Abstract: Reducing false negatives and finding new classes in object detectors is disclosed. Also disclosed is a method that includes grouping together a plurality of cropped image portions from region proposals based on image properties. The method also includes receiving first user input that either establishes that the grouped together, cropped image portions relate to uninteresting objects or establishes that the grouped together, cropped image portions relate to an object class of interesting objects. The method also includes obtaining, only when the grouped together, cropped image portions relate to the object class of interesting objects, second user input that includes an object label corresponding to the object class of interesting objects.

Abstract: Systems and methods for tissue classification are provided. An image of tissue on a substrate is obtained as a plurality of pixels. Fiducial markers are on the substrate boundary. Pixels are assigned to a first class, indicating tissue sample, or a second class, indicating background. The assigning uses the fiducial markers to define a bounding box within the image and disregards pixels outside the box. Then, heuristic classifiers are applied to the pixels: for each respective pixel in the plurality of pixels, each heuristic classifier votes for the respective pixel between the first and second class, thereby forming an aggregated score for each pixel that in one of first class, likely first class, likely second class, and obvious second class. The aggregated score and intensity of each pixel is applied to a segmentation algorithm to assign a probability to each pixel of being tissue sample or background.

Abstract: A biometrics authentication device for authenticating a person by comparing biometric features of a body part of the person with pre-stored biometric features of body parts of a plurality of registered persons is configured to: capture image data of the body part of the person; determine from the captured image data at least one characteristic geometric body part property of the body part of the person and biometric features of the body part of the person; limit comparison of the biometric features of the body part of the person to pre-stored biometric features of body parts of the plurality of registered persons which have a predefined similarity level with the at least one characteristic geometric body part property of the person.

Abstract: Systems, methods, and non-transitory media are provided for providing spatiotemporal recycling networks (e.g., for video segmentation). For example, a method can include obtaining video data including a current frame and one or more reference frames. The method can include determining, based on a comparison of the current frame and the one or more reference frames, a difference between the current frame and the one or more reference frames. Based on the difference being below a threshold, the method can include performing semantic segmentation of the current frame using a first neural network. The semantic segmentation can be performed based on higher-spatial resolution features extracted from the current frame by the first neural network and lower-resolution features extracted from the one or more reference frames by a second neural network. The first neural network has a smaller structure and/or a lower processing cost than the second neural network.

Abstract: An apparatus configured for head-worn by a user, includes: a screen configured to present graphics for the user; a camera system configured to view an environment in which the user is located; and a processing unit coupled to the camera system, the processing unit configured to: obtain a feature detection response for a first image, divide the feature detection response into a plurality of patches having a first patch and a second patch, determine a first maximum value in the first patch of the feature detection response, and identify a first set of one or more features for a first region of the first image based on a first criterion that relates to the determined first maximum value.

Abstract: The method is used for creating an all-in-focus image of a portion of an iridocorneal angle of an eye starting from a plurality of images (610), these images being shallow field-depth images of that portion taken with different focus planes but with a same image frame; the method comprises the steps of: A) pre-processing (620) said plurality of images so to obtain a plurality of single-channel images if the images of said plurality are color images, B) calculating (630) an initial focus map starting from said plurality of single-channel images, C) creating (640) an initial estimated all-in-focus image starting from said initial focus map and said plurality of single-channel images, D) calculating (650) an initial edge map starting from said initial focus map and said plurality of single-channel images, E) iterating (660) a regularization process until a stop regularization condition is met, wherein the regularization process comprises removing one or more edge points of the initial edge map by considering a r

Abstract: A diagnosis assisting system, a diagnosis assisting method, and a diagnosis assisting program provide information that contributes to an objective diagnosis, with a server of a diagnosis assisting system including a learned model acquisition unit that acquires a plurality of learned models, each of which is generated by machine learning, inputs information based on an image obtained by imaging a diagnostic target, and outputs information that indicates a diagnosis result of the diagnostic target; an image acquisition unit that acquires an image to be analyzed; a calculation unit that performs calculation based on the plurality of learned models acquired on the image acquired, and calculates one piece of information about a diagnosis using the plurality of learned models; and an output unit that outputs the information calculated by the calculation unit.

Abstract: Laser mapping imaging with reduced fixed pattern noise is disclosed. A method includes actuating an emitter to emit a plurality of pulses of electromagnetic radiation and sensing reflected electromagnetic radiation resulting from the plurality of pulses of electromagnetic radiation with a pixel array of an image sensor to generate a plurality of exposure frames. The method includes applying edge enhancement to edges within an exposure frame of the plurality of exposure frames. The method is such that at least a portion of the plurality of pulses of electromagnetic radiation emitted by the emitter comprises a laser mapping pattern.

Abstract: One or more machine learning techniques can be used to identify locations of potential malignancies within images (e.g., video images) captured during a medical procedure, such as an endoscopic procedure. The images can be displayed, in real-time, on a display unit. The images can be displayed with a graphical overlay that isolates the identified locations of potential malignancies.

Abstract: A method and system for multi-object tracking is set forth. Object data for boundaries of a plurality of objects are received. Poisson multi-Bernoulli mixture filtering is performed on the object data to form a filtered set of object data. Ultimately, the filtered set of object data is used to control the operation of the vehicle. Identifiers and probabilities are associated with the objects to reduce the set of object data.

Abstract: Disclosed is a reconfigurable parallel 3-Dimensional (3-D) convolution engine for performing 3-D Convolution and parallel feature map extraction on an image. The reconfigurable parallel 3-D convolution engine further comprises a plurality of CNN reconfigurable engines configured to perform 3-D convolution, in parallel, to process a plurality of feature maps, a kernel memory space, present in each instance of CNN reconfigurable engine, capable for holding a set of parameters associated to a network layer having each operational instance of CNN reconfigurable engine, and at least one memory controller, an Input Feature Map Memory (FMM) cluster and an Output FMM cluster.

Abstract: A violation detection platform may obtain image data, location data, and sensor data associated with a vehicle. The violation detection platform may determine a probability that a frame of the image data includes an image of a stop sign. The violation detection platform may determine that the probability satisfies a probability threshold. The violation detection platform may identify location data and sensor data associated with the frame of the image data based on the probability satisfying the probability threshold. The violation detection platform may determine an occurrence of a type of a stop sign violation based on the probability, the location data, and the sensor data. The violation detection platform may perform one or more actions based on determining the occurrence of the type of the stop sign violation.

Abstract: Adaptive phase unwrapping for a time-of-flight camera. A scene is illuminated with modulation light having two or more frequencies that do not have a common integer denominator. The modulation light that is reflected off objects within the scene is received at a sensor array. The received modulation light is then processed and weighted in the complex domain to determine unwrapped phases for each of the two or more frequencies of modulation light.

Abstract: An image recognition method, a training system for an object recognition model and a training method for an object recognition model are provided. The image recognition method includes the following steps. At least one original sample image of an object in a field and an object range information and an object type information in the original sample image are obtained. At least one physical parameter is adjusted to generate plural simulated sample images of the object. The object range information and the object type information of the object in each of the simulated sample images are automatically marked. A machine learning procedure is performed to train an object recognition model. An image recognition procedure is performed on an input image.

Abstract: An information processing system includes circuitry. The circuitry causes a terminal apparatus to display a setting screen for setting an extraction area for extracting, from a tabular image, an item value for each of one or more extraction target items. The setting screen displays, on the tabular image, an extraction guide representing the extraction area according to each of the one or more extraction target items. The circuitry further receives an operation of setting a position of the extraction guide on the setting screen.

Abstract: A processor-implemented method includes: generating a preprocessed infrared (IR) image by performing first preprocessing based on an IR image including an object; generating a preprocessed depth image by performing second preprocessing based on a depth image including the object; and determining whether the object is a genuine object based on the preprocessed IR image and the preprocessed depth image.

Abstract: Data for training a machine learning algorithm to detect airborne objects is generated by capturing background images using a camera aboard an aerial vehicle, and generating a trajectory of a synthetic object, such another aerial vehicle, in three-dimensional space. The trajectory is projected into an image plane of the camera, determined from a pose of the camera calculated using inertial measurement unit data captured by the aerial vehicle. Images of the synthetic object may be rendered based on locations of the trajectory in the image plane at specific times. Pixel-accurate locations for the rendered images may be determined by calculating a homography from consecutive images captured using the camera, and adjusting locations of the trajectory using the homography. The rendered images may be blended into the images captured by the camera at such locations, and used to train a machine learning algorithm.

Abstract: A method for detecting and labeling a target object in a 2D image includes receiving a plurality of 2D images from a visual sensor, manually marking points of the target object on each of the 2D images, generating from the 2D images a 3D world coordinate system of the environment surrounding the target object, mapping each of the marked points on the 2D images to the 3D world coordinate system using a simultaneous localization and mapping (SLAM) engine, automatically generating a 3D bounding box covering all the marked points mapped to the 3D world coordinate system, mapping the 3D bounding box to each of the 2D images, generating a label for the target object on each of the 2D images using a machine learning object detection model, and training the machine learning object detection model based on the generated label for the target object.

Abstract: Systems and methods for detecting symptoms of occupant illness is disclosed herein. In embodiments, a storage is configured to maintain a visualization application and data from one or more sources, such as an audio source, an image source, and/or a radar source. A processor is in communication with the storage and a user interface. The processor is programmed to receive data from the one or more sources, execute human-detection models based on the received data, execute activity-recognition models to recognize symptoms of illness based on the data from the one or more sources, determine a location of the recognized symptoms, and execute a visualization application to display information in the user interface. The visualization application can show a background image with an overlaid image that includes an indicator for each location of recognized symptom of illness. Additionally, data from the audio source, image source, and/or radar source can be fused.

Abstract: Methods and apparatuses are disclosed to personalize image capture operations of imaging equipment according to models that correspond uniquely to subjects being imaged. According to these techniques, a subject's face may be detected from a first image supplied by an image source and a first model of the subject may be developed from the detected face. The first model of the subject may be compared to another model of the subject developed from other images. Image adjustment parameters may be generated from a comparison of these models, which may control image adjustment techniques that are applied to the newly captured image of the subject. In this manner, aspects of the present disclosure may generate image capture operations that are tailored to characteristics of the subjects being imaged and avoid artifacts that otherwise could cause image degradation.