SlideShare a Scribd company logo
Deploy Your Embedded
Vision Solution on Any
Processor Using Edge
Impulse
Amir Sherman
Senior Director Global Business
Development Semiconductors & Eco
Partners
Edge Impulse
From cloud AI to edge AI/ML to endpoint AI
2
© 2023 Edge Impulse
Cameras are everywhere
3
© 2023 Edge Impulse
What is the “best/right” technology ?
4
© 2023 Edge Impulse
But it is all so complex!
5
© 2023 Edge Impulse
The leading embedded ML platform for any
technology – Edge Impulse
6
© 2023 Edge Impulse
Typical development of EdgeML applications
7
© 2023 Edge Impulse
Requires 20+ man years, expertise in ML and embedded to
build the infrastructure and integrate dozens of different tools.
Develop EdgeML applications with Edge Impulse
8
© 2023 Edge Impulse
An end-to-end platform for projects using any data or device,
built for developers with MLOps infrastructure built-in.
Some of the semiconductors & IP’s we support
9
© 2023 Edge Impulse
How it looks ?
10
BYOM-Bring Your Own Model
11
© 2023 Edge Impulse
12
© 2023 Edge Impulse
Technology Examples
13
© 2023 Edge Impulse
14
© 2023 Edge Impulse
AI/ML capabilities of the EFR32MG24 with MVP
Bringing machine learning (ML) to IoT
applications reduces bandwidth
requirements, saves power, and increases a
device’s ability to make smarter decisions.
Silicon Labs supports machine learning in all
Series 1 and Series 2 wireless SoCs
including newly released BG24 and MG24
products with built-in AI/ML hardware
accelerator.
The MVP accelerator is a co-processor
designed to perform matrix and vector
operations. Using hardware accelerated
kernel implementations will reduce neural
network inference time, as well as off-load
the main processor to allow it to perform
other tasks or go to sleep.
14
© 2023 Edge Impulse
AI/ML capabilities of the EFR32MG24 with MVP
Bringing machine learning (ML) to IoT
applications reduces bandwidth
requirements, saves power, and increases a
device’s ability to make smarter decisions.
Silicon Labs supports machine learning in all
Series 1 and Series 2 wireless SoCs
including newly released BG24 and MG24
products with built-in AI/ML hardware
accelerator.
The MVP accelerator is a co-processor
designed to perform matrix and vector
operations. Using hardware accelerated
kernel implementations will reduce neural
network inference time, as well as off-load
the main processor to allow it to perform
other tasks or go to sleep.
14
© 2023 Edge Impulse
AI/ML capabilities of the EFR32MG24 with MVP
For this project, we attached an Arducam
mini 2MP plus to the xG24 Dev Kit in order
to capture low-res images of people flow
from a real environment.
17
© 2023 Edge Impulse
AI/ML capabilities of the EFR32MG24 with MVP
For this project, we attached an Arducam
mini 2MP plus to the xG24 Dev Kit in order
to capture low-res images of people flow
from a real environment.
18
© 2023 Edge Impulse
ARM’s latest CortexM55 & microNPU Ethos-U55
16
© 2023 Edge Impulse
ARM’s latest CortexM55 & microNPU Ethos-U55
16
© 2023 Edge Impulse
ARM’s latest CortexM55 & microNPU Ethos-U55
16
© 2023 Edge Impulse
Official support for the Alif’s Ensemble family
22
© 2023 Edge Impulse
Astounding AI/ML performance benchmark
23
© 2023 Edge Impulse
24
© 2023 Edge Impulse
Offical support for Renesas RZ/V2L
2 x CortexA55 and DRP-AI ML accelerator
20
© 2023 Edge Impulse
Offical support for Renesas RZ/V2L
2 x CortexA55 and DRP-AI ML accelerator
20
© 2023 Edge Impulse
27
© 2023 Edge Impulse
TDA4VM multi-core embedded vision processor
28
© 2023 Edge Impulse
Industrial edge compute based on NVIDIA
29
© 2023 Edge Impulse
And so many other cores are supported
24
© 2023 Edge Impulse
And so many other cores are supported
24
© 2023 Edge Impulse
And so many other cores are supported
25
© 2023 Edge Impulse
And so many other cores are supported
25
© 2023 Edge Impulse
And so many other cores are supported
25
© 2023 Edge Impulse
Our business model
© 2023 Edge Impulse 35
A platform that goes from data to algorithms
© 2023 Edge Impulse 36
37
© 2023 Edge Impulse
Amir Sherman
Senior Global Director, Semiconductor @ Ecosystem Business Development
+972-52-2240811
+49-173-3232288
amir@edgeimpulse.com
www.edgeimpulse.com

More Related Content

PDF
“Toward the Era of AI Everywhere,” a Presentation from DEEPX
PDF
Deep Learning Neural Network Acceleration at the Edge - Andrea Gallo
PPTX
Supermicro AI Pod that’s Super Simple, Super Scalable, and Super Affordable
PDF
Deploy and Manage Your Industrial IoT Edge Solutions In Weeks With EdgeOps
PDF
“How to Right-size and Future-proof a Container-first Edge AI Infrastructure,...
PDF
Marv Wexler - Transform Your with AI.pdf
PDF
“Software-Defined Cameras for Edge Computing of the Future,” a Presentation f...
DOCX
embedded systems
“Toward the Era of AI Everywhere,” a Presentation from DEEPX
Deep Learning Neural Network Acceleration at the Edge - Andrea Gallo
Supermicro AI Pod that’s Super Simple, Super Scalable, and Super Affordable
Deploy and Manage Your Industrial IoT Edge Solutions In Weeks With EdgeOps
“How to Right-size and Future-proof a Container-first Edge AI Infrastructure,...
Marv Wexler - Transform Your with AI.pdf
“Software-Defined Cameras for Edge Computing of the Future,” a Presentation f...
embedded systems

Similar to “Deploy Your Embedded Vision Solution on Any Processor Using Edge Impulse,” A Presentation from Edge Impulse (20)

PDF
Каталог продукции Matrox Imaging
PDF
Microcontrollers for Artificial Intelligence and Machine Learning
PDF
“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...
PDF
01 AAA SoC Prototyping Oct2024P - Future of AI.pdf
PDF
“A Re-imagination of Embedded Vision System Design,” a Presentation from Imag...
PDF
“Solving Tomorrow’s AI Problems Today with Cadence’s Newest Processor,” a Pre...
PDF
“The Future of AI is Here Today: Deep Dive into Qualcomm’s On-Device AI Offer...
PPTX
Akraino and Edge Computing
PDF
The future of AI is hybrid
PDF
Leveraging Artificial Intelligence Processing on Edge Devices
 
PDF
“From Enterprise to Makers: Driving Vision AI Innovation at the Extreme Edge,...
PDF
Accelerating Edge Computing Adoption
PDF
“Accelerate Tomorrow’s Models with Lattice FPGAs,” a Presentation from Lattic...
PDF
Are you ready to be edgy? Bringing applications to the edge of the network
PDF
Sa*ple
PDF
“Machine Learning for the Real World: What is Acceptable Accuracy, and How Ca...
PDF
AI for Intelligent Cloud and Intelligent Edge: Discover, Deploy, and Manage w...
PDF
“Streamlining Development of Edge AI Applications,” a Presentation from NVIDIA
PDF
“5G and AI Transforming the Next Generation of Robotics,” a Presentation from...
PDF
Redington Value Journal - May 2018
Каталог продукции Matrox Imaging
Microcontrollers for Artificial Intelligence and Machine Learning
“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...
01 AAA SoC Prototyping Oct2024P - Future of AI.pdf
“A Re-imagination of Embedded Vision System Design,” a Presentation from Imag...
“Solving Tomorrow’s AI Problems Today with Cadence’s Newest Processor,” a Pre...
“The Future of AI is Here Today: Deep Dive into Qualcomm’s On-Device AI Offer...
Akraino and Edge Computing
The future of AI is hybrid
Leveraging Artificial Intelligence Processing on Edge Devices
 
“From Enterprise to Makers: Driving Vision AI Innovation at the Extreme Edge,...
Accelerating Edge Computing Adoption
“Accelerate Tomorrow’s Models with Lattice FPGAs,” a Presentation from Lattic...
Are you ready to be edgy? Bringing applications to the edge of the network
Sa*ple
“Machine Learning for the Real World: What is Acceptable Accuracy, and How Ca...
AI for Intelligent Cloud and Intelligent Edge: Discover, Deploy, and Manage w...
“Streamlining Development of Edge AI Applications,” a Presentation from NVIDIA
“5G and AI Transforming the Next Generation of Robotics,” a Presentation from...
Redington Value Journal - May 2018

More from Edge AI and Vision Alliance (20)

PDF
“An Introduction to the MIPI CSI-2 Image Sensor Standard and Its Latest Advan...
PDF
“Visual Search: Fine-grained Recognition with Embedding Models for the Edge,”...
PDF
“Optimizing Real-time SLAM Performance for Autonomous Robots with GPU Acceler...
PDF
“LLMs and VLMs for Regulatory Compliance, Quality Control and Safety Applicat...
PDF
“Simplifying Portable Computer Vision with OpenVX 2.0,” a Presentation from AMD
PDF
“Quantization Techniques for Efficient Deployment of Large Language Models: A...
PDF
“Introduction to Data Types for AI: Trade-offs and Trends,” a Presentation fr...
PDF
“Introduction to Radar and Its Use for Machine Perception,” a Presentation fr...
PDF
“NPU IP Hardware Shaped Through Software and Use-case Analysis,” a Presentati...
PDF
“Voice Interfaces on a Budget: Building Real-time Speech Recognition on Low-c...
PDF
“Computer Vision at Sea: Automated Fish Tracking for Sustainable Fishing,” a ...
PDF
“Squinting Vision Pipelines: Detecting and Correcting Errors in Vision Models...
PDF
“ONNX and Python to C++: State-of-the-art Graph Compilation,” a Presentation ...
PDF
“Beyond the Demo: Turning Computer Vision Prototypes into Scalable, Cost-effe...
PDF
“Running Accelerated CNNs on Low-power Microcontrollers Using Arm Ethos-U55, ...
PDF
“Scaling i.MX Applications Processors’ Native Edge AI with Discrete AI Accele...
PDF
“MPU+: A Transformative Solution for Next-Gen AI at the Edge,” a Presentation...
PDF
“Evolving Inference Processor Software Stacks to Support LLMs,” a Presentatio...
PDF
“Efficiently Registering Depth and RGB Images,” a Presentation from eInfochips
PDF
“Image Tokenization for Distributed Neural Cascades,” a Presentation from Goo...
“An Introduction to the MIPI CSI-2 Image Sensor Standard and Its Latest Advan...
“Visual Search: Fine-grained Recognition with Embedding Models for the Edge,”...
“Optimizing Real-time SLAM Performance for Autonomous Robots with GPU Acceler...
“LLMs and VLMs for Regulatory Compliance, Quality Control and Safety Applicat...
“Simplifying Portable Computer Vision with OpenVX 2.0,” a Presentation from AMD
“Quantization Techniques for Efficient Deployment of Large Language Models: A...
“Introduction to Data Types for AI: Trade-offs and Trends,” a Presentation fr...
“Introduction to Radar and Its Use for Machine Perception,” a Presentation fr...
“NPU IP Hardware Shaped Through Software and Use-case Analysis,” a Presentati...
“Voice Interfaces on a Budget: Building Real-time Speech Recognition on Low-c...
“Computer Vision at Sea: Automated Fish Tracking for Sustainable Fishing,” a ...
“Squinting Vision Pipelines: Detecting and Correcting Errors in Vision Models...
“ONNX and Python to C++: State-of-the-art Graph Compilation,” a Presentation ...
“Beyond the Demo: Turning Computer Vision Prototypes into Scalable, Cost-effe...
“Running Accelerated CNNs on Low-power Microcontrollers Using Arm Ethos-U55, ...
“Scaling i.MX Applications Processors’ Native Edge AI with Discrete AI Accele...
“MPU+: A Transformative Solution for Next-Gen AI at the Edge,” a Presentation...
“Evolving Inference Processor Software Stacks to Support LLMs,” a Presentatio...
“Efficiently Registering Depth and RGB Images,” a Presentation from eInfochips
“Image Tokenization for Distributed Neural Cascades,” a Presentation from Goo...

Recently uploaded (20)

PDF
Approach and Philosophy of On baking technology
PDF
Empathic Computing: Creating Shared Understanding
PDF
Building Integrated photovoltaic BIPV_UPV.pdf
PPTX
Machine Learning_overview_presentation.pptx
PDF
cuic standard and advanced reporting.pdf
PDF
gpt5_lecture_notes_comprehensive_20250812015547.pdf
PPTX
Big Data Technologies - Introduction.pptx
PDF
NewMind AI Weekly Chronicles - August'25-Week II
PPT
Teaching material agriculture food technology
PDF
Reach Out and Touch Someone: Haptics and Empathic Computing
PDF
Assigned Numbers - 2025 - Bluetooth® Document
PDF
Agricultural_Statistics_at_a_Glance_2022_0.pdf
PDF
Encapsulation_ Review paper, used for researhc scholars
PDF
7 ChatGPT Prompts to Help You Define Your Ideal Customer Profile.pdf
PDF
Diabetes mellitus diagnosis method based random forest with bat algorithm
PPTX
Programs and apps: productivity, graphics, security and other tools
PDF
Dropbox Q2 2025 Financial Results & Investor Presentation
PPTX
Tartificialntelligence_presentation.pptx
PDF
Encapsulation theory and applications.pdf
PDF
Electronic commerce courselecture one. Pdf
Approach and Philosophy of On baking technology
Empathic Computing: Creating Shared Understanding
Building Integrated photovoltaic BIPV_UPV.pdf
Machine Learning_overview_presentation.pptx
cuic standard and advanced reporting.pdf
gpt5_lecture_notes_comprehensive_20250812015547.pdf
Big Data Technologies - Introduction.pptx
NewMind AI Weekly Chronicles - August'25-Week II
Teaching material agriculture food technology
Reach Out and Touch Someone: Haptics and Empathic Computing
Assigned Numbers - 2025 - Bluetooth® Document
Agricultural_Statistics_at_a_Glance_2022_0.pdf
Encapsulation_ Review paper, used for researhc scholars
7 ChatGPT Prompts to Help You Define Your Ideal Customer Profile.pdf
Diabetes mellitus diagnosis method based random forest with bat algorithm
Programs and apps: productivity, graphics, security and other tools
Dropbox Q2 2025 Financial Results & Investor Presentation
Tartificialntelligence_presentation.pptx
Encapsulation theory and applications.pdf
Electronic commerce courselecture one. Pdf

“Deploy Your Embedded Vision Solution on Any Processor Using Edge Impulse,” A Presentation from Edge Impulse

  • 1. Deploy Your Embedded Vision Solution on Any Processor Using Edge Impulse Amir Sherman Senior Director Global Business Development Semiconductors & Eco Partners Edge Impulse
  • 2. From cloud AI to edge AI/ML to endpoint AI 2 © 2023 Edge Impulse
  • 3. Cameras are everywhere 3 © 2023 Edge Impulse
  • 4. What is the “best/right” technology ? 4 © 2023 Edge Impulse
  • 5. But it is all so complex! 5 © 2023 Edge Impulse
  • 6. The leading embedded ML platform for any technology – Edge Impulse 6 © 2023 Edge Impulse
  • 7. Typical development of EdgeML applications 7 © 2023 Edge Impulse Requires 20+ man years, expertise in ML and embedded to build the infrastructure and integrate dozens of different tools.
  • 8. Develop EdgeML applications with Edge Impulse 8 © 2023 Edge Impulse An end-to-end platform for projects using any data or device, built for developers with MLOps infrastructure built-in.
  • 9. Some of the semiconductors & IP’s we support 9 © 2023 Edge Impulse
  • 10. How it looks ? 10
  • 11. BYOM-Bring Your Own Model 11 © 2023 Edge Impulse
  • 12. 12 © 2023 Edge Impulse Technology Examples
  • 13. 13 © 2023 Edge Impulse
  • 14. 14 © 2023 Edge Impulse AI/ML capabilities of the EFR32MG24 with MVP Bringing machine learning (ML) to IoT applications reduces bandwidth requirements, saves power, and increases a device’s ability to make smarter decisions. Silicon Labs supports machine learning in all Series 1 and Series 2 wireless SoCs including newly released BG24 and MG24 products with built-in AI/ML hardware accelerator. The MVP accelerator is a co-processor designed to perform matrix and vector operations. Using hardware accelerated kernel implementations will reduce neural network inference time, as well as off-load the main processor to allow it to perform other tasks or go to sleep.
  • 15. 14 © 2023 Edge Impulse AI/ML capabilities of the EFR32MG24 with MVP Bringing machine learning (ML) to IoT applications reduces bandwidth requirements, saves power, and increases a device’s ability to make smarter decisions. Silicon Labs supports machine learning in all Series 1 and Series 2 wireless SoCs including newly released BG24 and MG24 products with built-in AI/ML hardware accelerator. The MVP accelerator is a co-processor designed to perform matrix and vector operations. Using hardware accelerated kernel implementations will reduce neural network inference time, as well as off-load the main processor to allow it to perform other tasks or go to sleep.
  • 16. 14 © 2023 Edge Impulse AI/ML capabilities of the EFR32MG24 with MVP For this project, we attached an Arducam mini 2MP plus to the xG24 Dev Kit in order to capture low-res images of people flow from a real environment.
  • 17. 17 © 2023 Edge Impulse AI/ML capabilities of the EFR32MG24 with MVP For this project, we attached an Arducam mini 2MP plus to the xG24 Dev Kit in order to capture low-res images of people flow from a real environment.
  • 18. 18 © 2023 Edge Impulse
  • 19. ARM’s latest CortexM55 & microNPU Ethos-U55 16 © 2023 Edge Impulse
  • 20. ARM’s latest CortexM55 & microNPU Ethos-U55 16 © 2023 Edge Impulse
  • 21. ARM’s latest CortexM55 & microNPU Ethos-U55 16 © 2023 Edge Impulse
  • 22. Official support for the Alif’s Ensemble family 22 © 2023 Edge Impulse
  • 23. Astounding AI/ML performance benchmark 23 © 2023 Edge Impulse
  • 24. 24 © 2023 Edge Impulse
  • 25. Offical support for Renesas RZ/V2L 2 x CortexA55 and DRP-AI ML accelerator 20 © 2023 Edge Impulse
  • 26. Offical support for Renesas RZ/V2L 2 x CortexA55 and DRP-AI ML accelerator 20 © 2023 Edge Impulse
  • 27. 27 © 2023 Edge Impulse
  • 28. TDA4VM multi-core embedded vision processor 28 © 2023 Edge Impulse
  • 29. Industrial edge compute based on NVIDIA 29 © 2023 Edge Impulse
  • 30. And so many other cores are supported 24 © 2023 Edge Impulse
  • 31. And so many other cores are supported 24 © 2023 Edge Impulse
  • 32. And so many other cores are supported 25 © 2023 Edge Impulse
  • 33. And so many other cores are supported 25 © 2023 Edge Impulse
  • 34. And so many other cores are supported 25 © 2023 Edge Impulse
  • 35. Our business model © 2023 Edge Impulse 35
  • 36. A platform that goes from data to algorithms © 2023 Edge Impulse 36
  • 37. 37 © 2023 Edge Impulse Amir Sherman Senior Global Director, Semiconductor @ Ecosystem Business Development +972-52-2240811 +49-173-3232288 amir@edgeimpulse.com www.edgeimpulse.com