Abstract: Embodiments provide improved techniques for identifying object and vehicle locations on an HD map using camera images. Synthetic data may be generated by populating a high-definition (HD) map with an object. The populated HD map can be projected to a two-dimensional camera view image depicting the object. The HD map and object detection data generated from image (e.g., identifying lane/object locations within the image) can be used to train the model to identify HD map locations of an autonomous vehicle capturing images as it travels, as well as various objects detected from those captured images. Subsequently, a new image may be processed using object detection techniques to detect lane/object locations within the image. An HD map and the detected lane/object data may be provided to the model, which in turn identifies, on the HD map, the locations of the vehicle and the various objects.

Abstract: An ultrasound diagnostic apparatus 1 includes a bladder pattern storage unit 22, a reference pattern setting unit 21, a bladder extraction unit 18 that extracts a bladder region from an ultrasound image, a bladder extraction success/failure determination unit 19 that determines whether the bladder region represents a bladder having the reference pattern, and an image quality adjustment unit 20 that adjusts the image quality of the ultrasound image in a case where determination is made that the bladder region does not represent the bladder having the reference pattern, in which in a case where the determination is made that the bladder region does not represent the bladder having the reference pattern even in an ultrasound image of which the image quality is adjusted, the bladder extraction success/failure determination unit 19 determines whether the bladder region represents the bladder having the abnormal bladder pattern.

Abstract: Computer-implemented methods, computer-readable storage media storing instructions and computer systems for labeling significant locations based on contextual data can be implemented to perform operations that include determining a location of a computing device, and determining a label for the determined location based on contextual data associated with the significant location. The location can be a significant location that has meaning to a user of the device.

Abstract: A first tone curve referred to in generating an image recognition processing signal as an image output signal for image recognition processing and a second tone curve referred to in generating a visual recognition signal as an image output signal for visual recognition are separately generated. The second tone curve for visual recognition is generated by connecting a dark control point, which is a control point specified in a luminance-pixel value coordinate system corresponding to the lowest luminance portion in a luminance histogram, a light control point, which is a control point specified in the luminance-pixel value coordinate system corresponding to the highest luminance portion in the luminance histogram, and an intermediate control point, which is a control point specified in the luminance-pixel value coordinate system corresponding to an intermediate luminance portion in the luminance histogram.

Abstract: An image acquisition section of an information processing apparatus acquires, from an imaging apparatus, polarization images in a plurality of orientations. A normal acquisition section of an image analysis section detects a surface of a subject by acquiring a normal vector on the basis of orientation dependence of polarization luminance. A surface assumption section assumes the presence of an undetected surface continuing from the detected surface. A subject detection section confirms whether or not the assumed surface is present using a normal vector estimated for the assumed surface. An output data generation section generates and outputs output data using information regarding the detected surface.

Abstract: There is a growing problem in correctional facilities in which contraband devices may be smuggled into a correctional facility. These devices are not subject to the typical monitoring and control provided by the inmate communication system provided by the correctional facility, and thus pose a significant security risk. The present disclosure provides details of a system and method that leverages the sanctioned mobile devices and the wireless infrastructure of the inmate communication system to scan for and triangulate the location of contraband devices. The mobile and wireless infrastructure devices scan for transmissions indicative of a contraband device and send alerts to each other and to a central monitoring system. The central monitoring system then leverages multiple alerts to determine a location of the contraband device using multiple triangulation techniques. The triangulation may also be performed by the mobile devices themselves.

Abstract: A method for identifying individual objects and their number and respective locations in a sealed case creates a detection model by using standard data as a training set. Image of the sealed case is captured and divided into a specified number of detection regions. Images of first detection regions in the detection image as taken as local images and input into the detection model. The numbers and locations of target objects in the sealed case is obtained based on a statistic result outputted by the detection model. The standard data includes sample images of the sealed case with different numbers and respective locations of the target objects in the case. A capacity of the sealed case is M, and a number of the sample image is less than 2M. A target identification apparatus and a storage medium applying the method are also disclosed.

Abstract: Computer-implemented methods, computer-readable storage media storing instructions and computer systems for labeling significant locations based on contextual data can be implemented to perform operations that include determining a location of a computing device, and determining a label for the determined location based on contextual data associated with the significant location. The location can be a significant location that has meaning to a user of the device.

Abstract: System and method of deploying a trained machine learning neural network (MLNN) in generating a fall injury condition of a subject. The method comprises receiving, at input layers of the trained MLNN, millimeter wave (mmWave) radar point cloud data representing fall attributes from monitoring the subject via mmWave radar sensing device, the input layers associated with the fall attributes, receiving, at a second set of input layers, personal attributes of the subject associated with ones of the second set of input layers, the first and second sets of input layers interconnected with an output layer of the trained MLNN via intermediate layers, the trained MLNN produced by establishing a correlation between an injury condition of prior subjects and mmWave point cloud data and personal attributes associated with the prior subjects, and generating, at the output layer, the fall injury condition attributable to the subject.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network using contrastive learning. One of the methods includes obtaining a network input representing an environment; processing the network input using a first subnetwork of the neural network to generate a respective embedding for each location in the environment; processing the embeddings for each location in the environment using a second subnetwork of the neural network to generate a respective object prediction for each location; determining, for each of a plurality of pairs of the plurality of locations in the environment, whether the respective object predictions of the pair of locations characterize the same possible object or different possible objects; computing a respective contrastive loss value for each of the plurality of pairs of locations; and updating values for a plurality of parameters of the first subnetwork using the computed contrastive loss values.

Abstract: System, methods, and embodiments described herein relate to predicting a future state of an object detected in a vicinity of a vehicle. In one embodiment, a method for predicting a state of an object includes detecting, at a plurality of discrete times [t, t?1, t?2, . . . ], a respective plurality of states of the object, obtaining, based at least in part on a present location of the vehicle, supplemental information, associated with an environment of the present location, that indicates at least a speed reduction factor, executing a prediction operation to determine a predicted state of the object at a time t+1 based at least in part on the detected plurality of states and the supplemental information, determining an actual state of the object at a time t+1 based on data from the one or more sensors, and modifying the prediction operation based at least in part on the actual state.

Abstract: A neural network can be configured to produce an electronic road map. The electronic road map can have information to distinguish lanes of a road. A feature in an image can be detected. The image can have been produced at a current time. The image can be of the road. The feature in the image can be determined to correspond to a feature, of a plurality of features, in a feature map. The feature map can have been produced at a prior time from one or more images. A labeled training map can be produced from the feature in the image and the plurality of features in the feature map. The labeled training map can have the information to distinguish the lanes of the road. The neural network can be trained to produce, in response to a receipt of the image and the feature map, the labeled training map.

Abstract: Methods and apparatus for predicting performance of an individual on a task, the method comprises receiving brain imaging data for the individual, wherein the brain imaging data comprises structural brain data, determining values for at least one characteristic of the structural brain data within regions of interest defined for a population of individuals having different performance levels, and predicting based on the determined values, a performance potential of the individual.

Abstract: Provided is a face recognition method comprising acquiring a masked face image including a masked region and an un-masked region; obtaining an image feature from the masked face image; inputting the image feature to a pre-trained segmentation model to automatically estimate a feature of the masked region; and refining the image feature using the estimated feature of the masked region, wherein the refining step comprising focusing on a feature of the un-masked region and discarding the estimated feature of the masked region.

Abstract: In some examples, a processor may receive images from a camera mounted on a vehicle. The processor may generate a disparity image based on features in at least one of the images. In addition, the processor may determine at least one region in a first image of the received images that has a brightness that exceeds a brightness threshold. Further, the processor may determine at least one region in the disparity image having a level of disparity information below a disparity information threshold. The processor may determine a region of light interference based on an overlap between at least one region in the first image and at least one region in the disparity image, and may perform at least one action based on the region of light interference.

Abstract: Described is a system for onboard, real-time, activity detection and classification. During operation, the system detects one or more objects in a scene using a mobile platform and tracks each of the objects as the objects move in the scene to generate tracks for each object. The tracks are transformed using a fuzzy-logic based mapping to semantics that define group activities of the one or more objects in the scene. Finally, a state machine is used to determine whether the defined group activities are normal or abnormal phases of a predetermined group operation.

Abstract: A computer-implemented image analysis method and system. The method comprises: quantifying one or more features segmented and identified from a medical image of a subject; extracting clinically relevant features from non-image data pertaining to the subject; assessing the features segmented from the medical image and the features extracted from the non-image data with a trained machine learning model; and outputting one or more results of the assessing of the features.

Abstract: A method for monitoring a person performing a physical exercise based on a sequence of image frames showing an exercise activity of the person.

Abstract: Systems, devices, and methods are described for providing patient anatomy models with indications of model accuracy included with the model. Accuracy is determined, for example, by analyzing gradients at tissue boundaries or by analyzing tissue surface curvature in a three-dimensional anatomy model. The determined accuracy is graphically provided to an operator along with the patient model. The overlaid accuracy indications facilitate the operator's understanding of the model, for example by showing areas of the model that may deviate from the modeled patient's actual anatomy.

Abstract: Systems and methods for determining user equipment (UE) locations within a wireless network using reference signals of the wireless network are described. The disclosed systems and methods utilize a plurality of in-phase and quadrature (I/Q) samples generated from signals provided by receive channels associated with two or more antennas of the wireless system. Based on received reference signal parameters the reference signal within the signals from each receive channel among the receive channels is identified. Based on the identified reference signal from each receive channel, an angle of arrival between a baseline of the two or more antennas and incident energy from the UE to the two or more antennas is determined. That angle of arrival is then used to calculate the location of the UE. The angle of arrival may be a horizontal angle of arrival and/or a vertical angle of arrival.