Amazon Technologies, Inc.

Orbeus, Inc.

Yi Li

Hao Chen

Tianqiang Liu

Meng Wang

Hua Wang

Danny Wei

Kerry Quintin Lee

Mahmood Miah

Nandakumar Gopalakrishnan

Yushan Chen

Yuxin Wu

Anchit Rastogi

Sanket Parikh

Shichang Liu

Ehsan Omidi

Abhay K Gupta

Lalithkumar Rajendran

Kevin K Zhang

Garrick Chow

Austin Bryant

Jun Woo Park

Kevin Zhang

Techniques for controlling operations of a motor based on position errors are described. In an example, a user device sends an amount of electrical current to the motor to cause the motor to move. The user device also determines the motor is in position for a time interval despite the amount of electrical current. Based at least one the time interval and the amount of electrical current, the user device determines a position difference associated with a target position and a measured position of the motor during the time interval, and reduces the amount of electrical current based at least in part on the time interval.

Back-drive of motor based on position data

Images are intelligently selected to create image narratives. Instead of a user having to manually search and locate images to view, the images to associate with a particular image narrative are programmatically determined. Many different types of image narratives may be created. For example, one image narrative may show images that include both a first user and a second user over some period of time. Another image narrative may show images that relate to an activity that a first user enjoys or an event that included the user (e.g., a graduation). The tags and metadata associated with the images of the user are analyzed to determine the tags that are important to the user. For example, the importance might be determined based on the frequency of the tags within the images. After creation, the user may select one of the image narratives to view the associated images.

Intelligent selection of images to create image narratives

Techniques for identifying thermal critical conditions in devices with multiple SoCs, and coordinating the resetting and rebooting of the SoCs to recover from the thermal critical conditions are described herein. A device may include a first SoC that monitors a first temperature sensor, and a second SoC that monitors a second temperature sensor, to determine whether temperatures in the device indicate thermal critical conditions. The second SoC may determine that a temperature determined using the second temperature sensor is above a threshold indicating a thermal critical condition, and may provide an indication to the first SoC that the temperature is above the threshold. The first SoC may detect the indication, and the first SoC and second SoC may each reset to allow the device to cool down. The first SoC and second SoC may then coordinate rebooting once the thermal critical condition is no longer detected in the device.

Identifying critical thermal conditions in multiple system-on-a-chip (SoC) systems

An image processing system for recognizing the scene type of an input image generates an image distance metric from a set of images. The image processing system further extracts image features from the input image and each image in the set of images. Based on the distance metric and the extracted image features, the image processing system computes image feature distances for selecting a subset of images. The image processing system derives a scene type from the scene type of the subset of images. In one embodiment, the image processing system is a cloud computing system.

System, method and apparatus for scene recognition

A method for automatically generating photo albums is performed by a server computer. The server computer retrieves a set of images over the network interface before it retrieves metadata and a first set of tags from each image. The server computer also generates a second set of tags for each image, and stores the sets of tags into a database. The server computer further determines a set of search parameters and retrieves a second set of images from the database. A photo album is then generated from the second set of images.

System and method for automatically generating albums

Methods and systems for detecting error in data storage entities based at least in part on importance of data stored in the data storage entities. In an embodiment, multiple verification passes may be performed on a data storage entity comprising one or more data blocks. Each data block may be associated with a probability indicating the likelihood that the data block is to be selected for verification. During each verification pass, a subset of the data blocks may be selected based at least in part on the probabilities associated with the data blocks. The probabilities may be adjusted, for example, at the end of a verification pass, based on importance factors such as usage and verification information associated with the data blocks. The probabilities may be updated to facilitate timely detection of important data blocks. Additionally, error mitigation and/or correction routines may be performed in light of detected errors.

Importance-based data storage verification

A method for recognizing a face in an image is performed by a facial recognition system. The system retrieves an image and detects a face within the image. The system then determines a set of facial feature positions for a set of facial features. The set of facial feature positions are used to separate the face into a set of facial feature parts. For each part, the system extracts a set of image features. The extracted features are concatenated into a full feature. The system performs dimension reduction on the full feature to derive a final feature. In addition, although narrow claims may be presented below, it should be recognized that the scope of this invention is much broader than presented by the claim(s). It is intended that broader claims will be submitted in one or more applications that claim the benefit of priority from this application. Insofar as the description above and the accompanying drawings disclose additional subject matter that is not within the scope of the claim or claims below, the additional inventions are not dedicated to the public and the right to file one or more applications to claim such additional inventions is reserved.

System, method and apparatus for facial recognition

Growing community of inventors

Mountain View, CA, United States of America

Yi Li