Video Anonymization

Protect Privacy and Monetize Data

VIDEO ANONYMIZATION

Protect Privacy and Monetize Data

Protect Identities with Anonymization

Gyrus utilizing the most advanced computer vision and deep-learning techniques has built different levels of proprietary video anonymization algorithms to protect the privacy and extract the required information for video analytics. It's an accurate, easy-to-use, and effective way to mask, blur or replace sensitive information with synthetic characters.

SOLUTIONS
Automated Video Anonymization

Gyrus offers 3 different levels of anonymization and they are

Mask out faces
Blur Faces with Intelligent Filters
Replace Faces with Synthetic Characters

In the first two levels, the model auto-detects the objects of the selected type and masks out or blurs the faces of specified objects. The Face replacement with synthetic character is an enhanced version of video anonymization model used to superimpose the specified object in the source video with a synthetic character or 3D model to protect sensitive information and analyse human behaviour. It replaces facial features and other Personally Identifiable Information with computer-generated face & data to ensure immediate privacy compliance. The PII free videos can be used freely for storing, training, inference, sharing, etc. The video anonymization models can be deployed on-premises or in the cloud. The AI models can also be customized and ported to various end devices.

Original
Mask
Blur
Synthetic Characters

How It Works

Video Anonymization Workflow

Gyrus Video Anonymization Model empowers the companies to use & monetize the video data in compliant with the Privacy regulations. The Video Anonymization Model auto-detects the objects of the selected type in the incoming video file and masks out or blurs the faces of specified objects as per customer requirements.

In Anonymization with Synthetic Character replacement, the people in the camera feed are classified by various demographics such as Age, Gender, Ethnicity, height/weight/face shape, and a specific replacement synthetic character is chosen. In output video, faces are replaced with the AI-generated, photorealistic faces of non-existent people. The anonymized faces retain a natural complexion and preserve key non-identifying attributes of the original face including age, gender, expression, gaze direction, and more, allowing for analysis while adhering to privacy laws and regulations. This technique is far superior to legacy solutions that rely on blurring or pixelation. The replaced video stream can be freely used for post-processing such as gaze detection, emotion detection, dwell times, etc. and ensure immediate privacy compliance.