Kepler Vision Technologies B.v.

Qualcomm Technologies, Inc.

Henricus Meinardus Gerardus Stokman

Marc Jean Baptist Van Oldenborgh

Ran Tao

Fares Alnajar

Cornelis Gerardus Maria Snoek

Cees Snoek

A method for identifying a scene, comprising a computing device receiving a plurality of data points corresponding to a scene; the computing device determining one or more subsets of data points from the plurality of data points that are indicative of at least one sub-scene in said scene, said at least one sub-scene displayed on a display device that is part of said scene, wherein said at least one sub-scene does not represent said scene; the computing device categorizing said scene, disregarding said at least one sub-scene, wherein the categorizing includes interpreting said scene by a computer vision system such that said at least one sub-scene is not taken into account in the categorizing of said scene.

Method for categorizing a scene comprising a sub-scene with machine learning

A device configured to transcribe an appearance of a human being, including a common housing holding an image capturing sensor, a computing device having a data processor, and a computer program product including a first machine learning model trained for detecting and labeling human beings, a second machine learning model trained for detecting appearances of human beings and a transcription module to transcribe the detected appearances of human beings to text.

Medical device for transcription of appearances in an image to text with machine learning

The invention provides a system configured to adjust a data rate of an image capturing device. The system comprises a computing device comprising a data processor, and a computer program product comprising a computer vision system for categorizing living beings having a pose that appear in a live video stream. The computer program product, when running on the data processor, receives a live video stream from the image capturing device at a first data rate, where the live video stream comprises a time slice with at least one frame comprising a living being having a pose; applies the computer vision system to the time slice for categorizing the living being, resulting in a category; and signals the image capturing device to set the live video stream at a second data rate, different from the first data rate and based upon the category.

Method for adapting the quality and/or frame rate of a live video stream based upon pose

There is provided a system configured to trigger system configured to trigger a function, said system comprising:

System to notify a request for help by detecting an intent to press a button, said system using artificial intelligence

A body language system for determining a body language message of a living being in a context comprising an artificial intelligence system, said AI system running a computer program that: retrieves an image of said living being showing body language; labels said living being in said image, resulting in a labeled living being; determines said context from said image using a trained machine learning model; determines a baseline body language of said labeled living being from said image using a trained machine learning model; adapts a trained machine learning model of said AI system using said baseline body language and said context; applies the adapted trained machine learning model of said AI system to the one image for categorizing said body language resulting in a category, and applying said category for determining said body language message.

Monitoring and analyzing body language with machine learning, using artificial intelligence systems for improving interaction between humans, and humans and robots

There is provided a device configured to transcribe an appearance of a human being, said device comprising a common housing holding an image capturing sensor, a computing device comprising a data processor, and a computer program product comprising a first machine learning model trained for detecting and labeling human beings, a second machine learning model trained for detecting appearances of human beings and a transcription module to transcribe the detected appearances of human beings to text.

An artificial intelligence (AI) system for determining to which social group a person belongs. The AI system includes a computer system and a computer program product which, when running on the computer system, is to: retrieve at least one image of the person belonging to a social group; labels the person, resulting in a labeled person; retrieve at least one image part showing appearance of the labeled person; subject said at least one image part to at least one trained machine learning model defined in the computer program product, the machine learning model including at least a part that is trained on a test set of annotated images which are annotated with respect to categories that correlate to social group, and determine from the at least one trained machine learning model a social group category to which the labeled person belongs.

Determining a social group to which customers belong from appearance and using artificial intelligence, machine learning, and computer vision, for estimating customer preferences and intent, and for improving customer services

There is provided a method for identifying an action in a scene, comprising: a computing device receiving a plurality of data points corresponding to a scene; the computing device determining one or more subsets of data points from the plurality of data points, wherein said one or more subsets of data points are indicative of at least one sub-scenes in said scene, said sub-scene displayed on a display device; the computing device categorizing said action in said scene, disregarding said a least one sub-scene.

Digital image processing is described that enables live prevention of recording and/or displaying of unwanted images. A device for processing a time sequence of images is provided. The device is configured to: retrieve an image of the time sequence of images from a memory; perform scene recognition on the retrieved image; and perform an action on the retrieved image, based upon the result of the scene recognition, before the images of the time sequence of images are recorded, displayed, and/or stored. The retrieval of the image, the performance of the scene recognition, and the performance of the action can be performed in real-time. The action can include at least one of adapting at least a part of retrieved image, modifying the retrieved image, preventing storage of the retrieved image, preventing a display of the retrieved image, erasing the retrieved image, or encrypting the retrieved image.

Growing community of inventors

Amsterdam, Netherlands

Henricus Meinardus Gerardus Stokman