Snapaid Ltd.

Snap-aid Patents Ltd.

Anyvision Interactive Technologies Ltd.

Ishay Sivan

Sankha Subhra Mukherjee

Rolf Hugh Baxter

Neil Martin Robertson

Alexander Zilberman

Ailon Etshtein

Ohad Shaubi

Idan Barak

Yaaqov Valero

A computerized method for computing the photo quality of a captured image in a device image acquisition system, comprising on-board combining of a plurality of quality indicators computed from said captured image and its previous image frames quality indicators and a confidence level for at least one of said quality indicators; and using a processor to determine, based on said combining, whether photo quality is acceptable and taking differential action depending on whether quality is or is not acceptable.

Real time assessment of picture quality

Presented herein are systems, methods and apparatuses for increasing reliability of face recognition in analysis of images captured by drone mounted imaging sensors, comprising: recognizing a target person in one or more iterations, each iteration comprising: identifying one or more positioning properties of the target person based on analysis of image(s) captured by imaging sensor(s) mounted on a drone operated to approach the target person, instructing the drone to adjust its position to an optimal facial image capturing position selected based on the positioning property(s), receiving facial image(s) of the target person captured by the imaging sensor(s), receiving a face classification associated with a probability score from machine learning model(s) trained to recognize the target person, and initiating another iteration in case the probability score does not exceed a certain threshold. Finally, the face classification may be outputted for use by one or more face recognition based systems.

Adaptive positioning of drones for enhanced face recognition

Provided herein are systems and methods for applying adaptive classes thresholds to enhance object detection Machine Learning (ML) models by receiving a plurality of labeled feature vectors extracted from a plurality of images associated with a plurality of objects, one or more subsets of the plurality of feature vectors are associated with respective object(s) and labeled accordingly, computing an adaptive threshold for each object in a plurality of iterations, each iteration comprising: (1) computing deviation of a respective feature vector of the subset from an aggregated feature vector, (2) computing, in case the deviation is within a predefined value, a threshold enclosing the respective feature vector, and (3) adjusting the adaptive threshold to enclose the threshold of the respective feature vector and outputting the adaptive threshold(s) for classifying unlabeled feature vectors to class(s) of respective object(s) associated with the adaptive threshold(s) in which the unlabeled feature vectors fall.

Inter-class adaptive threshold structure for object detection

A computerized method for computing the photo quality of a captured image in a device image acquisition system, comprising on-board combining of a plurality of quality indicators computed from said captured image and its previous image frames quality indicators and a confidence level for at least one of said quality indicators, and using a processor to determine, based on said combining, whether photo quality is acceptable and taking differential action depending on whether quality is or is not acceptable.

Presented herein are systems and methods for increasing reliability of object detection, comprising, receiving a plurality of images of one or more objects captured by imaging sensor(s), receiving an object classification coupled with a first probability score from machine learning model(s) trained to detect the object(s) and applied to the image(s), computing a second probability score for classification of the object(s) according to physical attribute(s) of the object(s) estimated by analyzing the image(s), computing a third probability score for classification of the object(s) according to a movement pattern of the object(s) estimated by analyzing at least some consecutive images, computing an aggregated probability score aggregating the first, second and third probability scores, and outputting, in case the aggregated probability score exceeds a certain threshold, the classification of each object coupled with the aggregated probability score for use by object detection based system(s).

Object detection based on machine learning combined with physical attributes and movement patterns detection

A video or still hand-held digital camera is activated or controlled based on estimation of a user head pose or gaze direction. The system comprises uses two wearable devices associated with right and left sides of the user body, each comprises an RF beacon. The head pose or gaze detection is estimated by comparing the signal strength (such as RSSI) or the phase of the RF signals from the wearable devices at the digital camera device. An angular deviation between the head pose (or gaze detection) and the digital camera (such as the line of sight) is estimated, and the digital camera is activated or controlled based on comparing the angular deviation to a set threshold. The RF signals may be Personal Area Network (PAN) signals, such as Bluetooth Low Energy (BLE) signals. The wearable devices may be head mounted, structured as glasses, earpieces, headphones, or hat mounted.

Estimating and using relative head pose and camera field-of-view

A device comprises a first digital camera having a first center line of sight and a second digital camera having a second center line of sight that is parallel and opposing the first camera. A method for controlling the first camera based on estimating the angular deviation between a person gaze direction and the line of sight of the first digital camera. A human face is detected in an image captured as an image file by the second digital camera, using a face detection algorithm. An angular deviation &#x3b1; is estimated, defined between the second center line of sight and an imaginary line from the second camera to the detected human face based on the captured image, and an angular deviation &#x3b2; is estimated, defined between the imaginary line from the second camera to the detected face and the human face gaze direction based on the captured image.

Growing community of inventors

Tel Aviv, Israel

Ishay Sivan