Assa Abloy has filed a patent for a method to provide training data for monitoring individuals using machine learning models based on video data. The method involves obtaining a data feed of the person, generating fake video data of a fictive person, combining them, and providing the training data for model training. GlobalData’s report on Assa Abloy gives a 360-degree view of the company including its patenting strategy. Buy the report here.

Smarter leaders trust GlobalData

Report-cover

Premium Insights Assa Abloy AB - Company Profile

Buy the Report

Premium Insights

The gold standard of business intelligence.

Find out more

According to GlobalData’s company profile on Assa Abloy, Intelligent access control was a key innovation area identified from patents. Assa Abloy's grant share as of January 2024 was 56%. Grant share is based on the ratio of number of grants to total number of patents.

Privacy-preserving training data generation for person monitoring machine learning

Source: United States Patent and Trademark Office (USPTO). Credit: Assa Abloy AB

The patent application (Publication Number: US20240028765A1) describes a method for providing training data for a machine learning model used in monitoring individuals based on video data. The method involves obtaining a data feed of the person, generating fake video data of a fictive person with a computer-generated face, combining the real and fake data to create training data, and then using this data to train the machine learning model. The data feed can be captured using privacy-preserving devices like radar or low-resolution infrared cameras to protect the individual's privacy. Additionally, the generation of fake video data is done using a generative adversarial network (GAN) to enhance the training process.

Furthermore, the patent application also includes details about a training data provider equipped with a processor and memory to execute the method described. The training data provider follows the same steps of obtaining real data, generating fake data, combining them, and providing the training data for the machine learning model. The use of privacy-preserving capturing devices and GAN for generating fake data is reiterated in this context. Additionally, a computer-readable storage medium storing a computer program for implementing the method is also mentioned in the claims. Overall, the patent application focuses on a novel approach to training machine learning models for monitoring individuals using a combination of real and fake video data while ensuring privacy protection through the use of specific capturing devices and techniques.

To know more about GlobalData’s detailed insights on Assa Abloy, buy the report here.

Premium Insights

From

The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.

GlobalData

GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.