Brinq is a comprehensive, vision-based approach to intelligent public safety. It combines powerful vision algorithms with state-of-the-art inference to detect, identify, track and characterize.
Brinq delivers real-time situational awareness by transforming live video into notifications and actions that matter. It works at the edge without requiring raw video to be streamed externally to a third-party service.
Brinq uses a microservices architecture that makes it possible to modify and deploy vision pipelines easily. Pipelines can span across heterogeneous compute platforms including CPUs, GPUs, NPUs and even cloud, providing scalability for heavy workloads and future-proofing edge investment.
State-of-the-art inference is only the start of intelligence.
People or vehicles are not always where they should be. Whether it’s a person at subway track-level or a vehicle driving on a pedestrian path, the sooner you detect it, the faster you can respond.
The movement of people helps to provide operational analytics to determine capacity compliance, over-crowding or even prolonged occupancy of a single changeroom.
From fare evasion on public transportation to compliance with workplace physical distancing protocols. Proximity detection tools help identify when people are too close for comfort.
Did a fire alarm go off or a game get out? Crowds give us insights into events and congestion while flow can identify wrong-way travellers, like a person or vehicle trying to enter using an exit.
It’s not always about mass surveillance. Our facial recognition solutions are used in applications on commercial vehicles to make sure the right operator is in the right vehicle at the right time.
Our characterization, identification and reidentification tools allow you to track or match by natural language description or by image. Easily create active watch lists or search archival data.
Detecting unusual behaviour is a precursor to avoiding a more serious issue. Detect and classify when behaviour seems abnormal, threatening, suspicious or requires additional attention.
Whether a distracted person forgot their luggage or a perpetrator tries to steal a delivery from your doorstep understanding objects and ownership gives us the insights we need to identify threats.
Motion tracking gives us insights into the movement and duration of people or objects in the field of view. While appearance tracking helps identify the same person or object again at a different time or place.
Live and playback video modes, real-time notifications, time-series database all within a comprehensive UX designed in consultation with law enforcement, transportation and security professionals.
Arcturus offers scalable, modular edge AI hardware using processors from NXP and NVIDIA with accelerated runtime support for TensorFlow Lite, TensorRT and Arm NN.
Atlas is a scalable edge inference platform that uses NPUs and GPUs to support up to 23.3 TOPs of ML acceleration. The platform uses SoCs from NXP and NVIDIA with up to 10x Arm v8 CPU cores, 16GB of SDRAM and up to 1TB of on-board storage. Brinq Edge AI and Vision analytics platform software is available for real-time analysis, SDK level access, component enablement and full-stack solutions.
Learn more about how Brinq can help you.
Whether you want to do-it-yourself or have a project that needs access to our specialized resources, Arcturus offers low-cost development kits or tailored engagements to help you get moving quickly.
Talk to us,
we don’t bite
