Abstract: To accurately recognize observed objects. An observed-object recognition system includes an observation region estimation portion, an existence region estimation portion, and an object recognition portion. The observation region estimation portion estimates an observation region that is relatively highly likely to be an observation point in at least one first-person image in a first-person video (a video based on the first-person perspective). Based on the observation region, the existence region estimation portion estimates an existence region that belongs to the first-person image and causes an observed object to exist. The object recognition portion recognizes an object in the estimated existence region of the first-person image.

Abstract: A method of recognizing gestures of a person from at least one image from a monocular camera, e.g. a vehicle camera, includes comp the steps: a) detecting key points of the person in the at least one image, b) connecting the key points to form a skeleton-like representation of body parts of the person, wherein the skeleton-like representation represents a relative position and a relative orientation of the respective body parts of the person, c) recognizing a gesture of the person from the skeleton-like representation of the person, and d) outputting a signal indicating the gesture.

Abstract: A computing device accesses video data displaying one or more traffic entities and generates a plurality of sequences from the video data. For each sequence, the computing device identifies a plurality of stimuli in the sequence and applies a machine learning model to generate an output describing the traffic entity. The computing device generates a data structure for storing, for each sequence, information describing the sequence and linking frame indexes of stimuli from the sequence to outputs of the machine learning model. The computing device stores the data structure in association with the video data. Responsive to receiving a selection of a sequence, the computing device loads video data for the sequence. Responsive to receiving a selection of a traffic entity within the video data, the computing device generates a graphical display element including the machine learning model output for the selected traffic entity.

Abstract: Provided is a method for determining a physical shape having a predefined physical target property that includes calculating a sensitivity landscape on the basis of a shape data record for the physical shape with the aid of a calculation device. The calculation device is a machine-taught artificial intelligence device. The shape data record identifies locations at or on the physical shape. For a plurality of these locations, the sensitivity landscape respectively indicates how the target property of the physical shape changes if the physical shape changes in the region of the location. Furthermore, the shape data record for the physical shape to be determined is changed on the basis of the sensitivity landscape in such a manner that the predefined physical target property is improved.

Abstract: A method for tracking a lane on a road is presented. The method comprises receiving, by one or more processors from an imaging system, a set of pixels associated with lane markings. The method further includes generating, by the one or more processors, a predicted spline comprising (i) a first spline and (ii) a predicted extension of the first spline in a direction in which the imaging system is moving. The first spline describes a boundary of a lane and is generated based on the set of pixels. The predicted extension of the first spline is generated based at least in part on a curvature of at least a portion of the first spline.

Abstract: A method of analyzing film on a substrate comprises receiving surface profile data obtained from measurements of a plurality of discrete regions on a substrate, the plurality of discrete regions comprising one or more film layers; extracting a plurality of parameters from the received surface profile data, the plurality of parameters comprising one or more parameters of the one or more film layers of each of the plurality of discrete regions, wherein the extracting is based on a predetermined pattern for the plurality of the discrete regions on the substrate; and displaying a user interface.

Abstract: The current document is directed to methods and systems that effectively and efficiently employ incomplete training data to train machine-learning-based systems. Incomplete training data, as one example, may include training data with erroneous or inaccurate input-vector/label pairs. In currently disclosed methods and systems, Incomplete training data is mapped to loss classes based on addition training-data information and specific, different additional-information-dependent loss-generation methods are employed for training data of different loss classes during machine-learning-based-system training so that incomplete training data can be effectively and efficiently used.

Abstract: A system and method for providing an interpretable and unified representation for trajectory prediction that includes receiving birds-eye image data associated with travel of at least one agent within a roadway environment. The system and method also include analyzing the birds-eye image data to determine a potential field associated with the roadway environment and analyzing the birds-eye image data to determine a potential field associated with a past trajectory of the at least one agent. The system and method further include predicting a future trajectory of the at least one agent based on analysis of the potential fields.

Abstract: An electronic device includes a graphic processor and a memory device. The graphic processor includes an artificial neural network engine that makes an object recognition model learn by using learning data and weights to provide a learned object recognition model. The memory device divides a feature vector into a first sub feature vector and a second feature vector, and performs a first calculation to apply the second sub feature vector and the weights to the learned object recognition model to provide a second object recognition result. The artificial neural network engine performs a second calculation to apply the first sub feature vector and the weights to the learned object recognition model to provide a first object recognition result and provides the first object recognition result to the memory device. The second calculation is performed in parallel with the first calculation.

Abstract: A method and system for checking data gathering conditions or image capturing conditions associated with images during AI based visual-inspection process. The method comprises generating a first representative (FR1) image for a first group of images and a second representative image (FR2) for a second group of images. A difference image data is generated between FR1 image and the FR2 image based on calculating difference between luminance values of pixels with same coordinate values. Thereafter, one or more of a plurality of white pixels or intensity-values are determined within the difference image based on acquiring difference image data formed of luminance difference-values of pixels. An index representing difference of data-capturing conditions across the FR1 image and the FR2 image is determined, said index having been determined at least based on the plurality of white pixels or intensity-values, for example, based on application of a plurality of AI or ML techniques.

Abstract: Embodiments disclosed herein include, but are not limited to, methods for capturing video sampling data comprising a plurality of video images of a moving object, for example using one or more cameras positioned on a stationary frame of reference adjacent to the mechanical component under investigation, in which a change in motion of the moving object is correlated to an origin frame obtained from the sampling data and representing a point at which the change in motion first occurs.

Abstract: An authentication system according to one aspect of the present disclosure includes: at least one memory storing a set of instructions; and at least one processor configured to execute the set of instructions to: track an object included in a video captured by a first capture device; detect a candidate for biometric authentication in the object being tracked; determine whether biometric authentication has been performed for the candidate based on a record of biometric authentication performed for the object being tracked; and perform the biometric authentication for the candidate based on a video of an authentication part of the candidate when the biometric authentication has not been performed for the candidate, the video of the authentication part being captured by a second capture device having a capture range including a part of a capture range of the first capture device.

Abstract: Disclosed are systems and methods for full body measurements extraction using a mobile device camera.

Abstract: Provided is a reward function generation method for calculating a reward in reinforcement learning, the method being executed by a computer, and the method includes accepting input of an instruction to generate a reward function including a plurality of setting data that is information regarding a key performance indicator, generating one partial reward function for one of the setting data, generating a linear combination of a plurality of the partial reward functions as the reward function, and outputting information regarding the reward function generated to the computer that executes the reinforcement learning, by the computer.

Abstract: The disclosure is generally directed to systems and methods for sharing a video feed of a camera among multiple image processing components in a vehicle. A first priority may be applied to a first image processing component that performs a first image processing function. A second priority that is lower than the first priority, is applied to a second image processing component that performs a second image processing function. The first function may be deemed more important than the second function due to various reasons. Consequently, the first image processing component is offered priority to apply a first set of camera settings on the camera. The second image processing component may prefer to apply a different set of camera settings for executing the second image processing function. An access arbitrator allows the second image processing component to do so when the first image processing component relinquishes control of the camera.

Abstract: Disclosed herein is a system and method for characterizing adventitial tissue. In one aspect, a system and method are disclosed that characterizes tissue types within the adventitial tissue including nerve bundles and blood vessels. In a further aspect, the adventitia is imaged and characterized to provide guidance for crossing lesions within an occluded vessel.

Abstract: Motion of actors within a scene may be detected based on imaging data, using machine learning tools operating on cameras that captured the imaging data. The machine learning tools process images to perform a number of tasks, including detecting heads of actors, and sets of pixels corresponding to the actors, before constructing line segments from the heads of the actors to floor surfaces on which the actors stand or walk. The line segments are aligned along lines extending from locations of heads within an image to a vanishing point of a camera that captured the image. Trajectories of actors and visual data are transferred from the cameras to a central server, which links trajectories captured by multiple cameras and locates detected actors throughout the scene, even when the actors are not detected within a field of view of at least one camera.

Abstract: Methods of identifying a hot spot from a design layout or of predicting whether a pattern in a design layout is defective, using a machine learning model. An example method disclosed herein includes obtaining sets of one or more characteristics of performance of hot spots, respectively, under a plurality of process conditions, respectively, in a device manufacturing process; determining, for each of the process conditions, for each of the hot spots, based on the one or more characteristics under that process condition, whether that hot spot is defective; obtaining a characteristic of each of the process conditions; obtaining a characteristic of each of the hot spots; and training a machine learning model using a training set including the characteristic of one of the process conditions, the characteristic of one of the hot spots, and whether that hot spot is defective under that process condition.

Abstract: A hybrid approach for using reference frames is presented in which a series of anchor frames is used, effectively resetting a global frame upon a trigger event. With each new anchor frame, parameter values for lane boundary estimates (known as lane boundary states) can be recalculated with respect to the new anchor frame. Triggering events may a based on a length of time, distance traveled, and/or an uncertainty value.

Abstract: A convolutional neural network is used to generate hash strings corresponding to object instances. The characteristic hash strings are used to recognize the same object instance depicted in images generated at different times and by different camera devices.