Powered by OpenFilter, A Universal Abstraction for Computer Vision Workloads

Downloadable AI annotation and model training software. Automated annotation of video, images, audio, medical imaging, satellite imagery and other datasets.
Demo Application: Overlays subject data from DriveID, Clipper, and TextScan on processed license plate frames
Write a images from video streams to disk

Generic vision filter using Hugging Face Transformers for object detection and image classification across video streams
A production-ready OpenFilter component that collects events from filter pipelines and reliably delivers them to a CloudEvents ingestion compatible endpoint.

Segment Anything Model 3 for object detection and segmentation. This filter is a part of Plainsight's HyperLabel™, which enables accelerated/automated annotation, model retraining and deployment promotion.
Automatically detects and blurs faces in video streams.
Detect motion and structural changes, and save video frames that meet specific criteria
Uploads video segments and images to Google Cloud Storage buckets.
Record frame data to files as JSON or CSV. If the output filename ends with '.csv' the output will be CSV, otherwise JSON
Exports data to MQTT, bundled in with OpenFilter
Read a single video file, network stream or webcam until the end
Write a single segmented video file or rtsp stream
Performs frame calibration, shake detection
crops any region of interest (polygon) in a video and creates a new video from it
Show incoming topic image stream on a web server
Read a images from a folder or GCS bucket or S3 bucket
Aggregates metadata into combined results (summing stats ..etc)
Label images using ChatGPT. This filter is a part of Plainsight's HyperLabel™, which enables accelerated/automated annotation, model retraining and deployment promotion.
Provide REST endpoint(s) and send incoming JSON data on down the filter pipeline