premises. VCA Technology provides security personnel with a powerful tool to detect and combat theft and other criminal activity, as well as an opportunity for installers, remote monitoring centres and end-users to work together to reduce the time consuming and costly impact of false alarms.
View video of the advanced people tracker
AI will Change Security Video Analytics - Fact or Fiction?
Author – Dr Rob Dupre PhD – Product Manager VCA Technology
Overview of AI in security
In recent years, Artificial Intelligence (AI) has been the buzzword in the video analytics domain. Trade show stands are rife with AI demos promoting ambitious functionality set to change the face of CCTV in security. Impressive as many of these demonstrations are, there is a definite air of scepticism on the part of the end-user. Is the hype around AI warranted, and can science actually deliver? This feels reminiscent of a decade ago when video analytics promised to revolutionise CCTV monitoring. Today, reliable and effective analytics is the mainstream and is driving tangible business value.
That said, there is no denying that the last five years of AI innovation has led to tangible and practical solutions, with the security industry finally starting to reap the benefits. However, AI is now at a precipice – on the cusp of what industry experts call an “AI winter” – so, everyone is wondering what’s next and what is possible. This paper investigates precisely this, focusing on the physical security space.
What is AI?
One formal definition of Artificial Intelligence (AI) identifies the technology with the “development of computer systems able to perform tasks normally requiring human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages.” [1]
In reality, the term AI covers a wide range of applications and tends to refer to the current problem being tackled, which of course is constantly evolving. When we think of AI in the security industry, this usually translates to a few key areas:
Asset protection & monitoring
Access control
Business intelligence
Decision support
Machine learning is the process of teaching a system to perform a task, while Deep Learning is just a subset of Machine Learning. There are many other non-Deep Learning based ML methods which, for the purposes of this paper, will be referred to as traditional ML approaches.Often, when AI is mentioned, what is really being referenced is the Machine Learning (ML) or Deep Learning (DL) algorithm powering that solution. For example, license plate recognition (LPR) is often the application of a DL model to locate and extract a license plate from an image, coupled with ML algorithms cross-referencing information from a database. Therefore, this application should be referred to as a combination of ML and DL – not simply AI.
The distinction between traditional ML and DL is an important one, as the recent boom in AI solutions often refers to advances in Deep Learning techniques. In the majority of cases, the use of Deep Learning has led to a significant jump in accuracy over traditional ML techniques. For example, a well known academic image classification challenge, in which images must be classified into one of a thousand different classes, has seen a notable increase in accuracy – going from 50% of the images being classified correctly in 2011, using traditional ML techniques, to nearly 90% today using modern DL techniques. The figure below illustrates the improvement in the ImageNet challenge over time [2].
Machine Learning vs Deep Learning
To understand Deep Learning’s dramatic improvement over traditional Machine Learning techniques, let’s look at how an example asset protection use case could be approached with both methodologies. The goal is to detect if the object in the field of view of a particular camera represents a threat and should generate an alarm (person, vehicle, etc), or constitutes mere background noise that can be ignored. To begin, through the use of a movement-based tracker (another ML system) a camera has detected motion and defined a region of interest around the object.
Machine Learning (ML)
The traditional Machine Learning pipeline generally requires the developer to represent an input (e.g. a region of interest in an image) into a structured feature descriptor of that input: for example, a set of numbers that represents the shape in the image (HOG, SIFT), or possibly another property in the image (colour, texture, etc.).
The model is then trained by feeding labelled examples of the object feature descriptors you want to recognise (person, vehicle) and object feature descriptors of objects you expect to see but want to ignore (trees, shadows, animals etc.). The Machine Learning algorithm learns to group these feature descriptors into these categories so, when a new unlabelled feature representation is fed to the system, it can make an assessment as to which category it might fall into.
A system’s accuracy hinges on a developers’ ability to come up with a feature descriptor which the Machine Learning algorithm can easily group into classes to detect vs those to ignore. One of the biggest advantages of using human-designed feature descriptors is the data required to train the ML model is reduced. Creation of labelled datasets to train any Machine Learning algorithm takes significant time and therefore resource. As a consequence, traditional Machine Learning techniques are still very much relevant due to this significant time and cost-saving.
Deep Learning (DL)
Deep Learning follows a similar process. However, instead of relying on a human-in-the-loop method of developing a robust feature descriptor, the Deep Learning system itself just looks at the labelled input data to learn the best way of grouping the images. By showing the system large numbers of samples (training), the system refines its model to best describe the data it is being shown. The disadvantage is that, for a Deep Learning model to learn that best representation from the data, a notably larger amount of data is necessary.
However, although the data requirements are more significant, the Deep Learning approach removes the guesswork of a developer trying to define the optimal representation of an input to enable the system to learn. It also has the advantage that the same approach can be applicable to a range of different problems, whereas traditional ML may require redesigning the feature descriptor based on the application.
Deep Learning has demonstrated its advantages over traditional methods. However, the real question is how it can be used to improve business processes or increase precision in detection, while reducing costs for security businesses. The race to contain costs whilst enhancing accuracy is where the biggest industry pain points are found. Typically, the deployment of Deep Learning backend systems in the field of CCTV analytics demands much more powerful and specialised hardware. Despite this, Deep Learning algorithms are starting to appear in the field and their benefits felt.
Example Algorithms for use in Security Applications
VCA Technology has been assessing algorithms based on customer feedback and ongoing projects. By exploring their applications, sample use cases, as well as requirements for implementation and deployment, the benefit of ML and DL, can be analysed.
Detection and Classification
Detection and classification algorithms combine the localisation and identification of an object in a single step, negating the need to use other algorithms to detect movement first. The image below represents the output of such an algorithm. In this instance, a bounding box outlining a detected object, a classification (person, car, etc.) and confidence in the algorithm’s decision (between 0 and 1). This analysis is done on a single frame, meaning the algorithm has no knowledge of where the object has been, or if a detected object was seen in a previous frame. Without this knowledge, simply knowing if a detected object is even moving is not possible, meaning stationary objects are detected. Additionally, rules such as dwell and direction analysis are also not possible without a motion detection and/or object tracking algorithm to provide this information.
Some common models are Faster R-CNN [3], Single Shot Detector (SSD) [4] and You Only Look Once (YOLOv3 seen above) [5]. Performance varies based on a number of parameters but around 15-20fps using an NVIDIA Titan X is possible. Minified versions of these models are also being developed.
GPU Hardware cost per channel: £250-350
Pros
Off-the-shelf localisation and classification
Able to support a large number of classes (>100)
Mature models improve accuracy, model size and therefore deployment costs are always coming down
Cons
Static objects are also detected
Requires tracking components for common applications in the security industry
Object Classification
Object classification is the process of categorising an area of interest into one of a number of predefined classes (person, vehicle, etc). This approach means you only need to make use of the algorithm when something of interest has been detected, e.g. movement in a zone. This facilitates the sharing of a single GPU resource between many channels. For example, VCA Technology’s Deep Learning Filter (DLF) model for detecting people and types of vehicles can classify around 34 objects per second on a NVidia GTX1080 (~£400). In a perimeter detection environment, this single GPU resource could be utilised across as many as 64 channels.
In the example above, moving objects have been tracked by VCA Technology’s motion tracking engine and bounding boxes have been defined. These regions of interest are then analysed by the Deep Learning Filter (DLF) to provide a classification (person, vehicle, etc.) and the level of confidence in the algorithm’s decision (between 0% and 100%). As with all motion detection engines, we can see objects created as a result of illumination changes from the car’s headlights. However, these objects are classified as background by the DLF and are ignored. Furthermore, the vehicle is classified and an event generated (red bounding box). Objects outside the defined red zone are also ignored and never sent to the Deep Learning Filter, saving GPU resources.
GPU Hardware cost per channel: less than £10
Pros
Very low cost per channel
Able to support multiple classes
Integrates with existing tracking technologies
Mature models improve accuracy
Cons
Requires object detection component to provide inputs to the model
Pose Estimation
Pose estimation algorithms allow the detection and localisation of body parts such as the shoulders, elbows and ankles from an input image. This information in isolation is not that informative, but can be used as the basis for systems which detect if someone has fallen over (Slip-trip-and-fall), or even behaviour analysis systems for fight detection. However, the computation cost is high, with the current state of the art methods (OpenPose [6]) runs at 4fps using a Nvidia GTX 1080ti.
GPU Hardware cost per channel: £500-700
Pros
Complex behaviours can be detected, covering both security and safety
Mature models improve accuracy
Active area of research, will bring cost per channel down
Cons
Cost prohibitive
Comprehensive work required to utilise the algorithm outputs into a fully-fledged system
Without a doubt, the developments in both accuracy and application for AI and its subsets over the last few years are astounding. A number of factors have contributed to this. The fact that AI was, until recently, a relatively new field of research means innovation is fast. The development of optimised hardware (parallel processing devices e.g. GPUs) enables the research, while edge-based processing devices enable cost-effective deployment of the solutions.
However, it is likely that this initial trend in fast-paced evolution will slow down in the coming years, and the huge progress in precision witnessed recently will give way to more incremental improvements over time. This is by no means a bad thing – on the contrary, it will help establish and refine the technology in a more controlled manner, allowing typically slow-moving industries and legislations to catch up with the technology.
Summary
The barrier to entry for deploying AI solutions and the financial practicality of the applications has been assisted by the continued reduction in component costs – in particular, processing. However, the cost of processing still remains rather high, and the performance expectations driven by TV, films and overzealous salespeople are simply not achievable in a competitive and cost-effective manner.
VCA Technology has always held efficient hardware requirements as a central tenet to its development programme, and continues to strive for the best performance at the best price. Potential users of Deep Learning-based video analytics need to ensure that their expectations of system performance are tempered by reality. Educating the industry on AI, Video Content Analytics (VCA) and Deep Learning accurately and comprehensively are crucial to setting more achievable expectations of these tools. Manufacturers and vendors in this market sector have a responsibility to ensure the products and performance are understood, not overhyped and oversold. All organisations involved in the sales and promotion of AI-based products should contribute to creating realistic expectations of this technology, or they risk negatively impacting the reputation not just of their company but of the security industry as a whole.
AI is here to stay, and its benefits for the security industry are clear. It will be an exciting few years and we look forward to facing and overcoming the challenges ahead.
Key Takeaways
Artificial Intelligence (AI) is the general term for current advances in visual perception, speech recognition, decision-making and translation between languages
Machine Learning (ML) refers to the algorithms that drive AI systems
Deep Learning (DL) is a subset of machine learning which has been the driving force behind the significant jump in performance across a range of applications
Deep learning algorithms are now mature enough to see widespread deployment in the security industry and are helping to improve accuracy and reduce costs
The fast innovation of AI algorithms over the last few years will now give way to more incremental improvements
Hardware requirements for the deployment of deep learning at the edge are helping to get algorithms out in the wild and making a positive impact in the security industry
References
[1] Anon, Artificial Intelligence: Meaning of Artificial Intelligence by Lexico. Lexico Dictionaries | English. Available at: https://www.lexico.com/definition/artificial_intelligence. [2] Anon, ImageNet Leaderboard: Papers with Code. Papers With Code : the latest in machine learning. Available at: https://paperswithcode.com/sota/image-classification-on-imagenet. [3] Ren, S. et al., 2017. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), [4] Liu, W. et al., 2016. SSD: Single Shot MultiBox Detector. Computer Vision – ECCV 2016 Lecture Notes in Computer Science, pp.21–37.pp.1137–1149. [5] Redmon, J. and Farhadi, A., 2018. Yolo v3: An incremental improvement. arXiv preprint arXiv:1804.02767 [6] Cao, Z. et al., 2019. OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields. IEEE Transactions on Pattern Analysis and Machine Intelligence, pp.1–1.
VCA Technology launches brand new powerful AI video analytics solution
VCA Technology, a UK provider of video analytics, has announced the release of VCA Server, an AI Deep Learning based video analytics software suite which provides a key upgrade to the company’s flagship VCA Core platform. Offering simple integration with VMS and NVR manufacturers’ technologies, the new release ensures that sophisticated analytics can be set-up and installed within as little as 15 minutes, allowing end users to significantly reduce false alarms with minimal disruption.
Central to VCA Server is its Deep Learning Filter which is pre-calibrated to immediately recognise vehicles and people, delivering an ‘instant analytics’ application. Its focus on ‘event filtering’ can, for example, distinguish foliage movement, shadows and changes in weather conditions from suspicious activity, enabling more accurate distinctions between true events and false positives. This makes it ideal for monitoring sterile zones and closed site installations and managing perimeter protection remotely. The VCA Core rule and feature sets are still available within the new release and for high density sites, such as airports and retail shopping centres that require a more comprehensive set up, there is still the option to use ‘Logical Rules’ alongside the extensive calibration features and the Deep Learning Filter.
The new release is compatible with both remote and local servers and can produce basic data or more comprehensive meta-data, depending on users’ requirements. Also available in a rack mounted unit, VCA Server is suitable for projects from four to 64 cameras and is ideal for applications with or without a VMS, where it would be used in conjunction with a local NVR for example. This provides installers with an extremely cost-effective solution and enables them to use VCA Deep Learning analytics at a significantly lower cost than the industry standard.
Kevin Waterhouse, Managing Director at VCA Technology, comments: “There is a misconception among integrators and installers that AI-based video analytics demands high processing requirements, making it cost prohibitive. However, our technology is compatible with all IP cameras of varying capabilities, as well as the most popular VMS and NVRs, greatly reducing cost and installation time. By quickly and seamlessly incorporating AI and Deep Learning into their existing portfolio, security providers can now future-proof their business by providing users with intelligent and real-time video analytics.
“For users, the launch of VCA Server means that there is now a more comprehensive solution that goes beyond just surveillance. With budgets being squeezed and a strained workforce, companies are looking for surveillance solutions that can overcome these industry bottlenecks and do more with less. This is where AI and Deep Learning significantly pushes the boundaries of standard video analytics.”
