Search Results

< Back Celebrating Innovation: PureTech CEO Larry Bowe Named 2025 Security Innovator Jul 21, 2025 PureTech Systems is proud to announce that our President and CEO, Larry Bowe, has been honored with the 2025 Security Innovator Award . This recognition celebrates Larry’s vision, leadership, and unwavering commitment to pushing the boundaries of innovation in the security industry. The Security Innovator Awards are the industry’s only 100% peer-nominated program, designed to highlight the groundbreaking contributions of individuals who are reshaping the future of security. Nominees come from across the industry—integrators, consultants, practitioners, manufacturers, and service providers—all recognized for their role in advancing the field. This year’s class of Security Innovators is as diverse as it is experienced, representing the full spectrum of the industry. Each profile was written by the peers who nominated them, underscoring the impact these leaders have made in their communities and organizations. Larry’s recognition reflects not only his personal dedication to innovation but also PureTech’s broader mission: to transform perimeter and critical infrastructure protection with AI-powered video analytics, geospatial intelligence, and advanced automation. Under his leadership, PureTech continues to pioneer technologies that save lives, reduce operational costs, and deliver stronger, more effective security solutions. We’re honored to see Larry’s vision and contributions celebrated among such an inspiring group of industry leaders. Read about all of this year’s Security Innovator Award winners here . Previous Next

< Back PureTech Systems Integrates PurifAI with IMMIX’s Monitoring Platforms to Transform Video Alarm Validation Mar 28, 2025 Revolutionary AI-Powered Solution Drastically Reduces Nuisance Alarms Enhancing Monitoring Efficiency and Effectiveness For Immediate Release Phoenix, AZ – PureTech Systems Inc. , a leader in geospatial AI-boosted video analytics for wide-area perimeter and border security, is proud to announce the integration of its patented, award-winning SaaS solution, PurifAI™ , with IMMIX’s CS & GS video monitoring platforms. This integration delivers a breakthrough in video alarm validation, significantly reducing nuisance alarms while enhancing the efficiency of both self-monitoring and central monitoring operations. PurifAI is a cloud-based service designed to intelligently process video alarms from diverse sources—including cameras, DVRs, NVRs, third-party video analytics, and motion sensors. Leveraging PureTech’s advanced AI-powered analytics, PurifAI filters out nuisance alarms, ensuring only verified security events are forwarded to IMMIX’s monitoring platforms. Non-actionable alarms are logged for reference, reducing operator distractions and dramatically improving operational effectiveness. Key Benefits of PurifAI Integration: Near-Elimination of Nuisance Alarms – Operators can focus on critical threats instead of nuisance alarms. Scalability for Growth – Enables video monitoring centers to handle more sites without increasing staffing needs. Lower Operational Costs – Reduces time and resources spent on unnecessary alarms, improving cost-efficiency. Seamless Compatibility – Works with existing video infrastructure (NVRs, DVRs, cameras) without requiring additional hardware. Enhanced Operator Productivity – Fewer interruptions lead to better efficiency, job satisfaction, and customer retention. "We are excited to integrate our award-winning, patented AI-driven video analytics into IMMIX’s monitoring platform," said Larry Bowe, CEO of PureTech Systems Inc. "PurifAI is a game-changer for central monitoring operations, offering superior filtering accuracy that eliminates nuisance alarms. This empowers monitoring centers to enhance service reliability, effortlessly scale operations, and significantly cut operating costs." About PureTech Systems Inc. PureTech Systems Inc. is a privately owned company established in 2004 that develops, markets, and supports its patented location-based AI-boosted video analytics software, PureActiv®, for real time safety and security applications and our SaaS-based PurifAI. Their primary emphasis is on autonomous perimeter intrusion detection and classification of ground and aerial targets for country borders, coastlines, facility perimeters, and critical infrastructures (pipelines, railroads, dams, bridges, ports, utilities, power plants, military bases, and airports). To find out more about PureTech Systems Inc. visit our website at www.puretechsystems.com , call 602-424-9842 or email info@PureTechSystems.com . About IMMIX Immix is a global provider of software that improves the ability of commercial central stations and monitoring centers to manage and respond to security events as well as deliver a variety of video-centric managed services to customers. The software is deployed successfully across a wide array of environments servicing commercial, residential, and enterprise markets. Immix supports the largest third-party product integration library in the industry, enabling ease of deployment and system administration for a broad spectrum of organizations across the globe. Immix® is UL Certified in the USA and BS8418 compliant in Europe. For more information, visit www.immixprotect.com . Previous Next

< Back Winter 2023 Newsletter Jan 9, 2023 PureActiv® PurifAI Contact Us if you are interested in a beta test in Q1 PureActiv PurifAI is a monthly subscription-based service that uses AI Deep Learning enhanced video analytics to eliminate false/nuisance alarms before they reach your central monitoring operations and/or your smart phones for self monitoring. The patented cloud-based service receives video motion alarms from any source (new or existing cameras, DVRs, NVRs, other video analytics, motion sensors), and reassess them using cutting-edge AI technology to filter out false/nuisance alarms. Only those alarms that pass the AI filtering are forwarded to your central monitoring software, SMS, and/or email, on your smart phone. False/nuisance alarms are logged, but not forwarded so you don’t have to waste time looking at them. LEARN MORE Edge Computers with PureActiv® Inside PureTech Systems is delivering edge computers with PureActiv Inside for high accuracy autonomous perimeter intrusion detection at the edge. This AI-boosted edge processing enables users to add PureTech's best-in-class AI Video Analytics to new or existing systems for increased site security and situatio nal awareness. READ MORE Winner of 6 ASTOR Awards PureTech Systems was a winner of 6 AST ASTORS Homeland Security Awards. The company took home 4 Platinum awards in: Best Artificial Intelligence & Machine Learning Solution, Best Video Analytics Solution, Best Long Range Surveillance Solution, and Best Maritime Perimeter Protection Solution. In addition to the Platinum wins, PureTech was awarded Gold honors for: Best Perimeter Protection System, and Best Mobile Surveillance ISR Solution - RDAPSS. LEARN MORE In Case You Missed It PureTech Systems was awarded its 16th patent from the U.S. Patent Office for Alarm Processing and Classification System and Method. The newly awarded patent automates the verification of alarms and passes on only validated alarms to Central Monitoring personnel for further action. With the use of AI Deep Learning enhanced video analytics for false alarm rejection, PureTech’s PurifAI™ solution can eliminate up to 95% of false alarms . READ MORE HERE Previous Next

< Back PurifAI | Immix Integration May 13, 2025 IMMIX announces integration with PureTech Systems PurifAI. We are excited to announce that PurifAI, from PureTech Systems, is now fully integrated with the Immix GF/CS platform. The integration of PurifAI with Immix creates a seamless and efficient workflow between AI-driven video analytics and event response management. It also allows central stations to receive intelligent, actionable alarm data. Enriched with visual evidence PurifAI helps to reduce response times, operator fatigue, and nuisance alarms — all without requiring custom integrations. Key Benefits: ✔ Rapid Deployment – Minimal configuration effort with no need for complex or custom integrations. ✔ Lower Costs – Avoids expensive middleware or vendor-specific drivers; SMTP protocol supports broad compatibility. ✔ Reduced Alarm Fatigue – AI analytics pre-filter nuisance triggers before they reach Immix operators. ✔ Improved Efficiency – Central stations receive only validated alarms with context — boosting speed, accuracy, and productivity. ✔ Scalable Monitoring – Easily support hundreds or thousands of video endpoints across multiple customer sites. Read IMMIX's full page here Previous Next

< Back Vance Hilderman Vance Hilderman is a 25-year software/systems engineering entrepreneur with repeated success starting and growing profitable technical firms. In 1990, he founded what would become the largest independent avionics software services company in the world. His company appeared three consecutive years on the Forbes’ list of Fastest Growing Technical Companies. Vance was the President of this company for all 14 years of its operation. Considered an expert on safety critical software/computer systems and certification, he consulted with ninety five of the world’s one hundred largest aerospace companies plus numerous medical, industrial, and telecommunications entities. Vance founded two other companies; SynApps Software and Pacific Scientific, both of which were successfully grown and divested. He also co-founded HighRely, which he sold to Atego, in 2011. Vance currently serves on two boards and travels extensively throughout the world in his current role as President and Emerging Markets Business Developer/Sales for Atego HighRely. Vance holds a BSEE and MBA from Gonzaga, and a Masters in Computer Engineering from USC (Hughes Fellow). info@mysite.com 123-456-7890

< Back PureTech Announces New Reseller Agreement with Echodyne Feb 11, 2020 PHOENIX, Ariz. – PureTech Systems, a leader in geospatial AI video analytics, has entered into a reseller agreement with Echodyne. This reseller agreement authorizes PureTech to resell Echodyne’s EchoGuard 3D Surveillance Radars as part of PureTech's automated perimeter and wide-area protection solution. PureTech’s patented geospatial wide-area protection solution, along with Echodyne’s patented radar technology brings significant value to the market. PureActiv is an automated outdoor surveillance software system that provides security professionals with reliable real-time intrusion alerts including intruder location, imagery, and live and recorded video, all presented in an intuitive common operating picture. PureActiv fuses detections and tracks from multiple similar and dissimilar sensors, including EchoGuard, to enhance probability of detection and reduce nuisance alarms. Additionally, with PureTech's AI video analytics, detected objects such as animals and debris, can be automatically ignored, if desired. "We are excited to incorporate EchoGuard into our time-tested automated wide area protection solution", said Larry Bowe, President of PureTech Systems Inc. "EchoGuard enhances our wide-area mid-range human and vehicle detection capabilities as well as adds detection of small aircraft and drones to our solution." "We are pleased to add PureTech as an authorized reseller" stated Darrick Felise, Echodyne Director of Sales for the Americas. "PureTech has a solid reputation for addressing some of the most challenging large perimeter intrusion detection scenarios, which fits well with the capabilities of our market-leading EchoGuard Radar." About Echodyne® Echodyne offers the highest performing compact, software-defined, solid-state, true electronically scanned array (ESA) radar sensor. Ideally suited for machine perception in an autonomous age, Echodyne’s commercially priced radars are used by governments, industries, and solution integrators for border and perimeter security, critical infrastructure protection, unmanned aircraft systems, and autonomous vehicles. Privately held, the company is based in Kirkland, Washington, and is backed by Bill Gates, NEA, Madrona Venture Group, Vulcan Capital, and Lux Capital among others. For more information, please visit: www.echodyne.com About PureTech Systems® PureTech Systems Inc. is a manufacturer of wide-area perimeter surveillance software including internally developed and patented outdoor AI video analytics, multi-sensor integration and a map-based (real object size) command and control. PureTech Systems serves fortune 1000 firms, petrochemical, water and electric utilities, seaports, airports and federal, state and local governments. PureTech Systems, headquartered in Phoenix, Arizona, delivers and supports installations throughout the world. To find out more about PureTech Systems Inc. visit our website at www.puretechsystems.com or contact at 602-424-9842 or info@PureTechSystems.com . Previous Next

< Back PurifAI for TMA's Dispatch Spring Edition May 28, 2025 We’re excited to announce that PureTech Systems’ PurifAI® solution is featured in the Spring 2025 edition of TMA Dispatch , the official publication of The Monitoring Association. The ad highlights how PurifAI® empowers central stations with AI-boosted geospatial video analytics — delivering smarter, faster alarm verification from any video alarm source. Fully integrated with platforms like Immix and more, PurifAI® helps reduce nuisance alarms, improve operator efficiency, and elevate monitoring service value. Check out the full issue here: TMA Dispatch Spring 2025 Previous Next

< Back Surpassing Legacy Standards Jan 12, 2026 1. Introduction Some surveillance vendors claim they can automatically detect and classify humans and vehicles at extreme distances—sometimes 1 to 6 miles —using only a few pixels per target. In some cases, claims as low as 2–100 pixels are made. These claims are often justified by citing DRI (Detection, Recognition, Identification) or DORI tables, which were created decades ago for human observers , not autonomous computer-vision systems. At the same time, some vendors attempt to avoid AI and machine learning altogether, relying instead on simple motion detection, thresholding, or rule-based analytics, while still claiming “automatic detection.” Both approaches— misusing DRI/DORI or avoiding ML entirely —lead to systems that fail in real-world deployments. These claims conflict with the physics of imaging , the limitations of sensors , and the fundamental requirements of modern machine-learning (ML) —especially in environments where atmospheric turbulence, reduced contrast, camera shake, background complexity, partial occlusions, animals, and environmental motion are common. This white paper explains why DRI and DORI apply only to human perception, why they cannot be used to predict autonomous classification performance, why ML systems require substantially more pixels on target , and why systems that do not use AI/ML suffer from unacceptably high false-alarm rates . It also explains why long-range conditions require even more margin, and why no company can bypass physics with software. Any extraordinary claim must be validated through a Proof of Concept (POC) . 2. What DRI and DORI Actually Measure 2.1 DRI (Detection, Recognition, Identification) DRI was developed in 1958 to estimate how far a human observer could visually interpret a target using optical or thermal equipment. It describes whether a person can detect that “something is there,” recognize a general category (such as human versus vehicle), or identify a specific type. Humans can often recognize a person with very limited visual information—on the order of 12–16 vertical pixels , which might correspond to roughly: 12 pixels high × ~4 pixels wide ≈ ~48 total pixels , or 16 pixels high × ~5 pixels wide ≈ ~80 total pixels This is possible because the human brain can infer missing detail, guess intent, and apply context. DRI was never designed to evaluate autonomous systems. 2.2 DORI (IEC 62676-4:2015) DORI extends similar ideas to CCTV system design and again describes what a human operator can interpret when viewing video. Recognition-level DORI values often correspond to 7–12 pixels across the target width , still assuming a human is making the judgment. Neither DRI nor DORI evaluates whether a computer can autonomously classify a target, nor do they account for turbulence, camera shake, background complexity, camouflage, or occlusions. 3. Why DRI/DORI Cannot Be Applied to Machine Learning Machine-learning systems such as Convolutional Neural Networks (CNNs) and Transformers classify objects by extracting visual features from the image, including shape, edges, texture gradients, motion consistency, and frame-to-frame stability. If these features do not physically exist in the pixels, the ML system cannot classify the object. For example, a person appearing 10 pixels high × ~3 pixels wide ≈ ~30 total pixels does not contain enough information to reliably determine head shape, limb movement, torso structure, or vehicle geometry. A human observer might guess; an algorithm cannot. DRI/DORI recognition thresholds describe what humans can guess from incomplete data. ML systems require real, measurable information. 4. What Happens If You Do NOT Use AI / Machine Learning It is equally important to understand the consequences of not using AI/ML at all . Systems that rely solely on traditional video analytics—such as simple motion detection, pixel change thresholds, background subtraction, or rule-based logic—lack the ability to understand what is moving. They can detect motion, but they cannot reliably classify it. As a result, non-AI systems typically suffer from: Extremely high false-alarm rates Inability to distinguish humans from animals Inability to reject nuisance motion Poor scalability to large or complex environments 4.1 Why Non-AI Systems Generate Excessive False Alarms Without ML classification, a system must alarm on any motion that meets basic criteria. This includes: Animals Blowing vegetation Shadows Clouds and moving sun patterns Heat shimmer and atmospheric turbulence Camera shake Insects and birds Rain, snow, and dust Rule-based filters can reduce some noise, but they quickly break down in real environments because natural motion is highly variable. As thresholds are tightened to reduce false alarms, real threats are missed. As thresholds are loosened to avoid misses, false alarms explode. This tradeoff cannot be solved without classification. 4.2 Non-AI Systems Cannot Scale As coverage areas grow larger or more complex, non-AI systems become unmanageable: Operators are overwhelmed by alarms Alarm fatigue sets in Systems are ignored or turned down Real threats are lost in noise In practice, many non-AI deployments are eventually disabled or relegated to “monitoring only” because they generate too many alarms to be useful. 4.3 Detection Without Classification Is Operationally Dangerous A system that “detects motion” but cannot determine whether the object is a human, vehicle, animal, or irrelevant noise is not an autonomous security system. It simply shifts the burden to the operator, increasing workload and increasing the chance of human error. This is why modern perimeter security requires both detection and classification , and why AI/ML—used correctly and within physical limits—is essential. 5. Long-Range Physics Further Increase ML Requirements (1–6 Miles) At long ranges, multiple physical effects degrade imagery beyond what DRI/DORI assume: Reduced contrast Background complexity Atmospheric turbulence Camera shake Loss of gradients PureTech mitigates camera-induced motion by performing its proprietary image stabilization as the first processing step , ensuring downstream analytics operate on a stable image. Even so, long-range ML classification requires more pixels , not fewer. 6. Occlusions: Why Real-World Systems Must Design for More Pixel Margin Real environments include frequent occlusions caused by vegetation, terrain, infrastructure, and partial self-occlusion. When only part of a target is visible, the effective usable pixel count drops sharply. For example: 40 px high × 15 px wide ≈ 600 total pixels may be sufficient for a fully visible person. Seeing only half the body may require significantly more total pixels to maintain classification confidence. Designing only to ideal conditions guarantees failure. 7. Independent Evidence: Pixel Requirements for Reliable Autonomous Classification Independent research and industry experience consistently show that reliable autonomous classification cannot be achieved with only a handful of pixels , regardless of algorithm choice or marketing claims. In practical deployments, autonomous classification systems must achieve high probability of correct classification , low false-alarm rates , and low misclassification rates simultaneously. Achieving all three requires substantial spatial and temporal information about the target. Across a wide range of studies and real-world deployments, several consistent observations emerge: Very small targets (on the order of only tens of total pixels) do not contain sufficient structure for reliable autonomous classification. As pixel counts increase into the hundreds of total pixels , classification accuracy improves substantially, particularly when combined with temporal information such as motion consistency. At long ranges, additional factors—including atmospheric turbulence, reduced contrast, background complexity, and partial occlusions—further reduce usable information, increasing the amount of image data (pixels) required to maintain high accuracy. Importantly, there is no single universal pixel threshold that guarantees reliable classification at long range. The effective pixel requirement depends on multiple factors, including sensor modality, environmental conditions, target contrast, degree of occlusion, and system architecture. Systems that rely primarily on static image appearance and single-frame analysis tend to require significantly larger target images (in the thousands) to achieve acceptable performance under degraded conditions. More advanced systems that exploit stabilized imagery, coherent motion over time, and real-world constraints can extract more information from the same imagery—but no credible system can achieve reliable autonomous classification at DRI/DORI recognition levels or at 2 to 10s of total pixels . For long-range applications, it is realistic to expect that classification accuracy improves as available target information (pixel count) grows from a few tens of pixels into the hundreds or more , depending on conditions. Claims of reliable classification far below this regime are not supported by physics, industry experience, or independent research. 8. Training Data: Why Good ML Requires Large, Clean, Real-World Datasets ML performance depends heavily on training data quality and quantity. Modern vision models typically require hundreds of thousands to millions of representative examples. PureTech has been training visible and thermal ML models for 8 years , using hundreds of thousands of real-world images collected under operational conditions. Garbage In, Garbage Out Poor training data leads directly to poor performance. Garbage data includes: Targets that are too small Unrealistic close-ups never seen in deployment Low-contrast imagery Partial fragments without sufficient structure Severe blur or turbulence distortion Incorrect or inconsistent labeling PureTech applies proprietary preprocessing and quality controls to prevent such data from contaminating training. 9. Thermal vs. Visible Imaging Thermal imaging often outperforms visible cameras at long range and at night because it measures emitted heat rather than reflected light. Advantages include better target-background separation, no need for lighting, reduced impact from shadows, and reduced effectiveness of visual camouflage. Thermal does not eliminate physics limits, but it improves signal quality under difficult conditions. 10. MWIR, LWIR, and SWIR Overview LWIR (8–14 µm): uncooled, durable, good short- to medium-range performance MWIR (3–5 µm): superior long-range performance, higher contrast, requires cooling SWIR (~1–2 µm): reflected-light imaging, good detail in low light, poor in fog or total darkness Each has tradeoffs; none can violate physics. 11. PureTech’s Physics-Aligned Multi-Cue Approach PureTech Systems combines: Image stabilization (first step) Terrain-mapped object tracking for real-world size, speed, and direction Motion consistency filtering Shape plausibility checks Speed profiling Contextual and trajectory filtering ML classification applied PureTech holds 16 issued patents covering image processing, stabilization, and computer vision. 12. Why This Matters: Missed Detections, False Alarms, and ROI A missed detection can mean loss of life, loss of critical infrastructure, regulatory penalties, lawsuits, and reputational damage. False alarms waste time, consume resources, cause alarm fatigue, and obscure real threats. Excessive false alarms are functionally equivalent to missed detections because operators stop responding appropriately. 1. Introduction Some surveillance vendors claim they can automatically detect and classify humans and vehicles at extreme distances—sometimes 1 to 6 miles —using only a few pixels per target. In some cases, claims as low as 2–100 pixels are made. These claims are often justified by citing DRI (Detection, Recognition, Identification) or DORI tables, which were created decades ago for human observers , not autonomous computer-vision systems. At the same time, some vendors attempt to avoid AI and machine learning altogether, relying instead on simple motion detection, thresholding, or rule-based analytics, while still claiming “automatic detection.” Both approaches— misusing DRI/DORI or avoiding ML entirely —lead to systems that fail in real-world deployments. These claims conflict with the physics of imaging , the limitations of sensors , and the fundamental requirements of modern machine-learning (ML) —especially in environments where atmospheric turbulence, reduced contrast, camera shake, background complexity, partial occlusions, animals, and environmental motion are common. This white paper explains why DRI and DORI apply only to human perception, why they cannot be used to predict autonomous classification performance, why ML systems require substantially more pixels on target , and why systems that do not use AI/ML suffer from unacceptably high false-alarm rates . It also explains why long-range conditions require even more margin, and why no company can bypass physics with software. Any extraordinary claim must be validated through a Proof of Concept (POC) . 2. What DRI and DORI Actually Measure 2.1 DRI (Detection, Recognition, Identification) DRI was developed in 1958 to estimate how far a human observer could visually interpret a target using optical or thermal equipment. It describes whether a person can detect that “something is there,” recognize a general category (such as human versus vehicle), or identify a specific type. Humans can often recognize an object is a person with very limited visual information—on the order of 12–16 vertical pixels , which might correspond to roughly: 12 pixels high × ~4 pixels wide ≈ ~48 total pixels , or 16 pixels high × ~5 pixels wide ≈ ~80 total pixels This is possible because the human brain can infer missing detail, guess intent, and apply context. DRI was never designed to evaluate autonomous systems. 2.2 DORI (IEC 62676-4:2015) DORI extends similar ideas to CCTV system design and again describes what a human operator can interpret when viewing video. Recognition-level DORI values often correspond to 7–12 pixels across the target width , still assuming a human is making the judgment. Neither DRI nor DORI evaluates whether a computer can autonomously classify a target, nor do they account for turbulence, camera shake, background complexity, camouflage, or occlusions. 3. Why DRI/DORI Cannot Be Applied to Machine Learning Machine-learning systems such as Convolutional Neural Networks (CNNs) and Transformers classify objects by extracting visual features from the image, including shape, edges, texture gradients, motion consistency, and frame-to-frame stability. If these features do not physically exist in the pixels, the ML system cannot classify the object. For example, a person appearing 10 pixels high × ~3 pixels wide ≈ ~30 total pixels does not contain enough information to reliably determine head shape, limb movement, torso structure, or vehicle geometry. A human observer might guess; an algorithm cannot. DRI/DORI recognition thresholds describe what humans can guess from incomplete data. ML systems require real, measurable information. 4. What Happens If You Do NOT Use AI / Machine Learning It is equally important to understand the consequences of not using AI/ML at all . Systems that rely solely on traditional video analytics—such as simple motion detection, pixel change thresholds, background subtraction, or rule-based logic—lack the ability to understand what is moving. They can detect motion, but they cannot reliably classify it. As a result, non-AI systems typically suffer from: Extremely high false-alarm rates Inability to distinguish humans from animals Inability to reject nuisance motion Poor scalability to large or complex environments 4.1 Why Non-AI Systems Generate Excessive False Alarms Without ML classification, a system must alarm on any motion that meets basic criteria. This includes: Animals Blowing vegetation Shadows Clouds and moving sun patterns Heat shimmer and atmospheric turbulence Camera shake Insects and birds Rain, snow, and dust Rule-based filters can reduce some noise, but they quickly break down in real environments because natural motion is highly variable. As thresholds are tightened to reduce false alarms, real threats are missed. As thresholds are loosened to avoid misses, false alarms explode. This tradeoff cannot be solved without classification. 4.2 Non-AI Systems Cannot Scale As coverage areas grow larger or more complex, non-AI systems become unmanageable: Operators are overwhelmed by alarms Alarm fatigue sets in Systems are ignored or turned down Real threats are lost in noise In practice, many non-AI deployments are eventually disabled or relegated to “monitoring only” because they generate too many alarms to be useful. 4.3 Detection Without Classification Is Operationally Dangerous A system that “detects motion” but cannot determine whether the object is a human, vehicle, animal, or irrelevant noise is not an autonomous security system. It simply shifts the burden to the operator, increasing workload and increasing the chance of human error. This is why modern perimeter security requires both detection and classification , and why AI/ML—used correctly and within physical limits—is essential. 5. Long-Range Physics Further Increase ML Requirements (1–6 Miles) At long ranges, multiple physical effects degrade imagery beyond what DRI/DORI assume: Reduced contrast Background complexity Atmospheric turbulence Camera shake Loss of gradients PureTech mitigates camera-induced motion by performing its proprietary image stabilization as the first processing step , ensuring downstream analytics operate on a stable image. Even so, long-range ML classification requires more pixels , not fewer. 6. Occlusions: Why Real-World Systems Must Design for More Pixel Margin Real environments include frequent occlusions caused by vegetation, terrain, infrastructure, and partial self-occlusion. When only part of a target is visible, the effective usable pixel count drops sharply. For example: 40 px high × 15 px wide ≈ 600 total pixels may be sufficient for a fully visible person. Seeing only half the body may require significantly more total pixels to maintain classification confidence. Designing only to ideal conditions guarantees failure. 7. Independent Evidence: Pixel Requirements for Reliable Autonomous Classification Independent research and industry experience consistently show that reliable autonomous classification cannot be achieved with only a handful of pixels , regardless of algorithm choice or marketing claims. In practical deployments, autonomous classification systems must achieve high probability of correct classification , low false-alarm rates , and low misclassification rates simultaneously. Achieving all three requires substantial spatial and temporal information about the target. Across a wide range of studies and real-world deployments, several consistent observations emerge: Very small targets (on the order of only tens of total pixels) do not contain sufficient structure for reliable autonomous classification. As pixel counts increase into the hundreds of total pixels , classification accuracy improves substantially, particularly when combined with temporal information such as motion consistency. At long ranges, additional factors—including atmospheric turbulence, reduced contrast, background complexity, and partial occlusions—further reduce usable information, increasing the amount of image data (pixels) required to maintain high accuracy. Importantly, there is no single universal pixel threshold that guarantees reliable classification at long range. The effective pixel requirement depends on multiple factors, including sensor modality, environmental conditions, target contrast, degree of occlusion, and system architecture. Systems that rely primarily on static image appearance and single-frame analysis tend to require significantly larger target images (in the thousands) to achieve acceptable performance under degraded conditions. More advanced systems that exploit stabilized imagery, coherent motion over time, and real-world constraints can extract more information from the same imagery—but no credible system can achieve reliable autonomous classification at DRI/DORI recognition levels or at 2 to 10s of total pixels . For long-range applications, it is realistic to expect that classification accuracy improves as available target information (pixel count) grows from a few tens of pixels into the hundreds or more , depending on conditions. Claims of reliable classification far below this regime are not supported by physics, industry experience, or independent research. 8. Training Data: Why Good ML Requires Large, Clean, Real-World Datasets ML performance depends heavily on training data quality and quantity. Modern vision models typically require hundreds of thousands to millions of representative examples. PureTech has been training visible and thermal ML models for 8 years , using hundreds of thousands of real-world images collected under operational conditions. Garbage In, Garbage Out Poor training data leads directly to poor performance. Garbage data includes: Targets that are too small Unrealistic close-ups never seen in deployment Low-contrast imagery Partial fragments without sufficient structure Severe blur or turbulence distortion Incorrect or inconsistent labeling PureTech applies proprietary preprocessing and quality controls to prevent such data from contaminating training. 9. Thermal vs. Visible Imaging Thermal imaging often outperforms visible cameras at long range and at night because it measures emitted heat rather than reflected light. Advantages include better target-background separation, no need for lighting, reduced impact from shadows, and reduced effectiveness of visual camouflage. Thermal does not eliminate physics limits, but it improves signal quality under difficult conditions. 10. MWIR, LWIR, and SWIR Overview LWIR (8–14 µm): uncooled, durable, good short- to medium-range performance MWIR (3–5 µm): superior long-range performance, higher contrast, requires cooling SWIR (~1–2 µm): reflected-light imaging, good detail in low light, poor in fog or total darkness Each has tradeoffs; none can violate physics. 11. PureTech’s Physics-Aligned Multi-Cue Approach PureTech Systems combines: Image stabilization (first step) Terrain-mapped object tracking for real-world size, speed, and direction Motion consistency filtering Shape plausibility checks Speed profiling Contextual and trajectory filtering ML classification applied PureTech holds 16 issued patents covering image processing, stabilization, and computer vision. 12. Why This Matters: Missed Detections, False Alarms, and ROI A missed detection can mean loss of life, loss of critical infrastructure, regulatory penalties, lawsuits, and reputational damage. False alarms waste time, consume resources, cause alarm fatigue, and obscure real threats. Excessive false alarms are functionally equivalent to missed detections because operators stop responding appropriately. Organizations that choose systems based solely on lowest acquisition cost often incur far higher total cost of ownership and risk exposure. Investing upfront in systems designed around physics, robust ML, stabilization, terrain mapping, and multi-cue validation delivers far better ROI by avoiding catastrophic failures and operational collapse. 13. Proof of Concept: The Only Valid Verification Any vendor claiming autonomous classification at DRI/DORI pixel levels, at less than several hundred total pixels , especially under extreme long-range and occluded conditions must demonstrate the claim in a Proof of Concept . Physics always wins. 14. Conclusion DRI and DORI describe what humans can infer. They do not describe what autonomous systems require. Systems that ignore ML generate unacceptable false alarms. Systems that misuse ML or ignore physics miss real threats. PureTech Systems delivers reliable autonomous detection and classification by respecting physical reality, using stabilized imagery, terrain-mapped measurements, multi-cue analytics, disciplined ML training, and patented computer-vision technology—producing operational security systems that actually work as demonstrated by its real-world deployments in the most challenging environments such as country borders. Organizations that choose systems based solely on lowest acquisition cost often incur far higher total cost of ownership and risk exposure. Investing upfront in systems designed around physics, robust ML, stabilization, terrain mapping, and multi-cue validation delivers far better ROI by avoiding catastrophic failures and operational collapse. 13. Proof of Concept: The Only Valid Verification Any vendor claiming autonomous classification at DRI/DORI pixel levels, at less than several hundred total pixels , especially under extreme long-range and occluded conditions must demonstrate the claim in a Proof of Concept . Physics always wins. 14. Conclusion DRI and DORI describe what humans can infer. They do not describe what autonomous systems require. Systems that ignore ML generate unacceptable false alarms. Systems that misuse ML or ignore physics miss real threats. PureTech Systems delivers reliable autonomous detection and classification by respecting physical reality, using stabilized imagery, terrain-mapped measurements, multi-cue analytics, disciplined ML training, and patented computer-vision technology—producing operational security systems that actually work as demonstrated by its real-world deployments in the most challenging environments such as country borders. Previous Next

< Back PureTech Systems Announces the Release of PureActiv® Version 16 Nov 14, 2024 Phoenix, AZ – PureTech Systems Inc., a leader in geospatial AI-boosted video analytics for wide-area perimeter and border security, is proud to announce the release of PureActiv® Version 16. This new version introduces advanced features aimed at providing nuisance alarm elimination, and autonomous perimeter detection, classification, tracking, alerting, and deterrence—designed to address the evolving security needs of critical infrastructure. PureActiv® Version 16 leverages PureTech’s patented geospatial AI-boosted technology, delivering accuracy in detecting and classifying potential threats with near-zero nuisance alarms. One of the new capabilities in Version 16 includes enhanced machine learning (ML) models that significantly improve classification accuracy, allowing for precise differentiation between real access control events and faulty door switches/locks. Key features include: Enhanced ML Models : Improved classification accuracy, ensuring real access control events are confirmed while nuisance alarms are automatically rejected. PTZ Camera Tracking of Specific Intruders : Intelligent tracking of specific intruders with Pan-Tilt-Zoom (PTZ) cameras for real-time situational awareness and response. Access Control Real and Nuisance alarm differentiation plus auto-clearing. Integrated Air and Ground Intrusion Detection : Integration of ground and counter-drone detection into a single operating picture, providing protection across land, maritime domain and air. "We are excited to release PureActiv® Version 16 as the next step in autonomous perimeter security," said Larry Bowe, CEO of PureTech Systems Inc. "With enhanced machine learning models, advanced PTZ camera tracking, and integrated detection capabilities, PureActiv® continues to set the standard for protecting borders and critical infrastructures." “This new release enables new autonomous capabilities that go beyond conventional measures, providing operational advantages and seamlessly blending with other integrated technology systems,” says Chris Sincock, VP of Critical Infrastructure. For more information on PureActiv® Version 16 and its new security capabilities, visit www.puretechsystems.com or contact us at 602-424-9842. Previous Next

< Back PureTech Honored with 2020 ‘ASTORS’ Homeland Security Awards Dec 10, 2020 PHOENIX, Ariz. – PureTech Systems today announced it is the recipient of five (5) coveted 2020 ‘ASTORS’ Homeland Security Awards from American Security Today for its patented Video Analytics technology, PureActiv®. The Annual ‘ASTORS’ Awards, now in its fifth year, is the preeminent U.S. Homeland Security Awards Program, highlighting the most cutting-edge and forward-thinking security solutions coming onto the market today. “2020 has been a very challenging year for everyone due to the COVID-19 pandemic however, the 2020 ‘ASTORS’ Homeland Security Awards Program was again a huge success and many new categories were added including a section for COVID-19 Detection and Innovation,” said Michael Madsen, co-founder and publisher of American Security Today. The program is specifically designed to honor distinguished government and vendor solutions that deliver enhanced value, benefit and intelligence to end users in a variety of government, homeland security, enterprise, and public safety vertical markets. 90% of ‘ASTORS’ Award Winners return to compete in the Annual ‘ASTORS‘ Homeland Security Awards Program, and 100% of ‘ASTORS’ Sponsors have returned year to year to reap the benefits of their participation in the industry’s largest and most comprehensive Annual Awards Program. As the nation continues to respond to escalating threats from home and abroad, the innovative solutions being implemented to meet those threats, has led to tremendous growth in the field of Homeland Security. “Today, the United States is increasingly focusing on protecting public spaces, as well as IT/cyber security networks and they are calling on innovative companies like (‘ASTORS’ Winner) to help them do so,” according to Tammy Waitt, co-founder and editorial director of American Security Today. “‘ASTORS’ nominations are evaluated on their technical innovation, interoperability, specific impact within the category, overall impact to the industry, relatability to other industry technologies, and application feasibility outside of the industry,” concluded Waitt. PureActiv received awards in five (5) categories for its cutting-edge Video Analytics that are AI Deep Learning and Geo-spatially boosted providing real-time detection, classification, and tracking of perimeter security threats. The innovative solution received Platinum Awards for Best Perimeter Protection System, Best Long-Range Surveillance for Border Protection, and Best Machine-Learning and AI Solution. PureActiv® also received a Gold Award for Best Maritime Perimeter Protection System and a Silver Award for Best Video Analytics Solution. PureTech’s PureActiv® AI Video Analytics provide a fully-integrated outdoor wide-area perimeter protection system with the highest probability of detection and the lowest nuisance alarm rates for securing facilities, critical infrastructure, seaports, and borders. “We are honored to be recognized in so many categories for our groundbreaking achievements in American Security Today’s distinguished 2020 ‘ASTORS’ Awards Program for advances in protecting borders and perimeters with AI Technology. These awards demonstrate the 15+ years of hard work and determination that PureTech Systems has dedicated to providing the strongest layered automated detection, classification, tracking, and deterrent solution for protecting any critical infrastructure, facility, or border,” said Larry Bowe, Jr., President of PureTech Systems. To learn more about PureTech Systems solutions for perimeter protection, please visit https://americansecuritytoday.com/ast-proudly-presents-the-2020-astors-awards-winners/ or PureTech’s website at www.puretechsystems.com . Previous Next

Charlie Farnsworth, with over 40 years of experience in the software industry, currently serves as the Operations Manager at PureTech Systems. In this position, Charlie is responsible for... < Back Charlie Farnsworth Operations Manager Charlie Farnsworth, with over 40 years of experience in the software industry, currently serves as the Operations Manager at PureTech Systems. In this position, Charlie is responsible for the company's day-to-day operations, ensuring excellence in customer and technical support. Before joining PureTech, Charlie made substantial contributions to the aerospace and aviation sectors during his tenure at Honeywell Intl Inc. There, he played a crucial role in the development and testing of advanced avionics systems for commercial airliners and business jets. Most recently, his expertise was pivotal in the development of the Orion space capsule, a cornerstone project in deep space exploration where he was awarded EM-1 Orion Program Manager’s Commendation . Recognized for his leadership and dedication to advancing technology, Charlie 's forward-thinking approach and commitment to excellence are a perfect match for the innovative culture at PureTech Systems. Charlie 's holds a Bachelor of Science degree in Mathematics and Geology from Millsaps College, and a Master of Science in Mathematics from Southern Methodist University. Mail Document

< Back Gord Helm, MPA Gord Helm is the former Port of Halifax Manager of Security and Operations. Gord served over 20 years in the Royal Canadian Navy and is active in corporate governance. He currently sits on the Security Advisory Board of Source Security, serves as a Director with SWANA, Nova Scotia Chapter; and is a past Chair, Halifax Port Security Committee and recently completed 6 years as an Executive Board member with the Sacred Heart School of Halifax; and was Chair of the Harbour Operations Committee and Harbour Master for several International Halifax Tall Ship events. Gord holds an under graduate degree in political science and a Master of Public Administration from Dalhousie and a Master Certification in Project Management from St. Mary’s University. He is a certified PMP. Gord currently serves as Chief Technology Officer for Fourth State Energy, a company which delivers renewable energy from waste through plasma gasification. info@mysite.com 123-456-7890