Abstract: Generally discussed herein are examples of gesture-based extended reality (XR) with object recognition and tracking. A method, implemented by an extended reality (XR) device can include recognizing and tracking one or more objects in the image data, recognizing a gesture in the image data, analyzing the image data to determine whether a condition is satisfied, the condition indicating a recognized and tracked object of the one or more objects proximate which the recognized gesture is to be made, and in response to determining that the condition is satisfied, performing an augmentation of the image data based on satisfaction of the condition.

Abstract: Systems and techniques are provided to identify, analyze, and evaluate key events and mechanical variables in videos of human motion related to an action, such as may be used in training for various sports and other activities. Information about the action is calculated based on analysis of the video such as via keypoint identification, pose identification and/or estimation, and related calculations, and provided automatically to the user to allow for improvement of the action.

Abstract: The present application discloses an image generation method, a neural network compression method, and a related apparatus and device in the field of artificial intelligence. The image generation method includes: inputting a first matrix into an initial image generator to obtain a generated image; inputting the generated image into a preset discriminator to obtain a determining result, where the preset discriminator is obtained through training based on a real image and a category corresponding to the real image; updating the initial image generator based on the determining result to obtain a target image generator; and further inputting a second matrix into the target image generator to obtain a sample image. Further, a neural network compression method is disclosed, to compress the preset discriminator based on the sample image obtained by using the foregoing image generation method.

Abstract: According to one embodiment, a method, computer system, and computer program product for identifying one or more intrinsic physical properties of one or more objects is provided. The present invention may include identifying one or more objects in a video set, extracting observable physical properties of the identified one or more objects from the video set, including one or more trajectories, and inferring, by a property-based graph neural network, intrinsic properties of the one or more objects based on the trajectories.

Abstract: The present disclosure relates to a system to proactively detect in real time one or more threats in crowded areas. The present disclosure presents a proactive system for real-time threat detection in crowded areas. Utilizing a network of imaging sensors and advanced machine learning algorithms, the system identifies suspicious individuals, objects, and behavioral patterns within a predefined area. The system detects potential threats such as individuals on watch lists, suspicious objects like unattended bags, and abnormal behaviors indicative of security risks, by continuously monitoring and analyzing images and video feeds. Upon detection, the system promptly notifies authorities, providing detailed information on threat location, suspected individuals, and behavioral analysis. Privacy-preserving measures, including encryption of facial recognition data, ensure compliance with privacy regulations.

Abstract: Various embodiments contemplate systems, architectures and methods for extracting and selecting headshots of human or non-human entities from catalogs of images of such subjects. The methods described may find and extract faces from within groups of subjects, verify that the extracted faces correspond to the desired subject, determine cropping or masking regions, or both, of rectangular, circular, elliptical or some other geometry to provide an easily recognized image of the desired subject, expand the output image by synthesizing pixels as may be needed for a desired cropping or masking region, select preferred images among a collection of images of the desired subject, and perform other useful functions. The resulting output images may be in either direct form, reference form or both forms.

Abstract: A method for computing dimensions of an object in a scene includes: controlling, by a processor, a depth camera system to capture at least a frame of the scene, the frame including a color image and a depth image arranged in a plurality of pixels; detecting, by the processor, an object in the frame; determining, by the processor, a ground plane in the frame, the object resting on the ground plane; computing, by the processor, a rectangular outline bounding a projection of a plurality of pixels of the object onto the ground plane; computing, by the processor, a height of the object above the ground plane; and outputting, by the processor, computed dimensions of the object in accordance with a length and a width of the rectangular outline and the height.

Abstract: Disclosed in the present invention is a method for whole-time space-air-ground integrated hyperspectral stereoscopic remote sensing, tracing and prediction of greenhouse/pollution gas, comprising: performing remote sensing of multi-source heterogeneous data: utilizing a hyperspectral stereoscopic remote sensing device, a hyperspectral imaging device, a hyperspectral unmanned aerial vehicle remote sensing device, a hyperspectral greenhouse gas remote sensing device based on grating light splitting and a night hyperspectral stereoscopic remote sensing device to perform the remote sensing of the multi-source heterogeneous greenhouse/pollution gas data; performing tracing and early warning of greenhouse/pollution gas components: progressively realizing tracing of greenhouse/pollution gas components at different locations based on the multi-source heterogeneous greenhouse/pollution gas data, and performing emission early warning according to a traced result; and performing stereo fusion and prediction of the multi

Abstract: A method for evaluating a gastrointestinal tract may include characterizing one or more disease parameters using objective measures obtained from imaging data of a gastrointestinal tract. The one or more disease parameters reflect a measure of at least one of lesions, ulcers, bleeding, stenosis, and vasculature. The method may also include using the one or more characterized disease parameters to classify a disease state.

Abstract: An apparatus, method, and computer program product for the improved development of training data sets for use in connection with machine learning models capable of operating on natural language data records and other unstructured data in a network environment. Some example implementations provide for the generation and presentation of record images in a user interface that allows captures user actions reflecting higher-order data analysis and discernment for incorporation into training protocols used for machine learning models.

Abstract: A detection method according to the present embodiment comprises the steps of (a) photographing a first reference color area indicated by a first reference color, a second reference color area indicated by a second reference color, and a detection region reacting with a target so as to change color, (b) converting a photography result into a single element, (c) extracting a single element gradation value from the converted photography result, (d) converting the extracted single element gradation value into a standard gradation value, and (e) detecting the concentration of the target from the standard gradation value.

Abstract: Methods, systems, and devices for wireless communications are described. In some wireless communications systems, a user equipment (UE) may support communications with a set of transmission/reception points (TRPs). The UE may receive one or more signals from at least one TRP of the set of TRPs. The one or more signals may indicate a condition corresponding to the UE for the multi-TRP communications. The UE may determine the condition of the UE based on the one or more signals. The UE may communicate with one or more TRPs of the set of TRPs based on the one or more signals. For example, the UE may communicate with the one or more TRPs according to a multi-TRP communications configuration determined based on the condition of the UE.

Abstract: The method, system, and non-transitory computer-readable medium embodiments described herein are directed to verifying documents. In various embodiments, a server may receive a first image of a front-side of a document. The server may extract a first feature of the front-side of the document from the first image and identify a first environmental feature from the first image. The server may receive a second image of a backside of the document and identify a second feature of the backside of the document from the second image. The server may also identify a second environmental feature from the second image. The server may verify the document by confirming that the first feature matches the second feature and the first environmental feature matches the second environmental feature.

Abstract: Within many applications impulse radio based ultra-wideband (IR-UWB) transmission offers significant benefits for very short range high data rate communications when compared with existing standards and protocols. In many of these applications the main design goals are very low power consumption and very low complexity design for easy integration and cost reduction. Digitally programmable IR-UWB transmitters using an on-off keying modulation scheme on a 0.13 microns CMOS process operating on 1.2V supply and yielding power consumption as low as 0.9 mW at a 10 Mbps data rate with dynamic power control are enabled. The IR-UWB transmitters support new frequency hopping techniques providing more efficient spectrum usage and dynamic allocation of the spectrum when transmitting in highly congested frequency bands. Biphasic scrambling is also introduced for spectral line reduction.

Abstract: An access control system for enabling access of an attendant to a customer account on a cloud application hosted on a cloud computing system includes a vision sensor coupled with the cloud computing system. The cloud computing system stores customer accounts, an access factorization rule, location-based endpoints, and a supervisor identifier. The system determines that the customer and attendant are at a first endpoint and determines a particular interaction between the attendant and the customer, then factorizes an access indicator and either permits access or denies access of the attendant to the customer account, and may form and send a message comprising a denial of access semantic to the supervisor.

Abstract: A viewpoint optimization system identifies a condition associated with an operating session during which a computer-assisted operation system performs a plurality of operations with respect to a body while an imaging device included within the computer-assisted operation system provides, for display on a display device during the operating session, imagery of the body from a first viewpoint. The viewpoint optimization system defines, based on the identified condition, a second viewpoint for the imaging device that is more optimal than the first viewpoint for an operation included in the plurality of operations. Additionally, the viewpoint optimization system directs the display device to display an indication of the second viewpoint. Corresponding systems and methods are also disclosed.

Abstract: Within many applications impulse radio based ultra-wideband (IR-UWB) transmission offers significant benefits for very short range high data rate communications when compared with existing standards and protocols. In many of these applications the main design goals are very low power consumption and very low complexity design for easy integration and cost reduction. Digitally programmable IR-UWB transmitters using an on-off keying modulation scheme on a 0.13 microns CMOS process operating on 1.2 V supply and yielding power consumption as low as 0.9 mW at a 10 Mbps data rate with dynamic power control are enabled. The IR-UWB transmitters support new frequency hopping techniques providing more efficient spectrum usage and dynamic allocation of the spectrum when transmitting in highly congested frequency bands. Biphasic scrambling is also introduced for spectral line reduction.

Abstract: Each of a first server installed inside a medical institution and a second server installed on a network outside the medical institution includes a server program that receives a processing request for a medical image and that outputs a processing result by executing image processing corresponding to the processing request. An image processing distributor calculates a processing waiting time required until the processing result is obtained in a case where each server executes the image processing on the medical image, based on a required time required for executing the image processing on the medical image, a network connecting situation, and the number of processing requests in a processing waiting state inside each server, and transmits the processing request for the medical image to a server having a shorter processing waiting time.

Abstract: Disclosed is a computer-implemented method of segmenting a medical patient image using an atlas and relating the segmentation result to a model of possible geometric changes to the segmentation result (e.g. for correcting the position of the segmentation of anatomical structures) which consider for example anatomical limitations. The thus-related segmentation result may be used as a basis for changing and/or correcting the position, shape and/or orientation of at least parts of the segmentation result, e.g. by user interaction. The invention also relates to an atlas data set comprising information such as values of the variables of the model of possible geometric changes in relation to the positions of anatomical structures in the atlas.

Abstract: Object parts (20, 21, 22, 23, 24) are detected in a picture using object detector(s) (3) and part location representations (40, 42, 43, 44) are generated for the detected object parts (20, 22, 23, 24). The size of an object (10) comprising object parts (20, 21, 22, 23, 24) is estimated based on a geometric model and the part location representations (40, 42, 43, 44). Search locations (51) in the picture for a search window (52) having a size based on the estimated size are determined based on the part location representations (40, 42, 43, 44). The search locations (51) are then processed by identifying any detected object part (20, 22, 23) that is within the search window (52) positioned at the search location (51). A homography is estimated by minimizing an error between mapped object part(s) from the geometric model and the identified detected object part(s) (20, 22, 23). If the error is smaller than a threshold value, an object location representation is determined for the object (10).