Our Technology Stack

Object Detection using Convolutional Neural Networks

Image and Video Anonymization with Deep Learning

Our core technology is object detection using deep convolutional networks (CNN), which in recent years has rapidly evolved from an academic playground to production-ready tools for solving industrial use cases fast and effectively.

We combine different architectures such as instance segmentation (Mask R-CNN^[1] with a FPN backbone^[2]) and keypoint detection (based on Faster R-CNN^[3]) to anonymize people, vehicles, faces or licence plates.

As part of the NVIDIA Inception program for AI startups, we have access to support, expertise and training by NVIDIA, the leading AI hardware manufacturer.

• [1] He, Kaiming et al. (2018). Mask R-CNN.
• [2] Lin, Tsung-Yi et al. (2017). Feature Pyramid Networks for Object Detection.
• [3] Shaoqing Ren et al. (2016). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.

Cloud, Docker and APIs

Scalable and Flexible Anonymization Pipeline

We have set up our scalable and flexible anonymization pipelines in GDPR-compliant data centres around Europe. Available also as a Docker container, it can be installed on a local machine, private or public cloud infrastructure.

Python

Amazon Web Services

PyTorch

NVIDIA