BittWare Partner Solution
Intelligent Video Analytics Solution
VAS Suite from Megh Computing is an intelligent video analytics solution for security and system integrators who need actionable insights with enterprise class performance, while managing TCO considerations.
With Megh’s Concierge Support to help you get started with development, VAS Suite makes it easy to transition to AI-driven business operations. VAS Suite runs on BittWare cards with Intel Stratix 10 FPGAs with plans to support Intel Agilex FPGAs.
Real Time Analytics
1 to 100
Edge-to-Cloud deployment options
Review live and stored events
- Real-time view across all sites and camera streams
- Review multiple events together in the timeline
Adjust settings for highest accuracy
- AI sensitivity controls
- Inclusion/exclusion zones
Rules and notifications
- Easy and powerful logic-based alerts
- Trigger email or SMS notifications
- Ability to limit notifications based on frequency and number of detections
Deployment and integration options
- Standalone or integrated with VMS systems
- Edge appliance or cloud application
- Diagnostic view for detailed analysis
- Advanced AI pipeline configuration settings
Performance numbers for the most common models running on Intel Stratix 10 compared to NVIDIA’s V100 GPUs
NVMe Bridge Platform IP Core Facts
Provided with Core
- Documentation: comprehensive user documentation
- Design file formats: Encrypted Verilog
- Constraints files: Provided per FPGA
- Verification: ModelSim verification model
- Instantiation templates: Verilog (VHDL wrappers available)
- Reference designs and application notes: Synthesis and place and route scripts
- Additional items: Reference design
Simulation tool used:
QuestaSim (contact IntelliProp for latest versions supported)
Phone and email support will be provided for fully licensed cores for a period of 6 months from the delivery date.
Other simulators are available. Please contact IntelliProp for more information.
View a demo of Arkville 17.05 performance plots.
Data Sheet and Product Details
Enable real-time analytics at the edge, on premises, or private or public cloud.
- Loiter detection
- Intrusion detection
- People counting
- Inventory tracking
- PPE compliance
- Collision detection
- People management
- Traffic management
- Anomaly detection
High performance DL inferencing on FPGAs for
- Takeoff and landing
The Inferencing stage is the most critical stage of the pipeline implementing the deep learning models for object detection and image classification. Megh’s DLE (Deep Learning Engine) running on FPGAs delivers the best performance for many of the models used for IVA. The high throughput achieved with FPGAs delivers the lowest cost per stream for many of the IVA use cases.
- Customize the AI / Video Analytics pipeline for any camera view
- Optimize for accuracy, TCO, or performance based on use case
- Edge-to-Cloud deployment options for performance, cost, and regulatory adherence
- Start with CPU and scale to GPU / FPGA as needed
- Scale from 1 to 100 cameras per system
- Link multiple systems and manage in VAS Suite dashboard
Easy AI Adoption
- Concierge Support for onboarding, support, or customization assistance
- Right-size hardware (not over or under-spec’d)
- Pre-tested requirements mean no surprises once deployed in the field
- Add software licenses as needed, per channel
Enables Operational Reliability
- Intelligent video analytics that actually delivers in complex environments and use cases
- Provides the accuracy and real-time performance to fully-transition to AI-driven business
Interested in Pricing or More Information?
Our technical sales team is ready to provide availability and configuration information, or answer your technical questions.