Abstract: Embodiments relate to automatic perspective and horizon correction. Generally, a camera captures an image as an image file. Capture-time orientation data from one or more sensors is used to determine the camera's attitude with respect to a defined reference frame. The orientation data and/or attitude can be registered into metadata of the image file and used to generate axis lines representative of the camera's reference frame. A reference line such as a horizon can be automatically identified from detected line segments in the image that align with one of the axis lines within a predetermined angular threshold. The reference line can be used to generate a camera transformation from a starting orientation reflected by the camera attitude to a transformed orientation that aligns the reference line with the reference frame. The transformation can be applied to the image to automatically correct perspective distortion and/or horizon tilt in the image.

Abstract: An information processing apparatus includes at least one processor causing the information processing apparatus to act as a first obtainment unit configured to execute processing for obtaining a first feature amount for each of a plurality of frames, a specification unit configured to specify a priority order of frames for obtaining a second feature amount different from the first feature amount based on the first feature amount obtained by the first obtainment unit, a second obtainment unit configured to execute processing for obtaining the second feature amount from a frame in accordance with the priority order, and a selection unit configured to select, based on the second feature amount obtained by the second obtainment unit, an image processing target frame. The number of frames from which the second feature amount is obtained is fewer than the number of the plurality of frames from which the first feature amount is obtained.

Abstract: A method for supporting visual tracking includes receiving a plurality of image frames captured at different times using an imaging device. Each of the plurality of image frames includes a plurality of pixels associated with a plurality of feature points. The method further includes analyzing the plurality of image frames to compute movement characteristics of the plurality of feature points and identifying a tracking feature relative to a background feature based on the movement characteristics of the plurality of feature points.

Abstract: A method includes, identifying, in a three-dimensional (3D) anatomical image of a patient organ, multiple anatomical points corresponding to respective predefined locations on a skin of the patient organ in a first coordinate system. Multiple positions in a second coordinate system, measured by a position sensor of a position-tracking system at the respective predefined locations on the skin of the patient organ, are received. At each predefined location, a distance is calculated between a respective anatomical point and closest bone tissue of the patient organ. Weights are assigned to the predefined locations based on respective distances between the anatomical points and the closest bone tissue. The first and second coordinate systems are registered, by correlating between the positions and the respective anatomical points using the assigned weights.

Abstract: The disclosure provides an object detection method and apparatus based on a Dynamic Vision Sensor (DVS). The method includes the following operations of: acquiring a plurality of image frames by a DVS; and, detecting the image frames by a recurrent coherent network to acquire a candidate box for objects to be detected, wherein the recurrent coherent network comprising a frame detection network model and a candidate graph model. By using a new recurrent coherent detection network, a bounding box for an object to be detected is fast detected from the data acquired by a DVS. The detection speed is improved greatly while ensuring the detection accuracy.

Abstract: Systems and methods for determining a breast region in a medical image are provided. The methods may include obtaining a first image relating to the breast region, determining a first region including a first plurality of pixels in the breast region, determining a second region including a second plurality of pixels relating to an edge of the breast region, and determining the breast region by combining the first region and the second region. The second plurality of pixels may include at least a portion of the first plurality of pixels.

Abstract: A method for assessing healing of a subject includes receiving a time series of signal intensity data capturing the transit of an imaging agent through tissue over a period of time, wherein the tissue comprises a plurality of calculation regions and wherein signal intensity in each calculation region over the period of time may be approximated by a time-intensity curve corresponding to the calculation region; determining, for each calculation region, a coefficient value that is related to at least a portion of the time-intensity curve corresponding to the calculation region; and converting the coefficient values across the plurality of calculation regions into a coefficient-derived image map.

Abstract: An image processing apparatus includes: an acquisition unit that acquires a plurality of first images that correspond to a plurality of spatial frequencies on a one-to-one basis; and a generation unit that generates a second image by synthesizing the first images acquired by the acquisition unit.

Abstract: A device for recognizing a vehicle license plate number comprises a division unit for dividing a vehicle license plate image into a plurality of images such that a predetermined area is included in each of the plurality of images; and a distribution management unit for distributing the plurality of divided images to a plurality of recognizing terminals corresponding to each area and receiving the results of recognizing the corresponding area from each of the plurality of recognizing terminals.

Abstract: A camera-based security system protects an asset by detecting an aerial surveillor and consequently storing notifications into a video archive, alerting to an operator console, and actuating privation apparatus. One or more cameras provides video streams to a processor which derives object motion. Attributes of object motion trigger notification to record and alert on conditions associated with an aerial surveillor. Tracking of pixels, pixel blocks, and motion vectors enable rules based determination of an airborne surveillance vehicle according to characteristic hovering or lingering by masking LSB of accumulated positive and negative movements. Actuators cause privation enhancement apparatus to obfuscate the protected asset (structure, area, or volume) or to interpose between the protected asset and the surveillor. The method traces a travel path of an object; and determines a ray from a private property to a surveillor drone.

Abstract: A distributed vehicle documentation system uses multiple sensor systems to capture vehicle information and generate vehicle documentation. A sensor system may be a micro server in communication with a sensor and a control device. In response to requests from the control device, the sensor system may analyze images input in order to identify an object in the images, and modifying the images based on the identified object. For example, in response to identifying a wheel in an image, the image may be cropped in order to be centered around the identified wheel. In the event that the sensor system cannot identify the object (e.g., cannot identify the wheel in the image), another image may be obtained with a different field of view based on a determined size of the vehicle.

Abstract: The present disclosure relates to a device, a system, and a computer-readable medium for calculating vessel flow parameters based on angiography. In one implementation, the device includes a processor and a memory storing computer-executable instructions that, when executed by the processor, cause the processor to perform the following operations: selecting a plurality of template frames from the angiographic images to generate a 3D model for a vessel; determining a start frame and an end frame in the plurality of angiographic images showing a contrast filling process; determining corresponding locations of front ends of the contrast in the start frame and the end frame in the 3D model of the vessel; calculating a vessel volume between the determined locations of the front ends in the 3D model; and determining an average blood flow rate based on the calculated volume, and a time interval between the start frame and the end frame.

Abstract: The present disclosure provides systems and methods that include or otherwise leverage use of a facial expression model that is configured to provide a facial expression embedding. In particular, the facial expression model can receive an input image that depicts a face and, in response, provide a facial expression embedding that encodes information descriptive of a facial expression made by the face depicted in the input image. As an example, the facial expression model can be or include a neural network such as a convolutional neural network. The present disclosure also provides a novel and unique triplet training scheme which does not rely upon designation of a particular image as an anchor or reference image.

Abstract: A tracker is described which comprises a processor configured to receive captured sensor data depicting an object. The processor is configured to access a rigged polygon mesh model of the object and to compute a plurality of approximate surface normals of a limit surface of the rigged polygon mesh. The processor is configured to compute values of pose parameters of the model by calculating an optimization to fit the model to the captured sensor data where the optimization uses an evaluation function based on the plurality of approximate surface normals.

Abstract: The invention provides a retinal prosthetic method and device that mimics the responses of the retina to a broad range of stimuli, including natural stimuli. Ganglion cell firing patterns are generated in response to a stimulus using a set of encoders, interfaces, and transducers, where each transducer targets a single cell or a small number of cells. The conversion occurs on the same time scale as that carried out by the normal retina. In addition, aspects of the invention may be used with robotic or other mechanical devices, where processing of visual information is required. The encoders may be adjusted over time with aging or the progression of a disease.

Abstract: A machine learning method for learning how to form bounding boxes, performed by a machine learning apparatus, includes extracting learning images including a target object among a plurality of learning images included in a learning database, generating additional learning images in which the target object is rotated from the learning images including the target object, and updating the learning database using the additional learning images.

Abstract: A method and system for detecting a fall risk condition, the system comprising a surveillance camera configured to generate a plurality of frames showing an area in which a patient at risk of falling is being monitored, and a computer system comprising memory and logic circuitry configured to store motion feature patterns that are extracted from video recordings, the motion feature patterns are representative of motion associated with real alarm cases and false-alarm cases of fall events, receive a fall alert from a classifier, determine motion features of one or more frames from the plurality of frames that correspond to the fall alert; compare the motion features of the one or more frames with the motion feature patterns, and determine whether to confirm the fall alert based on the comparison.

Abstract: A method for recognizing a picture, a method and an apparatus for labelling a picture, and a storage medium. The method for recognizing a picture comprises: acquiring a clothes picture labelled with a positioning key point and a clothes wearing region (S310); extracting, based on the locations of the clothes wearing region and the positioning key point, at least one picture region representing a feature region from the clothes picture (S320); and respectively acquiring feature information representing the feature region based on a region feature recognition model corresponding to the feature region (S330). By labelling the positioning key point, a picture representing a clothes content in the clothes picture is positioned, so that the interference of a background content in the clothes picture is reduced.

Abstract: A method and system for obtaining images of an object of interest using a system comprising an X-ray source facing a detector. The method and system enable the acquiring of a plurality of 2D projection images of the object of interest in a plurality of orientations. A selected 2D projection image such as the zero projection of the plurality of projections can be enhanced by using at least a subset of the plurality of tomosynthesis projection images. The obtained enhanced 2D projection image is displayed for review.

Abstract: Systems and methods are described herein for tracking an elongate instrument or other medical instrument in an image.