Video Analytics Solution (VAS)
Overview
Based on our advanced real-time analytics platform, Megh Computing’s Video Analytics Solution (VAS) addresses critical use-cases throughout the retail supply chain.
| Use case | Description | Business value |
| Fraud prevention | Fraud prevention due to miss-scans at self checkout counters | Decrease shrink at POS |
| Inventory intelligence | Decrease inventory distortion due to fraud or misplacement | Reduce inventory loss |
| Smart Surveillance | Enhance access control systems with video surveillance | Create a safe and secure retail environment |
VAS implements the complete video analytics pipeline (consisting of the ingest, transform, and infer phases) inline in the FPGA, resulting in higher performance efficiencies and lower latencies. It delivers 4X better performance/$ compared to GPU-based video analytics solutions.
VAS is supported on the following platforms:
- Servers:
- Dell PowerEdge R740 and R640
- HPE ProLiant DL380 Gen10
- FPGAs:
- Intel Programmable Accelerator Cards with Intel Arria10 and Stratix 10 FPGAs
- Xilinx Alveo U200 and U250 Data Center Accelerator Cards
Release notes
Megh VAS alpha 2 release notes (October 2019).
Share this page
VAS on Xilinx platform
Megh/Xilinx Video Analytics solution brief.
VAS on Intel platform
Megh’s Intel AI: In Production partner page.
In the following video, see how Intel and Megh have partnered in developing low-latency analytics using AI with Intel FPGAs.
The following 11-page Dell-EMC technical white paper evaluates a video analytics pipeline with deep learning inference using Megh’s VAS and Intel Programmable Acceleration Card (PAC) FPGAs on Dell EMC PowerEdge R740/R740xd servers.
Computing on Dell EMC PowerEdge Servers
The following 3-page HPE technical white paper discusses how customers can achieve dramatically increased performance and reduced TCO by running the Megh Computing real-time streaming video analytics platform on the HPE ProLiant DL380 Gen10 server with Intel Arria 10 GX FPGAs compared to a configuration without FPGAs.
Packard Enterprise, Intel, and Megh Computing
Presentation at Spark+AI Summit 2019
Demo video