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: 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: 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: 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 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: 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: 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.

Abstract: Systems and methods for motion correction in medical imaging are provided in the present disclosure. The systems may obtain at least two image sequences relating to a subject. Each of the at least two image sequences may be reconstructed based on image data that is acquired by a medical imaging device during one of at least two time periods. The subject may undergo a physiological motion during the at least two time periods. The systems may generate, based on the at least two image sequences, at least one corrected image sequence relating to the subject by correcting, using a motion correction model, an artifact caused by the physiological motion.

Abstract: According to embodiments of the present invention, a method, a device and a computer program product for image processing is provided. A computing device obtains an image of a first object, the image presenting a defect of the first object. A computing device obtains defect distribution information indicating respective frequencies of a plurality of predetermined categories of defects presented at corresponding locations in a plurality of training images, the plurality of training images presenting second objects and being used for training a defect classifier. A computing device determines a target category of the defect of the first object by applying the image and the defect distribution information to the defect classifier. A computing device generates one or more correction notifications.

Abstract: A system or process may generate a summarization of multimedia content by determining one or more salient moments therefrom. Multimedia content may be received and a plurality of frames and audio, visual, and metadata elements associated therewith are extracted from the multimedia content. A plurality of importance sub-scores may be generated for each frame of the multimedia content, each of the plurality of sub-scores being associated with a particular analytical modality. For each frame, the plurality of importance sub-scores associated therewith may be aggregated into an importance score. The frames may be ranked by importance and a plurality of top-ranked frames are identified and determined to satisfy an importance threshold. The plurality of top-ranked frames are sequentially arranged and merged into a plurality of moment candidates that are ranked for importance. A subset of top-ranked moment candidates are merged into a final summarization of the multimedia content.

Abstract: An apparatus that estimates a position of each object in image data in which a plurality of objects is imaged, the apparatus includes a first acquisition unit configured to acquire position information indicating positions of joints of the plurality of objects in the image data, a second acquisition unit configured to acquire a score map in which a feature for identifying each object is converted into a numerical value, the score map being output by a pre-trained model in response to input of the image data, and an identification unit configured to identify positions of joints belonging to each of the plurality of objects, based on the position information and the score map.

Abstract: Embodiments relate to circuitry for temporal processing and image fusion. An image fusion circuit receives captured images, and generates corresponding image pyramids. The generated image pyramids are raster or tiled processed, and stored in memory. A fusion module receives a first and second image pyramids from the memory, and warps and fuses image pyramids to generate a fused image pyramid, which may be used for further processing, and may also be stored back into the memory. The image fusion circuitry is configurable to operate in a plurality of different configuration modes corresponding to different image fusion applications for fusing image pyramids of received images, including two-frame fusion, temporal filtering, infinite impulse response (IIR) temporal processing, and/or finite impulse response (FIR) temporal processing.

Abstract: Embodiments relate to circuitry for temporal processing and image fusion. An image fusion circuit receives captured images, and generates corresponding image pyramids. The generated image pyramids are raster or tiled processed, and stored in memory. A fusion module receives a first and second image pyramids from the memory, warps the first image pyramid based upon the second image pyramid, and fuses the warped first image pyramid with the second image pyramid to generate a fused image pyramid, which may be used for further processing, and may also be stored back into the memory. Because pyramid generation occurs prior to warping and fusion, and by allowing fused image pyramids to be stored back into memory, the image fusion circuitry is configurable to implement a variety of temporal processing functions involving different image fusion combinations.

Abstract: Controls within images of a user interface of a computer application are detected by way of region-based R-FCN and Faster R-CNN engines. Datasets comprising images containing application control, wherein the application controls include images of application where width is greater than height, width is equal to height and height is greater than width are retrieved. Each of the datasets is processed with the R-FCN and Faster R-CNN engines to generate a software configured to recognize, from an input image, application controls wherein the application controls are characterized by dimensions where width is greater than height, where width is substantially equal to height, and where height is greater than width.

Abstract: A method of pipelining inference of a neural network, which includes an i-th layer (i being an integer greater than zero) and an (i+1)-th layer, includes processing, for a first input image, first i-th values of the i-th layer to generate first (i+1)-th values for the (i+1)-th layer, processing, for the first input image, the first (i+1)-th values of the (i+1)-th layer to generate output values, and concurrently with processing, for the first image, the (i+1)-th values, processing, for a second input image, second i-th values of the i-th layer to generate second (i+1)-th values.