The explosion of smart devices, high-bandwidth networks like 5G, and the need to capture and discern data closer to the source have led to the need for a unified edge-analytics application development framework. Devices at the edge, however, are diverse, with each providing their own optimized framework. This makes application portability a big challenge. What
The following piece is from insight.tech, an Intel-sponsored publication leveraging the Intel® Partner Alliance to provide business and technical decision-makers the latest and greatest technology trends and business solutions in the IoT space. Fixed-to-mobile, AI-powered video analytics for buildings By Pedro Pereira. November 16, 2022. Smart buildings deliver continuous streams of data from sensors, cameras,
Megh’s fully customizable, cross-platform Video Analytics Solution (VAS) is available as the VAS SDK toolkit and VAS Suite of products. VAS SDK is targeted for enterprises, system integrators (SI), OEMs, and developers, enabling full control to optimize video analytics pipelines and integrate highly customizable AI into applications. VAS SDK is one member of Megh’s family
The Arka runtime is Megh’s data streaming framework. Arka enables applications to build custom data pipelines spanning multiple devices and accelerators. Low-level details are abstracted away by Arka’s resource manager, which maps an application’s pipeline request to the pool of available hardware. This technology enables low-latency, low-overhead data streaming over complex functional topologies through Arka’s
Video analytics use cases Enterprise users are increasingly interested in implementing complex video analytics use cases that provide business value beyond typical applications. These involve multi-stage models for object detection and image classification with custom trained models that are integrated to solve business problems. Some examples include: Segment Use case Deep learning tasks Retail Cashier-less
This post is a follow-up to “Implementing a CPU-based real-time video analytics pipeline,” where we discussed a CPU-based end-to-end video analytics pipeline. As seen in that post, a CPU-based pipeline runs into severe performance bottlenecks. Here we discuss how we address and overcome these bottlenecks using FPGAs as hardware accelerators. We explain Megh’s Video Analytics
With growth in available data and computation power, use of video analytics solutions has been growing visibly. Most real-time video analytics use-cases, however, require response times in milliseconds—a level of performance that both CPUs and GPUs cannot always meet when it comes to inference. Here we discuss implementation of a real-time video analytics pipeline on
With the current information age defining the third wave, we are facing an explosion of real-time data, which is in turn increasing demand for real-time analytics. A real-time analytics solution pipeline typically utilizes a streaming library and an analytics platform. Apache Spark is an open-source, distributed computing platform designed to run analytics payloads on a