A computer implemented method, performed in a data processing system comprising a performance monitoring unit. The method comprises receiving a set of computer-readable instructions to be executed by the data processing system to implement at least a portion of a neural network, wherein one or more of the instructions is labeled with one or more performance monitoring labels based upon one or more features of the neural network. The method further comprises configuring the performance monitoring unit to count one or more events occurring in one or more components of the data processing system based on the one or more performance monitoring labels.

An exemplary embodiment of the present disclosure discloses a method of setting a model threshold value for detecting an anomaly of a facility monitoring system, the method including: acquiring sensor data output from each sensor; extracting a feature value for the sensor data of each sensor; acquiring output data by inputting input data including the extracted feature value to a trained neural network model; and comparing the input data and the output data and setting a threshold value for detecting an anomaly based on a calculated comparison result value.

An approach is provided for traffic estimation/detection based on anomaly detection. The approach involves, for instance, retrieving probe data or other sensor data collected from sensors of devices traveling in a geographic area. The approach also involves aggregating the probe or sensor data into a sequence of frames. Each frame comprises a plurality of spatial cells representing the geographic area at a respective time interval. The approach further involves computing a similarity of the sequence to one or more historical sequences comprising historical frames of spatially and temporally binned historical probe data. The approach further involves determining a classification of a traffic state associated with the probe or sensor data as either a normal traffic state or as a traffic anomaly based on the similarity. By way of example, the traffic state of the probe data can then be estimated/predicted based on the classification.

In one embodiment, an apparatus comprises a storage device and a processor. The storage device stores a plurality of images captured by a camera. The processor: accesses visual data associated with an image captured by the camera; determines a tile size parameter for partitioning the visual data into a plurality of tiles; partitions the visual data into the plurality of tiles based on the tile size parameter, wherein the plurality of tiles corresponds to a plurality of regions within the image; compresses the plurality of tiles into a plurality of compressed tiles, wherein each tile is compressed independently; generates a tile-based representation of the image, wherein the tile-based representation comprises an array of the plurality of compressed tiles; and stores the tile-based representation of the image on the storage device.

Embodiments generally relate to systems, methods, and processes that may use touch-free document reading at self-service interaction stations. Some embodiments relate to a self service station for conducting a passenger interaction process in transit environment, including, a display screen to display a visual prompt to present a travel document in a field of view of a video image recording device as part of the passenger interaction process, and configured to determine from the received live video images a document face image present on the travel document, to determine from the received live video images a machine-readable zone (MRZ) of the travel document and store a captured MRZ image of the MRZ, to process the captured MRZ image to determine identification information on the travel document, and store the document face image and the identification information for use in the passenger interaction process.

A computer-implemented method for learning an autoencoder notably is provided. The method includes obtaining a dataset of images. Each image includes a respective object representation. The method also includes learning the autoencoder based on the dataset. The learning includes minimization of a reconstruction loss. The reconstruction loss includes a term that penalizes a distance for each respective image. The penalized distance is between the result of applying the autoencoder to the respective image and the set of results of applying at least part of a group of transformations to the object representation of the respective image. Such a method provides an improved solution to learn an autoencoder.

Systems and methods for image modification to increase contrast between text and non-text pixels within the image. In one embodiment, an original document image is scaled to a predetermined size for processing by a convolutional neural network. The convolutional neural network identifies a probability that each pixel in the scaled is text and generates a heat map of these probabilities. The heat map is then scaled back to the size of the original document image, and the probabilities in the heat map are used to adjust the intensities of the text and non-text pixels. For positive text, intensities of text pixels are reduced and intensities of non-text pixels are increased in order to increase the contrast of the text against the background of the image. Optical character recognition may then be performed on the contrast-adjusted image.

In various examples, sensor data may be received that represents a field of view of a sensor of a vehicle located in a physical environment. The sensor data may be applied to a machine learning model that computes both a set of boundary points that correspond to a boundary dividing drivable free-space from non-drivable space in the physical environment and class labels for boundary points of the set of boundary points that correspond to the boundary. Locations within the physical environment may be determined from the set of boundary points represented by the sensor data, and the vehicle may be controlled through the physical environment within the drivable free-space using the locations and the class labels.

A computer-implemented method includes accessing an activation state of an energy-based surgical instrument, accessing at least one image of tissue, accessing control parameter values of a generator configured to provide energy to the energy-based surgical instrument, storing the control parameter values, receiving input information, annotating the stored control parameter values and the at least one image based on the received information, and tagging the annotated control parameter values and the annotated at least one image.

In some embodiments, there is provided a system for generating synthetic human fingerprints. The system includes at least one processor and at least one memory storing instructions which when executed by the at least one processor causes operations, such as receiving, from a database and/or a sensor, at least one real fingerprint; training, based on the at least one real fingerprint, a generative adversarial network to learn a distribution of real fingerprints; training a super-resolution engine to learn to transform low resolution synthetic fingerprints to high-resolution fingerprints; providing to the trained super resolution engine at least one low resolution synthetic fingerprint that is generated as an output by the trained generative adversarial network; and in response to the providing, outputting, by trained super resolution engine, at least one high resolution synthetic fingerprint.