Antal Person Pixelizer

Pixelate people in live video with an editable computer-vision project

Website

Meet Antal Person Pixelizer

Antal Person Pixelizer is a source-code project that detects and pixelates people in camera images. It uses C++ with OpenCV and a neural-network segmentation model to identify human regions, then obscures those regions in a live video stream. Developers can adjust the pixelation strength in the code.

The download includes source files, a pretrained segmentation model, a precompiled OpenCV WebAssembly module, and build instructions. Emscripten support lets the project run within a browser, and an online demonstration shows the approach. It is intended for developers and learners exploring video anonymization or integrating human pixelation into an application. Detection performance depends on conditions such as the subject's distance.

Discussion

Tried it? Share a useful thought or ask a question.

Product details

Website
antal.ai
Status
Launched
Listed

Explore related topics