Petanux shows how computer vision can turn ordinary retail cameras into edge-AI sensors for self-checkout, shelf analytics, and shrink control, integrating via API into existing POS and store software so upgrades don’t require a full lane refresh. The core idea is in-camera inference: product recognition on the scale plate, barcode-free item detection, and automated prompts only when confidence drops, with a stated target around 95%+ depending on training. https://petanux.com/
—
HDMI® Technology is the foundation for the worldwide ecosystem of HDMI-connected devices; integrated with displays, set-top boxes, laptops, audio video receivers and other product types. Because of this global usage, manufacturers, resellers, integrators and consumers must be assured that their HDMI® products work seamlessly together and deliver the best possible performance by sourcing products from licensed HDMI Adopters or authorized resellers. For HDMI Cables, consumers can look for the official HDMI® Cable Certification Labels on packaging. Innovation continues with the latest HDMI 2.2 Specification that supports higher 96Gbps bandwidth and next-gen HDMI Fixed Rate Link technology to provide optimal audio and video for a wide range of device applications. Higher resolutions and refresh rates are supported, including up to 12K@120 and 16K@60. Additionally, more high-quality options are supported, including uncompressed full chroma formats such as 8K@60/4:4:4 and 4K@240/4:4:4 at 10-bit and 12-bit color.
—
A key technical theme is keeping processing local for privacy and latency: models are quantized to fit the available compute in the camera (ARM SoC plus GPU/NPU-class acceleration, referenced as up to ~26 TOPS in this demo) so images don’t need to stream to Azure-style cloud inference. That on-device pipeline supports GDPR-minded deployment patterns, reduces WAN dependencies, and makes it easier to run in stores with constrained connectivity or strict data-handling rules today.
Beyond checkout, the demo expands to multi-camera re-identification and zone-to-zone tracking, where a local “broker” service coordinates multiple networked cameras (including light-rail style placements) to follow a shopper journey from departments to the cashier. This enables behavior-aware shrink workflows: instead of confronting mid-aisle, the system can flag suspect actions and validate at checkout, while also producing trajectory heatmaps and dwell-time metrics for merchandising decisions here.
Filmed at ISE 2026 in Barcelona, the conversation links this edge-vision stack with faytech camera hardware and the broader trend toward distributed perception across the store: ceiling, gondola ends, bakery zones, and kiosks. It also sketches opt-in personalization paths—age/gender estimation for signage, habit inference with app consent, and context-driven offers—while emphasizing that compliance hinges on minimization, local processing, and avoiding long-term customer data retention today.
The practical business case is labor and loss: automated out-of-stock detection replaces manual shelf walks, shrink reduction lowers inventory leakage, and analytics help fix “high interest, low purchase” areas by tuning price, placement, or assortment. If edge compute keeps improving, the same deployment can scale from single-lane product detection to store-wide agent-like guidance without turning every store into a cloud video pipeline today.
I’m publishing about 75+ videos from ISE 2026, check out all my ISE 2026 videos in my playlist here: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjUiepj5jbL6aIt6QB9jeCk
This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 )
“Super Thanks” are welcome 😁
Check out my video with Daylight Computer about their revolutionary Sunlight Readable Transflective LCD Display for Healthy Learning: https://www.youtube.com/watch?v=U98RuxkFDYY
