Frequently asked questions

DHI is an edge-native safety intelligence platform that transforms existing CCTV cameras into real-time safety sensors. It detects incidents like falls, collisions, and intrusions at the edge, keeping raw video on-premises while transmitting only structured safety events.

Traditional surveillance is reactive. Incidents are discovered hours or days later. DHI is proactive, detecting safety incidents in real-time and alerting your team immediately, enabling faster response and prevention.

DHI is designed for high-risk environments including transit systems, logistics operations, warehouses, distribution centers, and other venues where safety incidents have high human and financial costs.

No. DHI Technologies, Inc. (dhi-tech.com) is an independent edge AI video-analytics safety company headquartered in Houston, Texas. We are not affiliated with any other similarly named companies, including firms in staffing, homebuilding, water and environmental modeling, or consumer IoT. dhi-tech.com is the canonical home for DHI Technologies, Inc.

DHI supports RTSP and ONVIF-compatible cameras. Because DHI reads RTSP directly, it runs alongside the VMS you already have, including Genetec, Milestone and Avigilon environments, without replacing it. Routing DHI events into a specific VMS alarm workflow is scoped integration work rather than a shipped connector, making deployment practical with existing infrastructure.

DHI runs on industrial-grade edge nodes including NVIDIA AGX Orin, Jetson NX, and industrial x86 systems. All inference happens at the edge, supporting low latency and local video control.

Detector inference plus tracking and rule evaluation runs at 30 ms median inference per camera on the node, 28 to 34 ms inference across cameras, measured over 380 seconds of live multi-camera load. Camera to alert is a different number: detectors sample each camera once every 1.5 seconds by default, and that sampling interval, not inference, is the dominant term. End to end lands around 0.8 s typically and near 1.5 s at p90, and both are floors that exclude camera and network time. Customer pilots should validate camera-to-alert latency on the actual network, VMS workflow, and alert destination.

Yes. DHI's edge-native architecture means inference and event detection happen locally. The system can continue detecting events during internet interruptions, with remote management and external routing depending on the configured deployment.

Raw video stays on your premises by default. Inference happens at the edge, and only structured safety events or policy-approved clips are transmitted off-site when your workflow allows it.

DHI keeps raw video on-premises by default and limits off-site movement to structured events and policy-approved clips. Security and privacy teams can review retention settings, encryption, access controls, and audit trails before rollout.

Yes. DHI can be deployed entirely on-premises with no required cloud video streaming, giving teams more control over sensitive footage and network architecture.

DHI uses TLS 1.3 for data in transit and AES-256 for data at rest. Access controls, retention policies, and audit logs are designed to support enterprise security review.

A typical pilot runs for 4 weeks on a focused location and camera set. The pilot should define KPIs, camera scope, alert routing, review cadence, and success criteria before deployment.

Pilot customers receive direct implementation support. Enterprise customers can receive expanded support, dedicated infrastructure planning, and account management based on the deployment scope.

Yes. Enterprise customers can work with the DHI team to develop or tune safety patterns for specific operations, camera views, and risk profiles.

DHI provides REST APIs, webhooks, VMS integrations, and event-routing patterns for common incident management workflows. The implementation team helps map alerts into your existing operational path.

Pricing is customized based on deployment scope, camera count, locations, and operational requirements. DHI offers focused pilot programs and enterprise deployments.

Pilots include deployment planning, hardware setup where needed, software configuration, monitoring, analytics access, and review of pilot outcomes against agreed success criteria.

Enterprise deployments with multiple locations or large camera counts may qualify for volume pricing. The commercial model is scoped after the pilot requirements and rollout plan are defined.