Plainsight FilterBox

FilterBox — the foundation for vision AI apps — is easy, fast, accurate, & secure. Inspired by the success of containers in the DevOps and Cloud-native communities, Filters aren’t merely deployed models, but complete visual applications and FilterBox is their dedicated Runtime Engine.

Supply Chain Security

FilterBox provides a software bill of materials (SBOM) and the open-source components are sourced from Chainguard, ensuring a secure image you can trust.

Command Line Interface (CLI)

Developer-friendly CLI makes it easy to automate deployment, configuration, and updates using widely available tools of your choice.

Easily managed and controlled by IT

No machine learning or data science expertise required; basic familiarity with Kubernetes, Helm, and MQTT is all that’s needed.

Runs Filters from the FilterRepo

Choose from a library of pre-built Vision Intelligence Filters designed to solve business problems by automating data collection, alerting, and robotic automation of tasks. New filters are available all the time, so if you don’t see the filter you need, just ask.

Video feed to Spreadsheet / Data Stream Pipeline

FilterBox makes it easy to connect to cameras or video streams over USB or network, and output usable data using industry-standard MQTT data. You can easily push this data to a Snowflake, an AWS S3 bucket, Google BigQuery, or a database or datalake of your choice for further analytics.

Private Filters in Customer Filter Repositories

Customers of Plainsight can access commercially licensed filters including variations for different AI models, hardware, cloud, or configuration.

Containerized Runtime

A containerized RTE for Filters allows computer vision applications and AI models to be bundled and deployed using Docker, Kubernetes, Helm, and k3s (Kubernetes for Edge Computing)

Applying DevOps Best Practices to Video Intelligence at the Edge

FilterBox is based on Kubernetes, a cloud native computing paradigm, utilizing a low resource variant called K3S that is efficient at the edge.  Users manage their own instance, maintain full control, and aren’t exposed to typical SaaS patterns of data being shared with a third party.

Try FilterBox with Demo Filters

Play the arcade classic Pong with the Plainsight Technologies mascot Seymour! This Filter showcases Key Point mapping in real time onto hand images to control the Pong paddles

Demo: Object Detection

Detects 80 common items like people, cars, and elephants, and tracks them as they move. It demonstrates the kind of data feed that outputs to a MQTT broker that businesses ingest to take action as well as how easy it is to identify and remove image components from a video stream.

Let’s Talk