Videos on Edge AI and Visual Intelligence
We hope that the compelling AI and visual intelligence case studies that follow will both entertain and inspire you, and that you’ll regularly revisit this page as new material is added. For more, monitor the News page, where you’ll frequently find video content embedded within the daily writeups.
Alliance Website Videos
STMicroelectronics’ 3D direct ToF lidar module demo + Human detection application
Experience a live demonstration of the VL53L9CX, STMicroelectronics’ advanced 3D direct ToF lidar module, showcased at Embedded Vision. Delivering up to 2.3k zones and real-time streaming at up to 100 Hz, the system captures highly detailed depth data with strong accuracy from short range up to nearly 9 meters. This all-in-one module integrates SPAD sensing,
Squint Cognition Demonstration of Squint Vision Studio: AI Tooling and Watchdogs for Vision Models
Ken Wenger, Founder and CTO at Squint Cognition, demonstrates Squint Vision Studio, the company’s AI safety and performance tooling for vision-based systems, at the 2026 Embedded Vision Summit. Squint Vision Studio is built for anywhere a confidently wrong perception model is a liability; inventory and loss prevention, industrial, agriculture, defense, aerospace. Costly at best, hazardous
Squint Cognition Demonstration of Catching High-Confidence YOLO Errors in Real Time with Skittles
Ken Wenger, Founder and CTO at Squint Cognition, demonstrates the company’s squinting model technology at the 2026 Embedded Vision Summit. Using Skittles and M&Ms, Wenger shows where a standard YOLO object detection model confuses one candy for the other; and does so with high confidence, offering no signal that anything is wrong. He then runs
BrainChip Demonstration of the Company’s Always-On Radar-Based Edge Classification
Ritik Shrivastava, Solutions Architect at BrainChip, demonstrates Akida micro-doppler radar classification, a powerful radar-based object classification solution that runs entirely on-device without internet connection. Shrivastava showcases a live demo using BrainChip’s AKD1500 card attached to a Raspberry Pi, where the system detects and classifies between a bird and drone target in real time using radar.
BrainChip AKD1500 Edge AI Co-Processor Demo: Ultra-Low Power AI Inference at the Edge
Tharak Krishnan, Director of Product Management at BrainChip, demonstrates the AKD1500 — BrainChip’s ultra-low power Edge AI Co-Processor — at the 2026 Embedded Vision Summit. Already deployed in real-world applications such as epileptic seizure prediction and drowning swimmer detection, the AKD1500 is purpose-built for use cases where power consumption and battery life are critical constraints.
In-Situ Intelligent Mixed Reality Assistants for Adaptive Human-AI Collaboration
This video was originally published at OpenCV’s website. It is republished here with the permission of OpenCV. Our guest is Alireza Taheritajar, a Ph.D. Student an Augusta University focusing on In-Situ Intelligent Mixed Reality Assistants for Adaptive Human-AI Collaboration. Mixed-reality overlays have been around for awhile, but with the recent upgrades in camera quality, lens
Smarter Wildfire Datasets: Pruning Redundancy and Fixing Labels in 3LC
Using 3LC’s visualization dashboard, we can quickly recognize patterns within the wildfire detection dataset and address ground-truth labeling inaccuracies. Firstly, by visualizing how images are distributed in the model’s latent embedding space, we can intelligently remove redundant scenes that are feeding the model duplicate information. Next, by applying filters to key prediction metrics we can
3LC Hub: Data Management and AI Insights for Computer Vision & Physical AI
3LC Hub provides a centralized platform for managing and organizing the datasets that power AI systems. Using advanced data-centric AI algorithms, the platform continuously analyzes your data and surfaces actionable recommendations to identify labeling issues, uncover edge cases, improve data quality, and optimize model performance. Users can seamlessly launch into the appropriate views and workflows
Visionary.ai ISP Powered by NPX6
David Jarmon, Sr. VP of Worldwide Sales at Visionary.ai, and Guy Ben Haim, Sr. Staff Product Manager, discuss Visionary.ai’s advanced AI-powered ISP demo. The solution delivers exceptional video quality with industry-leading low-light and HDR performance, improved detection accuracy, a modular pipeline, and low-power, on-chip deployment—highlighting adaptable, software-defined image processing. Since the filming of this
Custom Vision Accelerator (NVIDIA PVA) Built with ASIP Designer in Action
Viswateja Nemani, Sr. Staff Solutions Architect, showcases NVIDIA’s Programmable Vision Accelerator (PVA), a low-power VLIW/SIMD processor built with ASIP Designer using custom instructions tailored for vision and image workloads. The live demo runs real-time stereo depth on the PVA, illustrating how heterogeneous compute on the Jetson Orin NX lets specialized accelerators handle vision while the
