Edge AI
 |
 |
 |
 |
 |
Open
|
Intuitive User
|
Advanced
|
Seamless
|
Time to
|
|
One of the main challenges in the Autonomous Mobile Robots (AMR) markets is to build enterprise-grade robots (based on ROS) quickly with the proper level of security and flexibility to scale up the operation with a fleet of AMRs, to ensure operational success with the right effective tools. MOV.AI and Lanner have joined forces to deliver integrated robotics leveraging the Robotics Engine Platform™ with Lanner’s Edge AI computing appliance. This collaborative AMR solution simplifies the development process by providing robot manufacturers and integrators with both the machine vision computing and the software platform they need to quickly build, deploy, and operate intelligent AMR solutions optimized for industrial environments. |
MOV.AI Robotics Engine PlatformThe MOV.AI ROS-based Robotics Engine Platform™ provides AMR manufacturers and automation integrators with navigation, localization, calibration, and the enterprise-grade tools they need for advanced automation. It includes a visual Integrated Development Environment (IDE), off-the-shelf algorithms and integrations, fleet management, flexible interfaces with warehouse environments such as ERP and WMS, and cyber-security compliance. |
|
|
LEC-2290 |
LEC-7242 |
|
|
|
|
|
|
|
|
Ready to Deploy? |
|
|
|
|
|
|
|
Restricted Zone Notifier |
Safety Gear Detector |
Machine Operator Monitor |
Predictive Maintenance |
Accelerate Industrial AI Monitoring DeploymentsImplementing AI-based industrial automation at the edge is crucial in mission-critical applications and requires real-time data processing with low-latency response. Lanner’s LEC-2290 has the computational performance to deliver real-time AI inference at the edge. Intel® Edge Insights for Industrial is an open and modular product validated software that aggregates and processes time series, image/video data at the edge to provide useful insights via edge analytics. Powered by the Intel® Distribution of OpenVINO™ toolkit, EIS accelerates development, enabling quick integrations of pre-trained models (e.g., Tensorflow, Caffe, etc.) for object recognition, classification, and facial recognition in vision-based solutions. To accelerate time-to-market AI deployment at the industrial edge, Lanner provides the hardware in a consolidated AI Kit together with Intel® software solutions for industrial Edge AI solutions. |
  |
|
|
|
||
Modular Data Bus |
|
|
Analytics Microservices |
|
|
|
|
||
Faster Edge DeploymentsConsolidated baseline AI hardware kit simplifies and accelerates deployment of edge AI solutions |
Quicker ProductizationPre-installed vision & analytics suite provides a vetted environment for development and integration of pre-trained use-case models |
Value-added SW SuiteFull vision suite optimized with OpenVINO™ to run faster on lower cost Intel hardware even with a CPU-only system |
Lanner Edge AI Appliance + Vision & Analytics SW suite
Ready to Deploy? |
|
|
|
|
|
|
|
People/Face Recognition |
Behavior Analysis |
Vehicle Recognition |
Business Intelligence |
Edge AI Video Analytics Technology for the FutureLanner’s LEC-2290 and LEC-2137 edge nodes have the performance and remote management features necessary to circumvent edge-to-cloud roundtrip bottlenecks and deliver speedy pre-processed insights from the edge for real-time AI Inference with rock-solid reliability. IoT devices, sensors and cameras send data to Gorilla IVAR edge computing devices for preprocessing and then forward it for analysis in public, private, or hybrid servers. Here, unstructured video and image data is transformed into structured data via deep learning. Events are stored in software defined storage and correlated and categorized for use in biometric authentication, account management, device management, business intelligence, and more. Gorilla IVAR™ real-time analytics technology gives insight into business and operations within a single dashboard. Protect your business with event-based solutions that effectively search and track people, vehicles, and objects. Detect suspicious events and prevent loss and shrinkage. |
 |
|
|
|
|
All-in-One VMS & IVA Solution |
Flexible & Scalable with Client Needs |
|
| Comprehensive yet compact Video Management System with Intelligent Video Analytics. Ideal for clients who prefer to take all-in-one and proactive video surveillance. | Scalable and flexible use from all-in-one machines or gateway hubs to large server scenarios. Well defined deployment to small shops, large sites or multiple site scenarios. | |
|
|
|
|
Intel® Optimized for Cost & Performance |
Adding Value with API Integration |
|
| Fully optimized by OpenVINO™ to run faster and give a better cost structure when compared to CPU/GPU-based hardware.Versatility that can run on CPU-only systems, NO GPU Needed. | Open architecture and API interface for quick integration with existing VMS solutions (e.g., Milestone) and other platforms (e.g., IoT, Access Control, Building Automation System – BAS, Kiosk) |
Lanner Intelligent NVR + Gorilla IVA & VMS
 |
|
Low Cost Inference with Intel CPU & iGPU using OpenVINOExtend computer vision and non-vision workloads across Intel® hardware, maximizing performance. It accelerates applications with high-performance, AI and deep learning inference deployed from edge to cloud. Robust Connectivity for Dual LTE or LTE + WiFi Fail-overThe LEC-2290 houses 1x Mini-PCIe w/ Nano-SIM and 1x B Key M.2 w/ Nano-SIM for Dual LTE or LTE + Wi-Fi Connectivity on a single device |
Ready to Deploy? |
|
|
|
|
|
|
|
Body Temperature Detection |
Mask Detection |
Cough Detection |
Social Distance Monitoring |
Health Monitoring in the COVID EraLanner’s AI inference edge node provides the digital I/O and PoE ports to connect and power IP cameras, sensors, actuators, and automatic-access controlled doors. PCI x16 slot easily integrates FPGA, GPU, VPU, and SSDs to accelerate AI-solutions with specific requirements for low-latency, high-throughput, and/or power-efficiency in reliable and mission-critical AI solutions. FogHorn Lightning™ Solutions are out-of-the-box packages of FogHorn’s award-winning Lightning™ Edge AI platform, providing use-case specific pre-configured machine learning models, notification capabilities, and visualization dashboards. Lighting™ Solutions allow organizations to rapidly deploy edge AI and immediately derive insights into common problems. Use them individually or combine solutions and customize with additional data science or integrate with existing IT systems, video management software, access control and more. |
 |
|
|
|
|
OOTB Intelligence and Insights |
Immediate ROI |
|
| FogHorn Lightning™ AI Solutions are out-of-the-box packages preconfigured with use-case specific machine learning models, notification capabilities, and visualization dashboards. | Quick to deploy, solutions can be set up in as little as a few hours. Lightning™ Solutions are also extensible in enterprise editions with unlimited opportunities |
Lanner Hardware + FogHorn Lightning™ Edge AI
 |
|
Flexible Access Control IntegrationWith 8x Digital I/O and 4x USB, you can easily interface with peripherals, sensors, and actuators to automate access-controlled doors and more. Optimized for Edge AI InferenceReduce expensive roundtrips to datacenters with powerful onboard compute directly on the edge where your data is generated. Built for 24/7 Operational ReliabilityLanner’s hardware platforms bring proven reliability, with a purpose-built design that can withstand the challenges in many edge deployments. Connect and power up to 4 IP PoE cameras4x Gigabit PoE ports capable of handling the highest resolution IP cameras. Rich expansion slots for GPU, VPU & FPGA AcceleratorsDeploy the right hardware accelerator for your AI workloads sensitive to low-latency, power efficiency, and/or throughput. |
Ready to Deploy? |
|
|
|
|
|
 |
Smart retail |
Manufacturing |
Smart Cities |
Low-latency Edge AI Solution for Retail, Manufacturing and Smart CitiesThe accelerating deployment of powerful AI solutions in competitive markets has evolved hardware requirements down to the very edge of our networks. Harnessing existing IT workflows is instrumental to edge-ready solutions capable of closing complex gaps between core business IT investments, competencies and upcoming AI opportunities. Designed and built in-house by Lanner for secure remote operation and accelerated workloads with the Tesla T4 Tensor core GPU, the LEC-2290E is validated and edge-ready out-of-the-box for streamlined NGC deployments. NVIDIA GPU CLOUD (NGC) fast-tracks edge AI solutions with its comprehensive catalog of containerized software GPU-optimized for edge-to-core solutions. |
 |
Raw throughput is just one of seven factors to consider in the overall evaluation of a system.
To get a complete picture of its performance you must take into account all of the above.
GPU Accelerated Edge AI
NVIDIA T4 enterprise GPUs supercharge the world’s most trusted mainstream servers. Its low-profile, 70-watt (W) design is powered by NVIDIA Turing™ Tensor Cores, delivering revolutionary multi-precision performance to accelerate a wide range of modern applications, including machine learning, deep learning, and virtual desktops.
From 2020-2025 AI is expected to grow by 25 billion in retail, manufacturing, and smart cities, with the demand for better, faster AI edge processing at its highest point. Below are examples of how an NGC- ready system can be utilized within these industries to bring cost-effective optimizations and valuable insights for today.
Lanner + NVIDIA Targeted Application Segments
 |
|
Intelligent RetailWith AI-enabled intelligent stores, retailers are reducing shrinkage, eliminating stockout, and gaining visibility into in-store customer behavior to optimize merchandising. These stores leverage data from cameras and sensors to provide valuable analytics that enable smart decision-making, improve operations, and increase efficiency. Additionally, the same infrastructure can be used for a faster customer checkout experience, including fully automated checkout systems. Efficient ManufacturingThe flexibility of automation and fast-paced technologies like 3D printing and ecommerce have greatly increased capabilities & diversity, along with overall complexity for manufacturers. To meet these demands manufacturers are relying on powerful AI to increase efficiency and improve logistics. Cutting edge AI implementations have enabled some of the largest manufacturers to manage the immense influx of millions of parts around the world every day. Machine vision driven robotics have optimized manufacturing of increasingly intricate and personalized products. Smart CitiesPopulous cities are deploying powerful autonomous AI solutions to reduce expenditure and increase revenue streams. Problems like vehicle-tax collection on such scales require machine vision AI solutions that can handle traffic monitoring and vehicle/license plate recognition. Rising public safety concerns with the ongoing pandemic have accelerated the creation and real world deployment of crowd and safety equipment detection solutions. |
NVIDIA EGX Edge Computing Platform
High Performance and ScalableCommunicate with customers in real time. Adapt quickly as data flows from billions of sensors, from factory floors to store aisles. Instantaneously diagnose diseases and provide life-saving patient care. All of this is possible—smart retail, healthcare, manufacturing, transportation, and cities—with today’s powerful AI and the NVIDIA EGX platform, which brings the power of accelerated AI computing to the edge. EGX starts with the tiny NVIDIA® Jetson Nano™, which in a few watts can provide one-half trillion operations per second (TOPS) of processing for tasks such as image recognition. And it spans all the way to a full rack of NVIDIA T4 servers, delivering more than 10,000 TOPS to serve hundreds of users for real-time speech recognition and other complex AI experiences. |
|
|
Ready to Deploy? |
|
|
|
|
|
|
|
|
|
26 TOPS/s in a small Package |
Transform Smart Retail |
Accelerate Smart Cities |
High-Yield Industrial Automation |
Low Power, Latency & Cost |
Actualize Your AI Vision Now with Revolutionary Cost-Effective Edge AI Hardware SolutionsCameras are pervasive across smart cities, retail businesses and industrial operations with each one generating swaths of data to process. Scaling AI to meet this challenge requires not just highly optimized software, but a processor architected to run it effectively. The Hailo-8™ AI processor, featuring up to 26 tera-operations per second (TOPS), significantly outperforms all other edge processors. Its area and power efficiency are leaps and bounds ahead of other leading solutions by a considerable order of magnitude (up to 3 TOPS/W). Lanner’s LEC-2290 pairs a robust x86 CPU and the Hailo-8™, leaving its PCI x16 slot for full-height FPGA, GPU or SSD to optimize demanding edge workloads. The low-footprint LEC-7242 integrates the Hailo module into a small form factor efficient edge vision appliance. Accelerate deployment with an edge-focused solution built to process multiple FHD video streams in real-time on a single device, and securely transmit curated metadata & insights with robust onboard network connectivity (wired and wireless LTE, CBRS, FirstNet, WiFi…) |
 |
|
|
|
|
AI Industry Standard Workflows and Framework Model Translations |
Real-time FullHD Multi-stream Semantic Segmentation |
|
| Hailo devices are accompanied by a comprehensive AI SDK tool chain which seamlessly integrates with existing deep learning development frameworks to allow smooth and easy integration in existing development ecosystems. | With an architecture that takes advantage of the core properties of neural networks, Hailo-8™ allows edge devices to run deep learning applications at full scale more efficiently and process multiple input streams in real-time. |
Proven Real-World AI Performance
Putting hardware to the test using well-known workloads showcases the Hailo-8™’s power, efficiency
and low-latency in real-time AI solutions, even while using just a fraction of its maximum TDP
Lanner's Edge Computing Appliances + Hailo 8 AI Processor
 |
|
Extensive I/O for System Integrations & AutomationWith 8x Digital I/O, multiple serial COM and USB ports along with modern network gigabit+ interfaces you can integrate with a wide range of systems. Built for 24/7 Operation, Even in Harsh EnvironmentsLanner’s hardware platforms bring proven reliability, with a purpose-built design that can withstand the harsh challenges in the industrial edge. LEC-7242 brings FCC/CE/PTCRB certification for LTE or WiFiLow/long-range wireless connectivity provides fallback redundancy communications for mission-critical and remote deployment. Rich Expansion Slots for mPCIe, M.2, PCIe x16Deploy the right hardware expansions and accelerators to overcome resource bottlenecks efficiently at the edge. |
Ready to Deploy? |
|
|
Implementing AI-based industrial automation at the edge is crucial in mission-critical applications and requires real-time data processing with a low-latency response.
Read more: Edge AI Platform Accelerates Industrial AI Monitoring Deployments