Sandisk Technologies Inc.

Meta Platforms Technologies, LLC

Shaomin Xiong

Toshiki Hirano

Lidu Huang

Fei Liu

Yizhi Xiong

Dongmin Yang

Michael Andrew Brookmire

Zhaochun Yu

One embodiment of the present invention sets forth a technique for intelligently accessing one or more different hardware-based mechanisms for cropping out, blurring or blocking private content in a live preview image generated for the camera and in media recorded by the camera. The technique incudes receiving input regarding a plurality of objects to be concealed in media captured by an imaging device and identifying at least one of the plurality of objects in a field of view of the imaging device. Further, the technique includes modifying the at least one of the plurality of objects in a live preview image or media captured by the imaging device using one or more hardware-based actuators, where the modifying the at least one of the plurality of objects causes the one of the plurality of objects to be concealed.

Hardware-based protection of private content captured by a camera device

Systems, methods, and data storage devices for improved classifier training using a video object tracker to determine video data samples are described. A group classifier may be trained using machine learning to classify image objects, based on a set of machine learning parameters, and assign them a group identifier. A retraining data set may be determined based on video data that was assigned that group identifier based on an object tracker. The group classifier may be retrained using the retraining data set to determine an updated set of machine learning parameters and the group classifier may be updated with those parameters.

Group classifier training using video object tracker

Systems, methods, and data storage devices using a video group classifier based on an object tracker are described. A group classifier may be trained using machine learning to classify image objects from a video frame and assign a classifier identifier. An object tracker and the group classifier may be used to determine correspondence between tracker identifiers and classifier identifiers for assigning group identifiers. The object tracker may then be used to determine image objects, assign tracker identifiers, and track the movement of those image objects through a video data stream to associate tracker identifiers with the video frames. The tracker identifier may be used to assign a group identifier to each video frame based the correspondence between the tracker identifier and the classifier identifier.

Video group classification using object tracker

Systems, methods, and data storage devices for image grouping in an end user device using trained machine learning group classifiers are described. The end user device may include an image group classifier configured to classify new image data objects using an image classification algorithm and set of machine learning parameters previously trained for a specific image group. The end user device may determine embeddings that quantify features of the target image object and use those embeddings and the image group classifier to selectively associate group identifiers with each new image data object received or generated by the end user device. Calibration, including selection and training, of the image group classifiers and ranking of classified images are also described.

Growing community of inventors

Newark, CA, United States of America

Shaomin Xiong