Senior Software Engineer

Milestone Systems announces AI built for Security operations, powered by real-world security data. PR Newswire Today at 12:00pm PDT COPENHAGEN, Denmark, March 19, 2026 /PRNewswire/ - Milestone Systems, a global leader in data-driven video technology, today announced new AI and analytics solutions, enabling security teams to deploy generative AI with confidence. These include AI Search, Video Summarization, and Video Anonymization. While generative AI is transforming other industries, many security operators still rely on manual processes for footage review, incident documentation, and video anonymization. The stakes in security are high. Missed alarms or false positives can have serious consequences, making organizations cautious about hallucinations, inconsistent outputs, and trusting automated systems where accurate judgement is essential. At the same time, the regulatory landscape is evolving rapidly. With the EU AI Act, GDPR, and shifting data privacy standards, organizations managing terabytes of video want to learn from the data they already have - but face growing uncertainty about compliance. Milestone's new AI solutions are purpose-built to address these challenges - helping security operators with AI solutions that they can trust in critical moments. Targeted, Accurate, and Responsible: AI built for Security Designed to reduce manual effort at key points in the security workflow, Milestone's generative AI solutions allow for faster video review, consistent incident documentation, and regulatory compliance - aligned with the EU AI Act and GDPR - within the Milestone ecosystem: * AI Search enables investigators to quickly identify relevant elements using natural language - no complex filters or manual scrubbing required. * XProtect Video Summarization uses generative AI to automatically produce text descriptions of video footage, standardizing incident documentation for operators and dramatically reducing review time. * Video Anonymization supports compliance with GDPR and other privacy regulations. Consider a reported traffic accident. With AI Search, an operator can describe the vehicle involved with natural language to surface relevant footage across dozens of cameras in seconds. Video Summarization then generates a structured, standardized and thorough incident report automatically. And when that footage needs to be shared with external authorities, Video Anonymization ensures all bystander faces and license plates are redacted before export. All solutions are built for security teams to trust in real-life scenarios. Milestone's vision language models (VLMs) are fine-tuned on vertical- and use-case-specific video data, delivering consistent, reliable outputs purpose-built for video intelligence - not broad, multi-purpose AI repurposed from other domains. Milestone brings the same rigor to sourcing and managing video data - with compliance in mind from the start. Milestone's library of video training data is responsibly-sourced, fully anonymized, and traceable video data. Milestone uses brighter AI's anonymization technology in its own data pipeline and is now making it available to customers directly. Andrew Burnett, Chief Technology Officer, Milestone Systems, said: "How can we build on our decades of experience in video management to prepare our customers for the next generation of artificial intelligence? The answer is trust. Trust that the data is compliant, trust that the AI is accurate, and trust that these tools will genuinely make operators' jobs easier. That's what we're delivering today." Built on the world's largest compliant data library Milestone's compliant data library is the foundation of its generative AI solutions. Video data is acquired through fair-exchange agreements with Milestone customers around the world, anonymized using brighter AI technology, and tagged with over 300,000 categorizations using NVIDIA technology. The video data is curated into use-case specific datasets - beginning with EU and US traffic scenarios - and used to fine-tune NVIDIA Cosmos Reason foundation models. When trained on security use-case specific data, Milestone's VLMs deliver exceptional accuracy and consistency. Performance evaluations of the traffic VLM show significant improvements over base foundation models, including a 19.4% improvement in flow and direction correctness and 4.4% improvement in alert verification accuracy.* The dataset is fully traceable and preserves individual privacy, meaning every model trained on it is aligned with the EU AI Act and GDPR. The city of Genoa, Italy, is Milestone's latest data collaborator, contributing video data to further expand the library's diversity and geographic coverage. Bringing AI to VMS, VSaaS, and Analytics With AI Search, operators simply describe what they're looking for in natural language and the system identifies and surfaces the relevant video snippets in seconds. To support secure and air-gapped environments, Milestone will also offer on-premises AI Search through BriefCam: the full intelligence of AI with no internet connection required. AI Search will be available by the end of 2026. XProtect Video Summarization automatically generates detailed descriptions of video footage. Operators can send video clips with custom prompts and receive structured, consistent summaries of exactly what's happening in the scene. Integrated with XProtect's rules engine, summarization can run automatically on alerts, on a scheduled cadence, or on demand. The result is faster incident review, standardized documentation, and operators who can focus on response rather than paperwork. XProtect Video Summarization is powered by Milestone's growing suite of use-case specific VLMs, such as its US and EU Traffic models. Video Anonymization automatically redacts faces and license plates in video footage - enabling organizations to share, export, and store video in full compliance with data privacy regulations. Whether exporting evidence to law enforcement or sharing footage across departments, operators can ensure personal identities are protected without manual effort. Video Anonymization is powered by brighter AI's deep anonymization technology and will be available soon in Arcules and XProtect. See Tomorrow at ISC West At ISC West, Milestone will showcase its complete VMS, VSaaS, and analytics portfolio - built on an open platform designed to help organizations capture everything, understand what matters, and see what's coming before it arrives. Visitors can also discover the new XProtect App Platform and BriefCam analytics engine alongside other recent developments that help Milestone customers stay ahead of the curve while remaining responsible. Stop by booth #18053 to see what's new, see what's next, and see tomorrow. *Based on Milestone's in-house testing. Milestone Systems is a world leader in data-driven video technology used in industries as diverse as manufacturing, airports, law enforcement, retail, and traffic management. Ashlandtownnews provide a clear picture of how to create a safer, better and more prosperous world. Its product suite includes XProtect video management software, BriefCam AI-powered analytics, and Arcules cloud VSaaS. It helps its customers learn from the past, understand the present, and predict the future. Milestone is also advancing responsible Vision AI through Project Hafnia, the world's largest regulatory-compliant video data library, and brighter AI anonymization technology. Founded in 1998 and headquartered in Copenhagen, Milestone employs more than 1,500 people worldwide and has been an independent company in the Canon Group since 2014. | Lars Lemche | Lisbeth Nedergaard | Sophie Bahn Cederström | | Global Media Relations Lead | Vice President, Communications & Public Affairs | Sr. PR & Communications Business Partner | | [email protected] | [email protected] | [email protected] | | Tel: +45 26 14 01 14 | Tel: +45 41 76 02 72 | Tel: +45 50 84 29 55 | SOURCE Milestone Systems This is a paid placement. For further inquiries, please contact PR Newswire directly.

Apella Solutions introduces Argus H264/H265 Transcoder for Mission-Critical operations. Apella Solutions has released the Argus Professional Transcoder to provide efficient H264 and H265 video compression for reliable, real-time imagery transmission in bandwidth-constrained operational environments By Olivia Hannam / 18 Mar 2026 Apella Solutions has unveiled the Argus H264/H265 Professional Transcoder, a next-generation video and imagery solution built to deliver high performance in bandwidth-constrained, mission-critical environments. The Argus Professional Transcoder provides high-quality H264/H265 video and imagery at low bitrates, optimized for transmission over constrained and satellite links. Suitable for both unmanned and manned platforms, the system enables reliable, real-time visual intelligence in bandwidth-limited environments, supporting mission-critical operations with efficient compression and high visual fidelity. Advanced Compression The Argus system incorporates advanced compression capabilities to maximize efficiency across constrained networks. It supports standard H264 compression for reliable, efficient streaming, with an optional H265 (HEVC) transcoding capability that enables higher-quality compression at significantly reduced bitrates. The system is optimized for operation over satellite, RF, LTE, and other bandwidth-limited networks, maintaining high-fidelity imagery even in low-bandwidth conditions. By leveraging H265 compression, operators can achieve improved image clarity alongside reduced bandwidth consumption, supporting Intelligence, Surveillance and Reconnaissance (ISR), security, and remote monitoring applications. Platform Compatibility & Integration Argus is designed for seamless integration into existing operational ecosystems and is compatible with Android Team Awareness Kit (ATAK), Milestone, OpenVPN, and other industry-standard video management and situational awareness systems. This interoperability enables rapid deployment within established command-and-control infrastructures without the need for complex redevelopment or proprietary system dependencies. Flexible Licensing Argus operates on a one-off licence payment model rather than a subscription-based structure. Optional licences include an H265 compression upgrade, integrated WiFi access for remote video download, and an OpenVPN encryption module, with additional options to be confirmed. The system does not incur recurring server hosting fees and is not dependent on server-based infrastructure, providing users with operational independence and long-term cost predictability. Secure Design With the optional OpenVPN integration, Argus enables encrypted communications for secure remote access and data transfer. This supports the secure transmission of video and imagery, helps protect against unauthorized access, and aligns with modern operational security requirements. Remote Access & Operational Flexibility The optional WiFi access module allows operators to remotely download video footage directly from the system, helping to streamline workflows and reduce the need for physical handling. Argus' standalone architecture removes reliance on centralized servers, making it well suited to deployed field operations, maritime environments, Unmanned Aerial Vehicle (UAV) and Unmanned Ground Vehicle (UGV) platforms, as well as secure or classified networks. Built for Mission-Critical Performance Engineered for resilience and reliability, Argus supports real-time situational awareness with low-latency video delivery and high visual fidelity in bandwidth-constrained environments. The system is designed for operation across both unmanned and manned platforms and maintains consistent performance over satellite links, tactical networks, and remote infrastructure. With support for H264/H265 compression, compatibility with ATAK and Milestone systems, optional secure connectivity features, and a one-time licensing model, Apella Solutions' Argus Professional System delivers secure, high-quality video for bandwidth-constrained operations. Mission-Critical Antenna, Tracking, & Video Solutions for Defense, Law Enforcement & Security Applications 85 High Street, Winchester, Hampshire, SO23 9AE United Kingdom Regional Offices [email protected] Products from Apella Solutions. Omnidirectional plate antennas for direct embedding into unmanned aircraft frames Omnidirectional stubby antennas for space-contained applications Omnidirectional flexible whip antennas for tactical drones & robotics Portable flat panel antennas for video & data transceivers Low-profile RHC polarized antennas for tactical drones & robotics Defense Advancement showcases Apella Solutions' antenna, tracking and video solutions for defense, law enforcement, and security applications Nov 20, 2025

Milestone unveils Hafnia AI tools at NVIDIA GTC. 18 Mar 2026 Quick Read Summary is AI-generated, newsdesk-reviewed * Milestone unveils Synthetic Data and TaaS innovations for AI at NVIDIA GTC. * Hafnia enhances AI training with synthetic data, bridging data and deployment gaps. * VLM-as-a-Service offers tailored Visual Language Models for Smart City applications. At the NVIDIA GTC event in San Jose, Milestone Systems is set to highlight significant enhancements in its AI developer tools, particularly within the Hafnia platform. The recent expansion includes the addition of Synthetic Data and an upcoming Training-as-a-Service (TaaS) feature, designed to equip developers to train AI models for not just familiar situations but also for unusual or previously unencountered scenarios. Bridging the AI gap. Hafnia aims to bridge the divide between data, training, and deployment by enabling the development of superior vision AI models. These enhancements allow the models to be deployed within Smart City environments, emphasizing proactive readiness rather than just reactive learning. NVIDIA's Physical AI Data Factory Blueprint serves as the reference model for integrating data curation and augmentation with large-scale agentic orchestration, which facilitates the transformation of both real and synthetic data into comprehensive, physics-aware datasets available for model training. Advancing beyond historical data. Edward Mauser, Director of Hafnia at Milestone Systems, stressed the collaboration with NVIDIA. "Together with NVIDIA, we are taking Hafnia to the next level by combining trusted real-world data with synthetic augmentation," he stated, highlighting how this combination aids in training AI models that address both known and unforeseen scenarios. AI typically learns from historical events, but unpredictable urban environments, including rare weather or traffic conditions, are often improperly represented in traditional datasets. Hafnia integrates synthetic data into its curated video library to address this, using NVIDIA's Cosmos Transfer to ensure rare situations and underrepresented classes are included, leading to a more comprehensive data balance. Training-as-a-Service unveiled. Milestone unveils TaaS at GTC, giving developers seamless access to Hafnia's video dataMilestone is introducing its TaaS model at GTC, designed to consolidate fragmented training processes into a seamless solution, allowing developers to access Hafnia's comprehensive video data library for their training needs. This service enhances the ability to customize datasets and fine-tune models according to specific applications, ensuring compliance and traceability. The streamlined process through TaaS is geared toward simplifying the training and management of data, allowing developers to build powerful video analytics solutions significantly faster. VLM-as-a-Service for Smart cities. In partnership with NVIDIA, Hafnia is offering VLM-as-a-Service, which includes a suite of Visual Language Models optimized for use in Smart City applications. The service includes EU-optimized models specifically for traffic, with additional models forthcoming to support a wider range of scenarios. These models aim to reduce costs related to data collection and infrastructure needs while showing marked improvements in several performance metrics. The VLM-as-a-Service offers significant improvements, including a 19.4% increase in flow and direction accuracy, 8.9% better visual feature detection, and 4.4% enhanced alert verification accuracy, demonstrating its efficacy in real-world applications. Comprehensive cloud infrastructure. Hafnia employs a flexible, multi-cloud strategy incorporating AWS, Nebius, among others, to support the AI model lifecycle. This approach particularly addresses data sovereignty issues, allowing full control and secure processing of sensitive data. The collaboration featuring the Milestone Synthetic Data Generation pipeline is set to launch on Nebius. This infrastructure supports the development lifecycle comprehensively, from data sourcing and fine-tuning to extensive training and deployment, providing the required scalability and control. Attendees at NVIDIA GTC can explore Hafnia's expanded offerings through live demonstrations at Booth #2036. Edward Mauser will further elucidate on "A New Frontier for Vision AI with Expert Reasoning Agents" on March 18, aiming to unpack the advancing scope of VLMs for future applications.