Patent classifications
G06V10/143
DATA BAND SELECTION USING MACHINE LEARNING
Methods, systems, apparatus, and computer-readable media for data band selection using machine learning. In some implementations, image data comprising information for each of multiple wavelength bands is obtained. A multi-layer neural network is trained using the image data to perform one or more classification or regression tasks. A proper subset of the wavelength bands is selected based on parameters of a layer of the trained multi-layer neural network, where the parameters were determined through training of the multi-layer neural network using the image data. Output is provided indicating that the selected wavelength bands are selected for the one or more classification or regression tasks.
SYSTEMS AND METHODS FOR MACHINE VISION ROBOTIC PROCESSING
Systems, methods, and media for machine vision-guided robotic loading are provided. Such systems and methods can allow for more accurate object detection so as to allow for robotic picking or loading of an object from a pile or group of objects. In some embodiments, a camera is controlled to capture a background image of the object or group of objects. One or more illumination sources (such as, e.g., laser illuminators) are controlled to project immunization toward the object or group of objects within the field-of-view of the camera. The camera may be controlled to capture a scan image comprising the projected illumination. Based on the scan image, a depth map can be determined, which is provided to a machine learning model along with the background image. The output of the machine learning model can then provide information associated with one or more objects, such as location information, orientation information, and the like.
FINGER VEIN SENSORS
The present disclosure relates to several types of finger vein sensor. In certain embodiments, the finger vein sensor includes: an image sensor, and an infrared light source. Image sensor captures infrared image of finger vein pattern of a finger of a target human. The image sensor faces down and is positioned at top of finger vein sensor. The infrared light source may include a predetermined number of infrared light-emitting diodes (LED), and they are arranged in one or more rows and one or more columns and positioned at bottom of finger vein sensor. The finger is positioned between infrared light source and image sensor. The infrared light from the infrared light source irradiates the finger vertically from the bottom to generate the infrared image of finger vein pattern of the finger on the image sensor, and the image sensor captures the infrared image of finger vein pattern of the finger.
SYSTEM AND METHOD TO CORRECT OVERSATURATION FOR IMAGE-BASED SEATBELT DETECTION
A system and method for detecting seatbelt positioning includes capturing, by a camera, a near infrared source image of an occupant in a vehicle, determining a position of a head of the occupant in the source image, determining a region of interest for a seatbelt based on the position of the head; determining an oversaturation condition in the region of interest for the seatbelt, adjusting the source image to form an adjusted image compensating the oversaturation condition in the region of interest for the seatbelt, converting the adjusted image to a black-and-white image, and detecting the seatbelt within the black-and-white image. Adjusting the source image to compensate the oversaturation condition may include adjusting an exposure level of the source image based on a contrast ratio in the region of interest and/or based on detecting a predetermined pattern of the seatbelt within the region of interest for the seatbelt.
IMAGE PROCESSING APPARATUS, OPTICAL TRANSMISSION APPARATUS, OPTICAL COMMUNICATION SYSTEM, PROGRAM AND IMAGE PROCESSING METHOD
An image processing apparatus 5 is provided with a processing unit, the processing unit acquiring images 44 that are continuous over time, acquiring a position of a visible light source in a lit-up state in each of the continuous images 44, as a position of a movable body 3; and acquiring identification information about the movable body 3 based on a blinking pattern of invisible light of an invisible light source provided on the movable body 3.
Ultrasonic fingerprint sensor with a contact layer of non-uniform thickness
An ultrasonic sensor includes a two-dimensional array of ultrasonic transducers, wherein the two-dimensional array of ultrasonic transducers is substantially flat, a contact layer having a non-uniform thickness overlying the two-dimensional array of ultrasonic transducers, and an array controller configured to control activation of ultrasonic transducers during an imaging operation. During the imaging operation, the array controller is configured to control a transmission frequency of activated ultrasonic transducers during the imaging operation, wherein a plurality of transmission frequencies are used during the imaging operation to account for an impact of an interference pattern caused by the non-uniform thickness of the contact layer, and is configured to capture at least one fingerprint image using the plurality of transmission frequencies.
Ultrasonic fingerprint sensor with a contact layer of non-uniform thickness
An ultrasonic sensor includes a two-dimensional array of ultrasonic transducers, wherein the two-dimensional array of ultrasonic transducers is substantially flat, a contact layer having a non-uniform thickness overlying the two-dimensional array of ultrasonic transducers, and an array controller configured to control activation of ultrasonic transducers during an imaging operation. During the imaging operation, the array controller is configured to control a transmission frequency of activated ultrasonic transducers during the imaging operation, wherein a plurality of transmission frequencies are used during the imaging operation to account for an impact of an interference pattern caused by the non-uniform thickness of the contact layer, and is configured to capture at least one fingerprint image using the plurality of transmission frequencies.
User interface system for an interactive exercise machine
A user interface for an interactive exercise system includes a display module held by a mechanical support system, with the display module able to display a video of a trainer. The trainer can be presented in full body view against a black background and a mirror element attached to at least partially cover the display module.
Invisible Luminescent Protection for Financial and Identification Documents
Methods and apparatus for invisible luminescent protection for financial and identification documents are described herein. An example apparatus includes an illuminating source to illuminate a sample with light having a first wavelength, a photo element to detect light having a second wavelength and to capture an image of a first pattern printed on the sample, wherein the first pattern is printed on a first area of the sample with clear ink containing inorganic, ceramic particles having a mean diameter of less than one micron and having luminescent properties such that when the particles are illuminated with light having the first wavelength, they emit light having the second wavelength.
GAZE POSITION DETECTION APPARATUS AND GAZE POSITION DETECTION METHOD
A gaze position detection apparatus includes: a memory which stores a plurality of registered move patterns of a gaze position and correction information of the gaze position included in the registered move pattern for each of the registered move patterns; a move pattern detection unit which detects a move pattern of a user's gaze position, from a plurality of measurement points of the user's gaze position which are obtained from data items representing a user's gaze direction generated by a gaze detection device in different timing; a similar-pattern extraction unit which extracts the registered move pattern similar to the move pattern of the user's gaze position from among the plurality of registered move patterns; and a correction unit which corrects the gaze position included in the move pattern of the user's gaze position using the correction information of the gaze position for the similar registered move pattern.