Samsung Electronics Co., Ltd.

Alexandra Dana

Ran Vitek

Netanel Stein

Nathan Henri Levy

Matthew C Wiggins

Omer Shabtai

Jungmok Bae

Ishay Goldin

Tomer Peleg

Roy Josef Jevnisek

Yotam Platner

David Tsidkiahu

Yaron Ukrainitz

Maor Shutman

Matan Shoef

Zuf Pilosof

Yotam Perlitz

Tal Heller

Alon Intrater

Techniques and apparatuses enabling high accuracy video object detection using reduced system resource requirements (e.g., reduced computational load, shallower neural network designs, etc.) are described. For example, a search domain of an object detection scheme (e.g., a target object class, a target object size, a target object rotation angle, etc.) may be separated into subdomains (e.g., such as subdomains of object classes, subdomains of object sizes, subdomains object rotation angles, etc.). Specialized, subdomain-level object detection/segmentation tasks may then be separated across sequential video frames. As such, different subdomain-level processing techniques (e.g., via specialized neural networks) may be implemented across different frames of a video sequence. Moreover, redundancy information of consecutive video frames may be leveraged, such that specialized object detection tasks combined with visual object tracking across consecutive frames may enable more efficient (e.g., more accurate, less computationally intensive, etc.) full domain object detection and object segmentation schemes.

Fast object detection in video via scale separation

A method for estimating blood pressure using a blood flow occlusion system applied to an artery includes receiving from a first sensor a sensed signal; processing at a processor the sensed signal to detect beats in a pulsatile signal; determining validity of the detected beats; storing the detected beats and data associated with the detected beats in the sensed signal as the pressure applied to the artery by the blood flow occlusion system deflates towards a level below a nominal level; determining baseline beat characteristics; evaluating the stored beats and associated data to detect change in beat characteristics as compared to the baseline beat characteristics; selecting a beat before the detected change in the beat characteristic as the last beat indicating the onset of the diastolic blood pressure for the artery; determining a value of the applied pressure at the last beat as the diastolic blood pressure for the artery.

Noninvasive blood pressure measurement method and device

An object detection system may generate regions of interest (ROIs) from an input image that can be processed by a wide range of object detectors. According to the techniques described herein, an image is processed by a light-weight neural network (e.g., a heatmap network) that outputs object center and object scale heat-maps. The heatmaps are processed to define ROIs that are likely to include objects. Overlapping ROIs are then merged to reduce the aggregate size of the ROIs, and merged ROIs are downscaled to a reduced set of pre-defined resolutions. Fully-convolutional, high-accuracy object detectors may then operate on the downscaled ROIs to output accurate detections at a fraction of the computations by operating on a reduced image. For example, fully-convolutional, high-accuracy object detectors may operate on a subset of the entire image (e.g., cropped images based on ROIs) thus reducing computations otherwise performed over the entire image.

Region of interest selection for object detection

Growing community of inventors

Tel Aviv, Israel

Alexandra Dana