US Software Professionals Inc. • Since 2003
Capability Brief
Edge AI & Computer Vision
On-premises computer vision for real-time safety monitoring, zone occupancy intelligence, and automated compliance — without facial recognition, without the cloud.
For government, commercial, healthcare, education, and industrial facilities.
VionOS.ai is USSP's Edge AI platform that transforms existing camera infrastructure into an intelligent safety and operations layer. Using NVIDIA Jetson edge devices and advanced computer vision models, VionOS.ai delivers real-time person detection, zone occupancy analytics, and automated alerts — all processed locally on-premises.
The platform is designed for any facility that needs continuous safety monitoring without the privacy risks of facial recognition or cloud-based surveillance. VionOS.ai works with existing IP camera infrastructure and requires no GPU servers or data center equipment.
All AI inference runs on local NVIDIA Jetson Orin devices. Video frames never leave the facility network. No cloud dependency, no external API calls, no data egress.
No facial recognition. No biometrics. No PII. Anonymous Person Tokens (SHA-256, 4hr TTL) enable spatial tracking without identification of individuals.
Designed from the ground up to comply with the Illinois Biometric Information Privacy Act. No biometric identifiers or biometric information are collected, stored, or transmitted.
Compatible with any IP camera infrastructure via standard RTSP streams. A single Jetson device handles 4-8 camera feeds depending on resolution and analytics complexity.
Step 1 — Camera Feeds: Existing IP cameras send RTSP video streams over the facility's local network to NVIDIA Jetson Orin edge devices.
Step 2 — On-Device AI Inference: Computer vision models (YOLO-based person detection, skeletal pose estimation) process video frames in real time directly on the Jetson hardware. No video is recorded, stored, or transmitted externally.
Step 3 — Anonymous Tracking: Each detected person is assigned an Anonymous Person Token — a SHA-256 hashed identifier with a 4-hour TTL. This enables spatial and temporal tracking (zone transitions, dwell time, counting) without any biometric identification.
Step 4 — Alerts & Analytics: The system generates real-time alerts (staff ratio thresholds, restricted zone intrusions, unattended areas) and populates a web-based dashboard accessible on the facility network with zone occupancy data, event logs, and trend analytics.
VionOS.ai is designed for any facility that needs real-time occupancy monitoring, safety alerts, or operational intelligence — without the privacy risks of facial recognition or cloud-based surveillance.
Youth safety monitoring, staff-to-youth ratio compliance, incident pattern detection, SB1366 alignment, BIPA-compliant monitoring.
Patient wandering alerts, fall risk zone monitoring, staff coverage optimization, visitor flow analytics, capacity planning.
Building occupancy monitoring, restricted zone alerts, emergency evacuation tracking, classroom utilization analytics.
Safety zone compliance, PPE detection areas, forklift zone alerts, loading dock monitoring, occupancy-based HVAC optimization.
Secure facility monitoring, visitor flow management, lobby queue optimization, compliance-ready audit trails.
Crowd density monitoring, queue wait-time estimation, zone capacity alerts, real-time guest flow analytics.
Zero biometric data. VionOS.ai uses skeletal pose estimation and bounding-box tracking — never facial recognition. Each detected person is assigned an Anonymous Person Token (SHA-256 hash, 4-hour TTL) for spatial tracking without identification. No biometric identifiers or biometric information as defined in 740 ILCS 14/10 are ever collected, stored, or transmitted.
Skeletal pose estimation and bounding-box tracking only. No face detection, no face encoding, no face matching.
All processing on local NVIDIA Jetson hardware. No external API calls. No data egress from facility network.
No names, faces, voices, or personally identifiable information. Only anonymous spatial and behavioral data.
No biometric identifiers collected or stored. Operates outside the scope of BIPA consent and retention requirements.
NVIDIA Jetson Orin edge devices. No cloud servers, no SaaS dependency, no third-party data processing.
Timestamped event logs with zone IDs and anonymous token trails. Configurable retention. Ready for compliance audits.
Reach out to discuss your facility and use case
Facility evaluation, camera audit, requirements gathering
On-premises pilot covering 1-2 priority use cases
Performance tuning, stakeholder review, sign-off
Phased rollout to additional facilities and use cases
Pilot Hardware Included: USSP provides temporary edge hardware for the pilot phase at no hardware cost. For scaled deployment, hardware is purchased or leased based on facility requirements. Contact us to discuss the right approach for your organization.
Established January 23, 2003 in Chicago, IL. Two decades delivering technology solutions to government agencies, healthcare organizations, and Fortune 500 enterprises.
Illinois BEP-certified Minority Business Enterprise (MBE) and Women Business Enterprise (WBE). IDOT-certified Disadvantaged Business Enterprise (DBE). Helps agencies meet supplier diversity goals.
Every engagement starts with a focused pilot — USSP provides temporary hardware, deploys 1-2 use cases, and proves value before you commit. Scale at your own pace with phased rollout and ongoing support.
From AI readiness assessment to pilot deployment to full-scale operations — a single partner for the entire Edge AI journey. No need to coordinate multiple vendors.