CCTV camera lenses - Expert commentary

HD over Coax provides cost-effective video surveillance upgrade
HD over Coax provides cost-effective video surveillance upgrade

According to IHS Market, it is estimated that there are over 60 million security cameras in the United States, and other reports say these cameras capture more than four billion hours of footage per week. Over the last decade, IP camera technology has dominated the conversation as it has provided users with a broad offering of enhanced image quality and features. With a large percentage of existing security systems relying on analogue, many end users looking for high definition (HD) video quality have been forced to take on a complete system overhaul. Infrastructure overhaul for HD video To make the switch, customers would need to change everything, from cameras to hardware to wiring– not to mention the lengthy installation process that would ensue. IP cameras also require higher Internet speeds and more cloud space. Whether constrained by budget, bandwidth or storage, many end users have been unable to adopt this new video surveillance method.Thanks to technological advancements within the security industry, HD over Coax offers a viable solution for integrators and end users alike Thanks to technological advancements within the security industry, HD over Coax offers a viable solution for integrators and end users alike. By utilising the current Coaxial cables, this offering yields high definition video, while requiring minimal infrastructure changes and is an optimal surveillance choice for security customers. Plus, with new advancements and updates being made frequently to this technology, there is a solution for every security need. The enhanced alternative of HD over Coax has been warmly welcomed in the security industry, thanks to its simple solutions and ever-evolving features. Many new analogue HD cameras are “plug and play,” able to connect directly to existing Coaxial cables. This eliminates the need for a complete system change, creating cost-savings for the end user and an enhanced video quality offering. Easy solutions for HD video As a result, integrators can cost-effectively upgrade their customer’s surveillance solution while using their legacy infrastructure, making it an attractive option for end users and an easy sell for dealers. Latency in video is another common issue with network-based camera systems, where even the slightest delay in video surveillance can hinder security response HD over Coax cameras themselves are always expanding and evolving to meet a wide array of security needs. With the introduction of fisheye and multi-sensor cameras, users now have a multitude of coverage options, not to mention the introduction of 4K bringing resolution options to the same level as IP. Some newer technologies are even touting 4K cameras paired with 4K digital video recorders (DVRs) made specifically for analogue systems. Longer cables grant transmission for up to 1600 feet, double the distance of standard analogue solutions, and triple that of IP systems. This single cable is able to transmit both HD video and audio. Recently, broadcast quality audio over Coax has become available in limited models, a substantial improvement over older analogue technology, which was unable to transmit audio. Stopping video delay Latency in video is another common issue with network-based camera systems. Even the slightest delay in video surveillance can hinder security response. IP cameras are forced to compress and packetise their video for transmission. The outcome of this is a reduced number of images per video, which in turn causes delay. HD over Coax on the other hand, delivers an unlimited amount of HD images in real time, with smooth motion and impressive clarity. Additionally, the point-to-point transmission delivers uncompressed video free of lag. Another touted benefit is that, unlike IP networked cameras, analogue systems provide a more secure video transmission. With so much sensitive information housed on a businesses’ network, adding another point of network access through an IP camera can create concerns for cyber security risks. HD over Coax delivers an unlimited amount of HD images in real time, with smooth motion and impressive clarity Preventing network hacking With HD over Coax, the physical connections between the camera and DVR prevent network hacking. By keeping the video surveillance system offline, security professionals are able to direct their attention to the physical threats at hand, rather than having to focus on deterring cyber security risks. One of the primary difficulties of deploying HD video solutions is the fact that many older systems utilise a wide variety of HD standards and platforms. To make matters more complicated, after HD over Coax was brought to market, manufacturers raced to create their own version of this technology. Today, the most popular proprietary standards are HD-CVI, HD-TVI and AHD. However, integrators and customers found that attempting to manage multiple HD technologies proved to be near impossible.Integrators and customers found that attempting to manage multiple HD technologies proved to be near impossible Diversifying surveillance through one DVR To combat these issues, manufacturers have introduced products with more flexibility to their portfolios. One example of this is the penta-brid DVR which grants the ability to seamlessly integrate multiple technologies deployed across one application. This means that systems with diverse camera brands and technologies, such as a mix of HD-CVI, HD-TVI, AHD, analogue or IP, can be connected through one DVR. For many end users with legacy analogue systems, penta-brid DVRs give them greater freedom to choose between a variety of solutions, rather than being limited to one option. With video resolution increasing, the space needed to store the footage is similarly rising. Penta-brid technology has been able to adapt to these evolving needs, giving users ample storage space to house the HD and 4K surveillance video with some of the newest models including H.265 compression.  HD casino surveillance made simple For casinos, HD images are critical for identifying unauthorised personnel and unlawful behaviours to create a safe environment for guests and staff While HD over Coax is beneficial to many end users and integrators, those in the casino and hospitality markets find it crucial. With a combination of high profile guests, large amounts of cash on hand, constant crowds and strict industry regulations, reliable video surveillance is a must. Deploying new IP systems comes at a stiff price. When looking to upgrade their video surveillance, casinos must also be mindful of the installation process. When moving to an IP-based system, ripping out old wires and replacing them with new is the standard practice. This practice can be both disruptive and costly, not to mention gaming regulations require casino activities be monitored at all times so a complete system shutdown would result in revenue loss. This cost can be hard to justify, especially when the current legacy analogue system remains in working condition with only the lower image resolution to date it. For these scenarios, the most cost-effective option is to leverage the legacy infrastructure, replace the existing cameras with new devices, and reap the benefits that HD video has to offer without any lapse in security. For casinos, HD images are critical for identifying unauthorised personnel and unlawful behaviours to create a safe environment for guests and staff. HD over Coax cameras now offer the same resolution as IP cameras with a plug and play approach, that cuts down on expense without sacrificing quality. For businesses and applications that are unable to adopt IP technology, whether it be cost or time prohibitive, HD over Coax now features most of the same benefits IP has to offer without breaking the bank. By providing clear images in real time, maximising existing infrastructure, and affording cyber security benefits, HD over Coax provides an attractive solution for many end users and integrators.

Saving lives with effective security control centre design
Saving lives with effective security control centre design

When people think of control rooms, images from James Bond movies or intense action stories come to mind. What they fail to realise is the incredible level of ergonomics, technology, precision and craftsmanship required to create a top-notch command and control room. “These are rooms of complex functionalities, where hundreds of elements must be integrated and function in sync,” says Jim Coleman, National Sales Manager, AFC Industries. Professional teams from several different industries must coordinate every single detail in order to ensure that functionality occurs each and every time. Reconfigurable furniture for control rooms AFC Industries is one company that specialises in equipping control rooms for security and other applications. AFC Industries was established in 1994 as a family-owned business that focuses on the design and construction of ergonomic products. Their height-adjustable units guarantee the right height for standing desks as well as traditional sitting levels. The company produces an array of Command and Control ergonomic security consoles and mounting solutions. Modular racking systems facilitate efficient storage of electronic and audio-visual equipment. As technology changes, older traditional consoles are no longer a necessity. Many organisations instead are choosing to use lighter, less costly, reconfigurable furniture that allows more flexibility. Command Centres need to be able to reconfigure the space at will. Because most systems are housed in secure data centres, users should be able to quickly move their positions by relocating their workstations, utilising different network connections. Simple control room features, like those addressing lighting or operator comfort, can make the difference in a correct or incorrect decision during a crisis Emergency operations centres A positive trend driving the market for control rooms is an increase in emergency operations centres (EOCs), says Randy Smith, President of Winsted. “Everybody is concerned about what happens in an emergency,” says Smith, and the centres are popping up as a tool for emergency preparedness. It’s another environment where sit-stand work stations are the rule. Winsted’s product lines include stock modular and customised elements in good-better-best categories – from basic to lots of “bells and whistles;” jobs can be configured from modular elements or customised as needed. Customised control rooms for seamless operation There is a lot at stake in control room design: Lives can depend on how effectively a control room functions in an emergency. Control rooms should seamlessly accommodate both everyday occurrences and crisis situations, says Matko Papic, Chief Technology Officer of Evans Consoles. Better-operating control rooms can increase efficiency and reduce and/or mitigate risk. Simple control room features, like those addressing lighting or operator comfort, can make the difference in a correct or incorrect decision during a crisis. Addressing operator comfort can reduce the possibility of workers’ compensation claims. End users are seeing multiple benefits of creating a better operating environment, better sightlines, more comfort and attention to ergonomics. As a fully integrated control room solutions provider, Evans Consoles approaches the needs of a control room environment beginning in the conceptual/operational planning stage. They consider broad issues such as how information will be processed, the interface between technology and operators, and the cognitive and physical interactions of operators – understanding that these factors drive the layout and function of control rooms. After analysing tasks to be performed in the environment, Evans lays out the consoles to meet those needs. Rather than a predesigned solution, each installation is tailored around a specific application. Read part 2 of our Control Rooms series here

HD surveillance: Secrets to producing the best possible image quality
HD surveillance: Secrets to producing the best possible image quality

Many end-users shell out the cash to acquire the newest high-end devices, plug in, and expect to be wowed A well-developed surveillance system can give a single security guard the power to see what otherwise might take a hundred pairs of eyes to see. But what happens when all the components are all connected and powered up, and the resulting image on the screen is, well, indiscernible, or, at the very least, terribly pixelated? Many end-users shell out the cash to acquire the newest high-end devices, plug in, and expect to be wowed. Often enough, however, what they see on the screen is not what they were expecting – and they wonder what they just paid for. In a good high-definition system, what factors actually create the best image quality? With so many variables involved, from the camera’s lens to the imaging algorithms to the monitor resolution – just to name the obvious ones – how do system integrators achieve the best on-screen images?   The lens The first component to handle light from an object, this may be the one most taken for granted in cameras of any sort. (Just try scratching or cracking one and you’ll agree.) In the days of analogue cameras, it seemed that any old lens would do just fine. However, as the technology inside cameras evolved and more powerful sensors (more pixels) became available, engineers and programmers demanded more from lenses. Moreover, intelligent video content analyses would be impossible without high-accuracy lenses.In what way do lenses impact the image quality? The key factor here is light transmission. The quality of light passing through the lens itself will forever be critical to the quality of image reproduced. A lens made using ultra-precision molding aspherical technology achieves more accurate colour, better light, and clearer images. Multilayer broadband anti-reflection coating further maximises a lens's light transmission while minimising the residual reflection of light on the surface of each optical lens. Variables involved include the camera’s lens, the imaging algorithms and the monitor resolution When it comes to fabricating a megapixel lens that hits the mark, the materials used and the processes by which lenses are produced are the two most critical criteria. The materials most often used to create lenses are glass and specialised plastics. An HD lens made of ultra-low-dispersion optical glass – which, by using dispersion characteristics that are different from those of conventional optical glass – will deliver better HD performance. Machine-automated lens production using specialised plastics results in high output for camera producers, and the lenses produced are more uniform in design and quality. For an HD vari-focal lens, its image quality depends largely on the precision of the cam. The cam rotates to drive the zoom and focus lens groups forward and backward for a smooth continuity of focal length and adjustment of the focal point. A lack of precision with the cam inevitably causes an offset or tilt of the lens' optical axis during zooming and focusing, leading to a serious loss of image quality. Lens production is a delicate balancing act. The slightest errors or imperfections will be very noticeable when tested Lens production is a delicate balancing act. The slightest errors or imperfections will be very noticeable when tested. The features of a lens that affect image resolution, clarity, and contrast must be perfect. Achieving uniformity of image resolution at the centre and the edges of a lens requires high-precision machinery. And once a lens has been properly crafted, the assembly of the camera, the lens housing materials, and the alignment of the optical axis demand utmost accuracy. To put it mildly, quality control must be rigorous. Image signal processing As light passes through the lens, the sensor captures it and converts it to data. Raw RGB data is transmitted by the camera sensor and undergoes Image Signal Processing (ISP) such as noise reduction, white balance, WDR, curve correction and colour correction, etc. The data is then transformed to true colours for each pixel point, for people to see images that look “normal” to the human eye. It is the Image Signal Processing that defines the final image quality on the screen. Collecting data in different conditions is vital, for instance, outdoor data should be analysed with natural light on days with sun, overcast, rain, and fog, at dawn, at dusk, and so on. Similarly, when using cameras equipped with infrared sensors, testing the IR light signals in various conditions is necessary as well.  Actual image performance depends upon variables such as low light illumination, signal to noise ratio, dynamic range of light, and more. ISP algorithms aim at increasing the signal data and decreasing noise. Cameras with Wide Dynamic Range (WDR) will yield improved video imaging with both background and foreground objects in high contrast or high-backlight environments, maximising the amount of detail in brighter and darker areas in one field-of-view. In scenes with low contrast and low light, the sensors deliver digital image signals and at the same time send some amount of digital noise that directly hinders image clarity. Three-dimensional digital noise reduction (3D DNR) removes unwanted artifacts from an image, reducing graininess. Where cloudy weather poses a challenge, auto-defogging technology helps to identify the density of fog or rain with gray-white colour ratio analysis, and imbues images with true colour reproduction. Ramping up the megapixels and frame rates yields great video, but also results in more bandwidth used and more storage occupied Matching megapixels to image quality When the factors mentioned above line up well, correlating cameras and monitors creates the best viewing experience. When a high definition camera is in place, a monitor with a high resolution will display images much more clearly. But if the monitor’s resolution is low, it will not deliver the high-quality images expected – or possible – from that HD camera. For an 8 MP camera, for instance, users do best to apply monitors with 4K × 2K resolution. Though common sense, this deserves to be mentioned because users might decide to upgrade their systems with 4K monitors, but with perhaps 1.3 MP cameras installed. In such a scenario, there’s no guarantee the on-screen image quality will automatically improve. Managing data and bandwidth In terms of a complete, high definition surveillance system, when the right factors come together and the calibrations are set, image quality – even in a standard HD 1080p setup – can be extremely good. The final piece of the puzzle is managing the data. Ramping up the megapixels and frame rates yields great video, but also results in more bandwidth used and more storage occupied. Squeezing bandwidth threatens image quality and clarity, but keeping ample room for signal transmission and storage will eventually increase the overall cost for customers. Is it possible for integrators to optimise their customer’s system and, at the same time, stay within budget constraints? Luckily, it can be done. Squeezing bandwidth threatens image quality and clarity, but keeping ample room for signal transmission and storage increases the overall cost for customers To do this, a more efficient video encoding solution would allow an improvement in compression efficiency of 40–50% over H.264. Improvements to algorithms that are adaptive to a particular scene give users control over bitrate. Another option would be to start recording video only when an event triggers an alarm, since most security guards are primarily concerned with moving objects rather than a scene’s generally stagnant background. This intelligently helps optimise bandwidth and storage consumption. Another method is to use a single panoramic or fisheye camera in place of several HD cameras for coverage – the reduced number of security devices will reduce bandwidth demands and the rate of storage consumption as well. Getting the best image quality Now let’s put this all together. Naturally, integrators and users will refer to their product specs to understand features and functions, fine-tuning each component for best results. Also, as suggested above, users should select an HD camera comprehensively in terms of lens performance, pixels, image quality, and overall system compatibility and performance. Next, matching the backend device and management platform should be carefully considered in a complete security system. Installing equipment that has been engineered for a given scene is a must, along with strategising how to get the most coverage out of the lowest number of cameras. Finally, product quality, warranty, price, and on-going customer service are all important factors that customers should take into account as well.

Latest Panasonic System Communications Company Europe news

Panasonic i-PRO EMEA announces expansion of the new AI-driven camera line-up at The Security Event 2021, headed up by Gerard Figols
Panasonic i-PRO EMEA announces expansion of the new AI-driven camera line-up at The Security Event 2021, headed up by Gerard Figols

Panasonic i-PRO EMEA is using The Security Event 2021 in Birmingham, one of Europe’s first large-scale security events, to be held face-to-face in 15 months, to share news about the newly-founded independent company that has been transferred from Panasonic. Gerard Figols will be leading the security market expansion of the new company, as it becomes an independent organisation from Panasonic, effective October 1, 2021. Innovative i-PRO products Gerard Figols, who moves from heading Panasonic’s European Total Security business unit, will use the company’s new agility to quickly respond to market developments, delivering more high-quality products, in shorter development times and at good value for money. The objective is to make innovative i-PRO products more available and accessible and increase overall competitiveness. Aligned with these goals, Panasonic i-PRO EMEA also aims to lead the widespread AI (Artificial Intelligence) technology adoption in the security camera market, by making AI the new standard. The Security Event 2021 At The Security Event 2021, i-PRO has expanded its line-up with 4 new AI-capable outdoor models At The Security Event 2021, i-PRO has expanded its line-up with 4 new AI-capable outdoor models, with 2 MP resolution in bullet and dome shape. The current AI-capable portfolio includes cameras starting at 2 MP resolution, up to 4K, in order to give all businesses access to the advantages of AI. i-PRO plans to triple the number of cameras in the range, over the next 6 to 12 months. Besides the advantages of cost savings, system reliability and flexibility, at the same level of accuracy as server-based systems, i-PRO AI-driven cameras are open systems that enable any developer to work on their own apps, to run on the cameras. AI-driven outdoor camera models “In order to underline our new direction and the evolution that the company is going through, combining expertise of more than 60 years of industry know-how, with innovative open technology, like AI, we will also begin to use i-PRO as the standalone product identity from April 1st, 2022,” said Gerard Figols, currently Head of Panasonic’s European Total Security business unit. He adds, “It will be the same quality products, introducing additional innovation from the i-PRO brand and its value to bring the product to the next stage in this new era.”

Panasonic AI-driven cameras empower an expanding vision of new uses
Panasonic AI-driven cameras empower an expanding vision of new uses

Imagine a world where video cameras are not just watching and reporting for security, but have an even wider positive impact on our lives. Imagine that cameras control street and building lights, as people come and go, that traffic jams are predicted and vehicles are automatically rerouted, and more tills are opened, just before a queue starts to form. Cameras with AI capabilities Cameras in stores can show us how we might look in the latest outfit as we browse. That’s the vision from Panasonic about current and future uses for their cameras that provide artificial intelligence (AI) capabilities at the edge. Panasonic feels that these types of intelligent camera applications are also the basis for automation and introduction of Industry 4.0, in which processes are automated, monitored and controlled by AI-driven systems. 4K network security cameras The company’s i-PRO AI-capable camera line can install and run up to three AI-driven video analytic applications Panasonic’s 4K network security cameras have built-in AI capabilities suitable for this next generation of intelligent applications in business and society. The company’s i-PRO AI-capable camera line can install and run up to three AI-driven video analytic applications. The AI engine is directly embedded into the camera, thus reducing costs and Panasonic’s image quality ensures the accuracy of the analytics outcome. FacePRO facial recognition technology Panasonic began advancing AI technology on the server side with FacePRO, the in-house facial recognition application, which uses AI deep learning capabilities. Moving ahead, they transitioned their knowledge of AI from the server side to the edge, introducing i-PRO security cameras with built-in AI capabilities last summer, alongside their own in-house analytics. Moreover, in line with the Panasonic approach to focus more on collaboration with specialist AI software developers, a partnership with Italian software company, A.I. Tech followed in September, with a range of intelligent applications, partially based on deep learning. Additional collaborations are already in place with more than 10 other developers, across the European Union, working on more future applications. i-PRO AI-capable security cameras Open systems are an important part of Panasonic’s current approach. The company’s i-PRO AI-capable cameras are an open platform and designed for third-party application development, therefore, applications can be built or tailored to the needs of an individual customer. Panasonic use to be a company that developed everything in-house, including all the analytics and applications. “However, now we have turned around our strategy by making our i-PRO security cameras open to integrate applications and analytics from third-party companies,” says Gerard Figols, Head of Security Solutions at Panasonic Business Europe. Flexible and adapting to specific customer needs This new approach allows the company to be more flexible and adaptable to customers’ needs. “At the same time, we can be quicker and much more tailored to the market trend,” said Gerard Figols. He adds, “For example, in the retail space, enabling retailers to enhance the customer experience, in smart cities for traffic monitoring and smart parking, and by event organisers and transport hubs to monitor and ensure safety.” Edge-based analytics offer multiple benefits over server-based systems Edge-based analytics Edge-based analytics offer multiple benefits over server-based systems. On one hand, there are monetary benefits - a cost reduction results from the decreased amount of more powerful hardware required on the server side to process the data, on top of reduction in the infrastructure costs, as not all the full video stream needs to be sent for analysis, we can work solely with the metadata. On the other hand, there are also advantages of flexibility, as well as reliability. Each camera can have its own individual analytic setup and in case of any issue on the communication or server side, the camera can keep running the analysis at the edge, thereby making sure the CCTV system is still fully operational. Most importantly, systems can keep the same high level of accuracy. Explosion of AI camera applications We can compare the explosion of AI camera applications to the way we experienced it for smartphone applications" “We can compare the explosion of AI camera applications to the way we experienced it for smartphone applications,” said Gerard Figols, adding “However, it doesn’t mean the hardware is not important anymore, as I believe it’s more important than ever. Working with poor picture quality or if the hardware is not reliable, and works 24/7, software cannot run or deliver the outcome it has been designed for.” As hardware specialists, Figols believes that Panasonic seeks to focus on what they do best - Building long-lasting, open network cameras, which are capable of capturing the highest quality images that are required for the latest AI applications, while software developers can concentrate on bringing specialist applications to the market. Same as for smartphones, AI applications will proliferate based on market demand and succeed or fail, based on the value that they deliver. Facial recognition, privacy protection and cross line technologies Panasonic has been in the forefront in developing essential AI applications for CCTV, such as facial recognition, privacy protection and cross line. However, with the market developing so rapidly and the potential applications of AI-driven camera systems being so varied and widespread, Panasonic quickly realised that the future of their network cameras was going to be in open systems, which allow specialist developers and their customers to use their sector expertise to develop their own applications for specific vertical market applications, while using i-PRO hardware. Metadata for detection and recognition Regarding privacy, consider that the use of AI in cameras is about generating metadata for the detection and recognition of patterns, rather than identifying individual identities. “However, there are legitimate privacy concerns, but I firmly believe that attitudes will change quickly when people see the incredible benefits that this technology can deliver,” said Gerard Figols, adding “I hope that we will be able to redefine our view of cameras and AI, not just as insurance, but as life advancing and enhancing.” i-PRO AI Privacy Guard One of the AI applications that Panasonic developed was i-PRO AI Privacy Guard Seeking to understand and appreciate privacy concerns, one of the AI applications that Panasonic developed was i-PRO AI Privacy Guard that generates data without capturing individual identities, following European privacy regulations that are among the strictest in the world. Gerard Fogils said, “The combination of artificial intelligence and the latest generation open camera technology will change the world’s perceptions from Big Brother to Big Benefits. New applications will emerge as the existing generation of cameras is updated to the new open and intelligent next generation devices, and the existing role of the security camera will also continue.” Future scope of AI and cameras He adds, “Not just relying on the security cameras for evidence when things have gone wrong, end users will increasingly be able to use AI and the cameras with much higher accuracy to prevent false alarms and in a proactive way to prevent incidents." Gerard Figols concludes, “That could be monitoring and alerting when health and safety guidelines are being breached or spotting and flagging patterns of suspicious behaviour before incidents occur.”

Panasonic joins IPSA as a founder to support key workers
Panasonic joins IPSA as a founder to support key workers

Panasonic Security Solutions announced that it had become a Founder of the relaunched International Professional Security Association (IPSA). The association is dedicated to supporting those individuals and companies working in the fire and security sector, many of which are classified as key workers. Member job roles range from installation technicians of security systems and fire systems to vital security personnel. Free app and membership The Panasonic investment, as one of a number of Founders, has helped to fund a radical shake-up of the UK's longest established security association. New initiatives include free membership for all frontline security and technical workers and a new free app. The app will provide information and training modules, and a network of approved suppliers that support the industry The app will provide information and guidance, welfare, training modules, and a network of approved suppliers that support the industry. IPSA also plans to use the app to capture important data and trends about unreported incidents, mental well-being, injuries, diversity, and disability - all of which, for the first time, will allow for an accurate picture of incidents affecting front-line security officers, businesses, and the wider community. Driving security standards "IPSA plans to represent the security industry with "one voice" and the support of Founder organisations, such as Panasonic, enable us to deliver on this vision," said Simon Pears, Chairman of IPSA. "Each and every one of our Founders is showing their commitment and support in driving security standards and professionalism forward. Their support is invaluable as we showcase all aspects of the security solutions and career progression available." Safeguard security society Commenting on the investment, Panasonic Security Solutions Marketing Manager Rachael Crook, said, "Panasonic has a 60-plus-year proud history of supporting the security industry - providing reliable camera and software solutions and the valuable real-time information used by its professionals to safeguard society.” “With the relaunch of IPSA, its commitment to the industry, and the important role it plays in society, as well as the focus on technology solutions like the app, it made perfect sense for us to support the new-look organisation."

Related white papers

Connected video technology for safe cities

Monitoring traffic flow: Everywhere, all the time

Six things to look for when adding AI cameras to your operation