The Metro AI Suite accelerates application development for sophisticated edge AI video safety, security, and smart city use cases.
The Metro AI Suite includes Intel® software such as OpenVINO™ toolkit, Deep Learning Streamer, Intel® oneAPI Toolkit, and other tools, libraries, and microservices for media analytics and AI performance optimization for the abovementioned use cases.
It includes the following tools and tookits: - Metro AI Suite SDK: Provides a comprehensive and modular toolkit for accelerated media processing and AI inference, designed to fast-track the development of visual AI solutions. - Visual Pipeline and Performance Evaluation Tool: Assess Intel® hardware options, benchmark performance, and analyze key metrics to optimize hardware selection for AI workloads. - Device qualification tool For device and equipment manufacturers, the suite includes a device qualification tool to verify and benchmark hardware performance and create system qualification reports. See recommended hardware catalog for a list of qualified system configurations.
The Suite also provides a collection of visual analytics sample applications, using deep learning and large models (generative AI):
| Sample Application | Definitions | User Docs |
|---|---|---|
| Loitering Detection | Effortlessly monitor and manage areas with AI-driven video analytics for real-time insights and enhanced security. | Link |
| Smart Parking | Effortlessly manage parking spaces with AI-driven video analytics for real-time insights and enhanced efficiency. | Link |
| Smart Intersection | Combines analytics from multiple traffic cameras to provide a unified intersection view, enabling object tracking across multiple viewpoints, motion vector analysis (e.g., speed and heading), and understanding object interactions in three-dimensional space. | Link |
| Video Processing for NVR | A sample application based on Video Processing Platform SDK that allows users to evaluate and optimize video processing workflows for NVR. | Link |
| Smart NVR | Integrates generative AI-powered vision analytics to a Network Video Recorder (NVR) and delivers advanced event detection, summarization, and automation while reducing bandwidth and storage requirements by processing and analyzing video data directly at the edge. | Link |
| Image Search by Text | A reference implementation using multi-modal large language models to perform image search with text query. | Link |
| Image Based Video Search | Performs near real-time analysis and image-based search to detect and retrieve objects of interest in large video datasets. | Link |
| Visual Search Question and Answering | A unified application that integrates a multi-modal search engine for image search with text query with a visual question and answering assistant. | Link |
See the respective sample applications to learn more about using them in your application development as well as customizing them to meet your use case needs.
Metro AI Suite reference implementations and platform blueprints: - Video Processing Platform: A platform blueprint for video security walls and similar applications utilizing video processing acceleration API. - Sensor Fusion for Traffic Management: A platform blueprint that integrates AI inferencing with sensor fusion technology, utilizing multi-modal sensors such as cameras and radars to deliver unparalleled performance, guiding you with designing such sensor fusion capabilities in your application development. - Interactive Digital Avatar: A reference implementation for integrating 2D/3D avatars with a backend LLM server to provide real-time and intelligent responses to user queries through speech-based conversational interfaces.