Skip to main content

MitySOM Demos

People Tracking Demo

This demo utilizes the YOLOX-S-Lite machine learning model for real-time vision-based people tracking with statistical insights such as total visitors, current occupancy, and visit duration. It also offers heatmap: highlighting frequently visited areas.

Featured Hardware: MitySOM-AM62A System on Module powering Critical Link’s Edge AI Camera

Example Applications: Retail, Building Automation, Safety/Security

Contact info@criticallink.com for more information

Object Recognition AI Demo (Agilex)

Critical Link has implemented the Altera FPGA AI Suite on our Agilex 5 system on modules. The demo utilizes the YOLOv8 model with COCO dataset for object recognition and pose estimation. It runs up to 8K, 60Hz. Critical Link’s off-the-shelf hardware supports up to 8 MIPI cameras. The on-board Agilex 5 FPGA can support up to 24 cameras in custom applications.

Featured Hardware: Each of Critical Link’s Agilex-based solutions can run this demo: MitySOM-A5E StandardMitySOM-A5E Mini, and MitySBC-A5E

Example Applications: Retail Automation, Quality Control, Smart Agriculture, Medical Imaging, Smart City

Contact info@criticallink.com for more information

Facial Recognition Demo

Critical Link’s Qualcomm Dragonwing QCS6490-based SOM is performing facial recognition with Qualcomm’s proprietary Lightweight Face Detection model. The system can be trained to recognize and remember specific faces.

Featured Hardware: MitySOM-QC6490 Development Kit and MitySOM-QC6490 System on Module

Example Applications: Security/Authentication, Retail, Building Automation, Smart City

Contact info@criticallink.com for more information

Mono Depth Estimation Demo

This demo performs single camera (monocular) depth estimation with Qualcomm’s implementation of the MiDaS V2 Deep Convolutional Neural Network model. Images are collected from a single camera, and the neural network runs on the QCS6490 processor, featuring AI hardware acceleration, to create a relative depth map. This depth map is visualized as a heat map, such that red pixels correspond to shorter distances and blue to longer distances.

Featured Hardware: MitySOM-QC6490 Development Kit and MitySOM-QC6490 System on Module

Example Applications: Robotics, Surveillance, Safety/Security

Contact info@criticallink.com for more information

Object Classification Demo (Qualcomm)

This demo utilizes the YOLO-X model to perform Real‑Time object detection and classification optimized for mobile and edge. The 6th Gen Qualcomm AI Engine packs the Qualcomm® QCS6490 Hexagon™ Processor with fused AI tensor and scalar accelerators.

Featured Hardware: MitySOM-QC6490 Development Kit and MitySOM-QC6490 System on Module

Example Applications: Retail Automation, Quality Control, Smart Agriculture, Medical Imaging, Smart City

Contact info@criticallink.com for more information

Multi-Camera Demo (Qualcomm)

This demo shows integration of 3 discrete OV9281 cameras connected via MIPI CSI interfaces using Critical Link’s QCS6490-based System on Module and development board. Each camera is 1280×720, monochrome, operating at 30fps.

Featured Hardware: MitySOM-QC6490 Development Kit and MitySOM-QC6490 System on Module

Example Applications: Medical Imaging, Security/Surveillance, Surround View, Cabin Recorder

Contact info@criticallink.com for more information

Use our SOM Selector Product Quote Engineering Support Inquiry General Contact Email Us