Vision Algorithms for Embedded Vision
Most computer vision algorithms were developed on general-purpose computer systems with software written in a high-level language
Most computer vision algorithms were developed on general-purpose computer systems with software written in a high-level language. Some of the pixel-processing operations (ex: spatial filtering) have changed very little in the decades since they were first implemented on mainframes. With today’s broader embedded vision implementations, existing high-level algorithms may not fit within the system constraints, requiring new innovation to achieve the desired results.
Some of this innovation may involve replacing a general-purpose algorithm with a hardware-optimized equivalent. With such a broad range of processors for embedded vision, algorithm analysis will likely focus on ways to maximize pixel-level processing within system constraints.
This section refers to both general-purpose operations (ex: edge detection) and hardware-optimized versions (ex: parallel adaptive filtering in an FPGA). Many sources exist for general-purpose algorithms. The Embedded Vision Alliance is one of the best industry resources for learning about algorithms that map to specific hardware, since Alliance Members will share this information directly with the vision community.
General-purpose computer vision algorithms
One of the most-popular sources of computer vision algorithms is the OpenCV Library. OpenCV is open-source and currently written in C, with a C++ version under development. For more information, see the Alliance’s interview with OpenCV Foundation President and CEO Gary Bradski, along with other OpenCV-related materials on the Alliance website.
Hardware-optimized computer vision algorithms
Several programmable device vendors have created optimized versions of off-the-shelf computer vision libraries. NVIDIA works closely with the OpenCV community, for example, and has created algorithms that are accelerated by GPGPUs. MathWorks provides MATLAB functions/objects and Simulink blocks for many computer vision algorithms within its Vision System Toolbox, while also allowing vendors to create their own libraries of functions that are optimized for a specific programmable architecture. National Instruments offers its LabView Vision module library. And Xilinx is another example of a vendor with an optimized computer vision library that it provides to customers as Plug and Play IP cores for creating hardware-accelerated vision algorithms in an FPGA.
Other vision libraries
- Halcon
- Matrox Imaging Library (MIL)
- Cognex VisionPro
- VXL
- CImg
- Filters
“Understand the Multimodal World with Minimal Supervision,” a Keynote Presentation from Yong Jae Lee
Yong Jae Lee, Associate Professor in the Department of Computer Sciences at the University of Wisconsin-Madison and CEO of GivernyAI, presents the “Learning to Understand Our Multimodal World with Minimal Supervision” tutorial at the May 2024 Embedded Vision Summit. The field of computer vision is undergoing another profound change. Recently,… “Understand the Multimodal World with
“Market and Technology Trends in Automotive ADAS,” a Presentation from the Yole Group
Florian Domengie, Senior Technology and Market Analyst at the Yole Group, presents the “Market and Technology Trends in Automotive ADAS” tutorial at the May 2024 Embedded Vision Summit. In this talk, Domengie takes an in-depth look at the rapidly advancing and fast-growing space of driver assistance and autonomous driving. He… “Market and Technology Trends in
“Identifying and Mitigating Bias in AI,” a Presentation from Intel
Nikita Tiwari, AI Enabling Engineer for OEM PC Experiences in the Client Computing Group at Intel, presents the “Identifying and Mitigating Bias in AI” tutorial at the May 2024 Embedded Vision Summit. From autonomous driving to immersive shopping, and from enhanced video collaboration to graphic design, AI is placing a… “Identifying and Mitigating Bias in
“The Fundamentals of Training AI Models for Computer Vision Applications,” a Presentation from GMAC Intelligence
Amit Mate, Founder and CEO of GMAC Intelligence, presents the “Fundamentals of Training AI Models for Computer Vision Applications” tutorial at the May 2024 Embedded Vision Summit. In this presentation, Mate introduces the essential aspects of training convolutional neural networks (CNNs). He discusses the prerequisites for training, including models, data… “The Fundamentals of Training AI
Snapdragon Powers the Future of AI in Smart Glasses. Here’s How
This blog post was originally published at Qualcomm’s website. It is reprinted here with the permission of Qualcomm. A Snapdragon Insider chats with Qualcomm Technologies’ Said Bakadir about the future of smart glasses and Qualcomm Technologies’ role in turning it into a critical AI tool Artificial intelligence (AI) is increasingly winding its way through our
“An Introduction to Semantic Segmentation,” a Presentation from Au-Zone Technologies
Sébastien Taylor, Vice President of Research and Development for Au-Zone Technologies, presents the “Introduction to Semantic Segmentation” tutorial at the May 2024 Embedded Vision Summit. Vision applications often rely on object detectors, which determine the nature and location of objects in a scene. But many vision applications require a different… “An Introduction to Semantic Segmentation,”
Upcoming Webinar Explores How AI Can Make Cameras See In the Dark
On September 10, 2024 at 9:00 am PT (noon ET), Alliance Member companies Ceva and Visionary.ai will deliver the free webinar “Can AI Make Cameras See In the Dark? Real-Time Video Enhancement.” From the event page: As cameras become ubiquitous in applications such as surveillance, mobile, drones, and automotive systems, achieving clear vision 24/7 under
NVIDIA TensorRT Model Optimizer v0.15 Boosts Inference Performance and Expands Model Support
This blog post was originally published at NVIDIA’s website. It is reprinted here with the permission of NVIDIA. NVIDIA has announced the latest v0.15 release of NVIDIA TensorRT Model Optimizer, a state-of-the-art quantization toolkit of model optimization techniques including quantization, sparsity, and pruning. These techniques reduce model complexity and enable downstream inference frameworks like NVIDIA
“DNN Quantization: Theory to Practice,” a Presentation from AMD
Dwith Chenna, Member of the Technical Staff and Product Engineer for AI Inference at AMD, presents the “DNN Quantization: Theory to Practice” tutorial at the May 2024 Embedded Vision Summit. Deep neural networks, widely used in computer vision tasks, require substantial computation and memory resources, making it challenging to run… “DNN Quantization: Theory to Practice,”
“Leveraging Neural Architecture Search for Efficient Computer Vision on the Edge,” a Presentation from NXP Semiconductors
Hiram Rayo Torres Rodriguez, Senior AI Research Engineer at NXP Semiconductors, presents the “Leveraging Neural Architecture Search for Efficient Computer Vision on the Edge” tutorial at the May 2024 Embedded Vision Summit. In most AI research today, deep neural networks (DNNs) are designed solely to improve prediction accuracy, often ignoring… “Leveraging Neural Architecture Search for
“Introduction to Visual Simultaneous Localization and Mapping (VSLAM),” a Presentation from Cadence
Amol Borkar, Product Marketing Director, and Shrinivas Gadkari, Design Engineering Director, both of Cadence, co-present the “Introduction to Visual Simultaneous Localization and Mapping (VSLAM)” tutorial at the May 2024 Embedded Vision Summit. Simultaneous localization and mapping (SLAM) is widely used in industry and has numerous applications where camera or ego-motion… “Introduction to Visual Simultaneous Localization
Scalable Public Safety with On-device AI: How Startup FocusAI is Filling Enterprise Security Market Gaps
This blog post was originally published at Qualcomm’s website. It is reprinted here with the permission of Qualcomm Enterprise security is not just big business, it’s about keeping you safe: Here’s how engineer-turned-CTO Sudhakaran Ram collaborated with us to do just that. Key Takeaways: On-device AI enables superior enterprise-grade security. Distributed computing cost-efficiently enables actionable
EyePop.ai Demonstration of Effortless AI Integration
Andy Ballester, Co-Founder of EyePop.ai, demonstrates the company’s latest edge AI and vision technologies and products at the 2024 Embedded Vision Summit. Specifically, Ballester demonstrates the ease and accessibility of his company’s AI platform. Tailored for startups without machine learning teams, this demo showcases how to create a custom computer vision endpoint that can be
Interactive AI Tool Delivers Immersive Video Content to Blind and Low-vision Viewers
This blog post was originally published at NVIDIA’s website. It is reprinted here with the permission of NVIDIA. New research aims to revolutionize video accessibility for blind or low-vision (BLV) viewers with an AI-powered system that gives users the ability to explore content interactively. The innovative system, detailed in a recent paper, addresses significant gaps
Exploring the Present and Future of AI: Insights from Qualcomm’s AI Analyst and Media Workshop
This blog post was originally published at Qualcomm’s website. It is reprinted here with the permission of Qualcomm A day with Qualcomm revealed the innovations empowering new and exciting AI experiences running within devices In the rapidly evolving world of artificial intelligence (AI), staying ahead of the curve is crucial. As a leader in on-device
Accelerating Transformer Neural Networks for Autonomous Driving
This blog post was originally published at Ambarella’s website. It is reprinted here with the permission of Ambarella. Autonomous driving (AD) and advanced driver assistance system (ADAS) providers are deploying more and more AI neural networks (NNs) to offer human-like driving experience. Several of the leading AD innovators have either deployed, or have a roadmap
