Abstract: Among other things, techniques are described for cross-modality active learning for object detection. In an example, a first set of predicted bounding boxes and a second set of predicted bounding boxes is generated. The first set of predicted bounding boxes and the second set of predicted bounding boxes are projected into a same representation. The projections are filtered, wherein predicted bounding boxes satisfying a maximum confidence score are selected for inconsistency calculations. Inconsistencies are calculated across the projected bounding boxes based on filtering the projections. An informative scene is extracted based on the calculated inconsistencies. A first object detection neural network or a second object detection neural network is trained using the informative scenes.

Abstract: An apparatus for image reconstruction that includes input circuitry configured to acquire, from an image sequence, first and second 2D projection data of a region of interest of an object at respective acquisition times; and provide first 3D object data of a first object in a region of interest and second 3D object data of a second object in a region of interest. The apparatus also includes a processor configured to generate a first registration of the first and/or second 3D object data to the first 2D projection data and a second registration of the first and/or second 3D object data to the second 2D projection data; provide a vector field defining motion of the second object relative to the first object between the acquisition times based on the registrations; generate corrected projection data using the vector field; and generate a motion-compensated image sequence based on the corrected projection data.

Abstract: A detection system includes a filter and a detector. The filter receives input packets from one or more dynamic vision sensors (DVSs) deployed in an area. The filter reduces the bandwidth of the input packets to produce compressed data packets while maintaining good end-to-end detection capability. The compressed data packets are transmitted to a detector in a low bandwidth transmission. The detector may collect compressed data packets from many filters. The detector determines if an object of interest is represented in the information of the input packets. If an object of interest is present, the detector activates an alarm, sends a notification to a person associated with the area and/or stores an indication in a database.

Abstract: Provided are an object tracking system and an object tracking method.

Abstract: Provided herein is technology relating to analysis of images and particularly, but not exclusively, to methods and systems for determining the area and/or volume of a region of interest using optical coherence tomography data. Some embodiments provide for determining the area and/or volume of a lesion in retinal tissue using three-dimensional optical coherence tomography data and a two-dimensional optical coherence tomography fundus image.

Abstract: To enable high-speed autonomous flight of a flight object. A three-dimensional real-time observation result is generated on the basis of self-position estimation information and three-dimensional distance measurement information. A prior map corresponding to a three-dimensional real-time observation result is acquired. The three-dimensional real-time observation result and the prior map are aligned. After the alignment, the three-dimensional real-time observation result is expanded on the basis of the prior map. A flight route is set on the basis of the three-dimensional real-time observation result having been expanded. In the flight object such as a drone, a somewhat long flight route can be accurately calculated at a time in a global behavior plan, which enables high-speed autonomous flight of the flight object.

Abstract: A method of establishing an image set for image recognition includes obtaining a single-label image set comprising an image annotated with a single label, and a multi-label image set comprising an image annotated with a plurality of labels; converting content of each label into a corresponding word identifier according to a semantic network, to obtain a word identifier set, a converted single-label image set, and a converted multi-label image set; and constructing a hierarchical semantic structure according to the word identifier set and the semantic network. The method also includes performing label supplementation on the image in the converted single-label image set to obtain a supplemented single-label image set; performing label supplementation on the supplemented single-label image set to obtain a final supplemented image set; and establishing a target multi-label image set to train an image recognition model by using the target multi-label image set.

Abstract: A human-object scene recognition method includes: acquiring an input RGB image and a depth image corresponding to the RGB image; detecting objects and humans in the RGB image using a segmentation classification algorithm based on a sample database; in response to detection of objects and/or humans, performing a segment detection to each of the detected objects and/or humans based on the ROB image and the depth image, and acquiring a result of the segment detection; calculating 3D hounding boxes for each of the detected objects and/or humans according to the result of the segment detection, and determining a position of each of the detected objects and/or humans according to the 3D bounding boxes.

Abstract: Provided is a method for detecting a biomarker indicating states of a target biological system based on data acquired by measuring the target biological system. The method includes the steps of: preparing a reference dataset based on data acquired from one or more reference biological systems; generating a target dataset by adding, to the reference dataset, target biological data acquired from the target biological system; acquiring first correlation coefficients between a plurality of factor items in the reference dataset; acquiring second correlation coefficients between the plurality of factor items in the target dataset; acquiring difference correlation coefficients that are differences between the first correlation coefficients and the second correlation coefficients; acquiring indexes respectively for the plurality of factor items based on the difference correlation coefficients; and selecting the biomarker based on the indexes.

Abstract: One embodiment provides a method, including: receiving a sample set for training a machine-learning model, wherein the sample set includes a plurality of classes, wherein classes within the plurality of classes have an imbalance in a number of samples; creating an enlarged minority class by generating new samples from the samples within the minority class and adding the new samples to the minority class; selecting subset samples from both the samples within the enlarged minority class and the majority class; weighting each of the subset samples based upon user input defining goals for attributes of a training sample set to be used in training the machine-learning model; and generating, using the neural network, the training sample set by re-running the selecting in view of the weighting.

Abstract: The present disclosure provides a method of measuring a semiconductor device, including the following operations: obtaining a first image corresponding to a first layer in the semiconductor device; obtaining a second image corresponding to a second layer, below the first layer, in the semiconductor device, wherein the first layer includes at least one first structure and the second layer includes a plurality of second structures that are overlapped by the at least one first structure; generating a third image by combining the first image and the second image; and calculating an offset between the at least one first structure and the plurality of second structures based on the first image and the third image.

Abstract: Methods for compressing shape data for a set of electronic designs include inputting a set of shape data, where the shape data comprises mask designs. A convolutional autoencoder encodes the set of shape data, where the encoding compresses the set of shape data to produce a set of encoded shape data. The convolutional autoencoder is tuned for increased accuracy of the set of encoded shape data based on design rules for the set of shape data. The convolutional autoencoder comprises a set of parameters comprising weights, and the convolutional autoencoder has been trained to determine what information to keep based on the weights.

Abstract: A computer-implemented method of identifying filters for use in determining explainability of a trained neural network. The method comprises obtaining a dataset comprising the input image and an annotation of an input image, the annotation indicating at least one part of the input image which is relevant for inferring classification of the input image, determining an explanation filter set by iteratively: selecting a filter of the plurality of filters; adding the filter to the explanation filter set; computing an explanation heatmap for the input image by resizing and combining an output of each filter in the explanation filter set to obtain the explanation heatmap, the explanation heatmap having a spatial resolution of the input image; and computing a similarity metric by comparing the explanation heatmap to the annotation of the input image; until the similarity metric is greater than or equal to a similarity threshold; and outputting the explanation filter set.

Abstract: Sharpness at each focus position is calculated as an individual sharpness. Thereafter, one or M (where M is a natural number equal to or greater than 2 and smaller than N) corrective sharpness are calculated and image reference values are determined from the individual sharpness. An luminance value is calculated based on the image reference values and the corrective sharpness for each pixel. An all-in-focus image is generated by combining those luminance values.

Abstract: A method is provided. The method may include, in response to electronically receiving a document, automatically classifying the document and different parts of the document, by electronically identifying a document type associated with the document and electronically tagging data associated with the different parts of the document based on classification rules. The method may further include automatically extracting the tagged data associated with the automatically classified document based on data extraction rules. The method may further include detecting first feedback associated with the classification rules and second feedback associated with the data extraction rules. The method may further include automatically generating and updating validation rules based on the identified document type, the detected first feedback, and the detected second feedback to validate the automatically classified document and the automatically tagged and extracted data.

Abstract: Temporal filtering operations may be reset for certain pixels within an image frame to reduce contribution from previous input frames to reduce ghosting and other artifacts. The resetting reduces the contribution to, for example, zero, either immediately or within a predetermined period of time (e.g., a certain number of frames). A decision regarding whether to reset temporal filtering for a pixel of the image frame may be based on a probability assigned to that pixel. The probability can be based on rules with one or more criteria. One example factor for adjusting probability is a confidence level regarding the temporal filtering decision for the pixel, in which the probability for a random reset of a pixel is based on the confidence level regarding the temporal filtering decision for those pixels.

Abstract: An embodiment of the present application provides an optical fingerprint identification apparatus, which includes: at least one non-visible light source, configured to emit non-visible light to a human finger to provide excitation light for fingerprint identification; an optical component, disposed under a fingerprint detecting area of the display screen, and configured to receive signal light scattered and reflected by the human finger; and a fingerprint sensor configured to perform imaging based on the signal light passing through the optical component, where a working wave band of the fingerprint sensor is the same as a light emitting wave band of the non-visible light source, a number of the working wave bands is the same as the number of the light emitting wave bands, and the fingerprint sensor is connected to the non-visible light source, and is configured to control the non-visible light source to actively emit light.

Abstract: The invention relates to a method of determining the sagittal rotation of a patient's pelvis based on a standard anterior posterior X-ray-image with known image parameters and a calibration of the image, for example by using at least one King-Mark calibration object. The angle of the pelvic rotation is determined between a pelvic plane which is orthogonal to the midsagittal plane of the pelvis, and the image plane of the X-ray-image. Assuming the patient's position shown on the X-ray-image represents a standard neutral position, the X-ray-image plane can be used as a functional reference plane for further calculations, for example during hip-replacement surgery. The present invention further relates to a corresponding computer program and system.

Abstract: Disclosed are an apparatus and method for configuring spatial information required to visualize a space represented based on a hierarchical structure having a plurality of levels each of which includes one or more tiles, configuring spatial information. The method includes checking tile visibility of each level according to whether a tile exists in the corresponding level; grouping one or more levels in which tile visibility is consistently maintained into one or more groups; and assigning a tile visibility index to each group.

Abstract: Disclosed herein are system, method, and computer program product embodiments for locating, identifying, and tracking a known criminal, fugitive, missing person, and/or any other person of interest. An embodiment operates by deploying an unmanned aerial vehicle, determining the mode of operation of the UAV, operating the UAV in accordance with the mode of operation of the UAV, determining whether a subject has been detected, capturing a first voice sample associated with the subject, authenticating the identity of the subject, and transmitting the GPS location of the unmanned aerial vehicle to a computing device.