An image filtering arrangement comprising a controller configured to receive an image data file; propose zero or more regions of interest for the image data file; and to select adaptive filtering for at least one of the proposed zero or more regions of interest and apply the selected adaptive filtering to the at least one of the proposed zero or more regions of interest.

A method, apparatus and system for adapting a pre-trained network for application to a different dataset includes arranging at least two different types of active adaptation modules in a pipeline configuration, wherein an output of a previous active adaptation module produces an input for a next active adaptation module in the pipeline in the form of adapted network data until a last active adaptation module, and wherein each of the at least two different types of adaptation modules can be switched on or off, determining at least one respective hyperparameter for each of the at least two different types of active adaptation modules, and applying the at least one respective determined hyperparameter to each of the at least two different types of active adaptation modules for processing received data from the pretrained network to determine an adapted network.

Extracting entities from a document with a hierarchical entity graph of entities. Entity definitions and entity recognition definitions are customized by a user and provided. The configuration information is utilized to generate (905) an entity graph, which is then utilized to parse one or more documents. In some implementations, the resulting parse tree may be utilized, in conjunction with user feedback, to generate one or more training instances for a machine learning model assigned to one or more of the custom nodes as an entity recognition definition. Parsing of the resulting tree may be performed with a lazy parsing methodology, with only the portions of interest to the user being identified in the document.

Systems, devices, and methods for training a neural network and performing image interest point detection and description using the neural network. The neural network may include an interest point detector subnetwork and a descriptor subnetwork. An optical device may include at least one camera for capturing a first image and a second image. A first set of interest points and a first descriptor may be calculated using the neural network based on the first image, and a second set of interest points and a second descriptor may be calculated using the neural network based on the second image. A homography between the first image and the second image may be determined based on the first and second sets of interest points and the first and second descriptors. The optical device may adjust virtual image light being projected onto an eyepiece based on the homography.

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 method for evaluating a minimum breaking distance of a vehicle, in particular a car. The method comprises the step of obtaining at least one image in a movement direction of the vehicle associated substantially with an actual location of vehicle. A first road type indication from the at least one image is determined by a trained neural network architecture. Second road type indication associated with the actual location of the car are obtained from a database and compared with the first road type indication. If the second road type indication supports the determined first road type indication, an adjustment parameter associated with one of the at least first and second road type indication is selected. If second road type indication does not support the determined first road type indication, a default adjustment parameter as adjustment parameter is selected. Finally, a minimum breaking distance using the adjustment parameter is set.

The present disclosure relates generally to methods, systems and computer program products for classifying and identifying input data using neural networks and displaying results (e.g., images of vehicles, vehicle artifacts and geographical locations dating from the 1880s to present day and beyond). The results may be displayed on displays or in virtual environments such as on virtual reality, augmented reality and/or mixed-reality devices.

According to some embodiments, a system and method are provided comprising a vegetation management module to receive image data from an image source; a memory for storing program instructions; a vegetation management processor, coupled to the memory, and in communication with the vegetation module, and operative to execute program instructions to: receive first image data and second image data for an area of interest; overlay the first image data over the second image data to generate an overlaid image; receive feeder attribute data for at least one feeder in the overlaid image; generate a risk score for the at least one feeder based in part on the received feeder attribute data; and generate a visualization based on the at least one feeder and the generated risk score. Numerous other aspects are provided.

Disclosed are methods, apparatuses and systems for CNN network adaption and object online tracking. The CNN network adaption method comprises: transforming a first feature map into a plurality of sub-feature maps, wherein the first feature map is generated by the pre-trained CNN according to a frame of the target video; convolving each of the sub-feature maps with one of a plurality of adaptive convolution kernels, respectively, to output a plurality of second feature maps with improved adaptability; training, frame by frame, the adaptive convolution kernels.

A method (100) for performing event detection on a data stream is disclosed, the data stream comprising data from a plurality of devices connected by a communications network. The method comprises using an autoencoder to concentrate information in the data stream, wherein the autoencoder is configured according to at least one hyperparameter (110) and detecting an event from the concentrated information (120). The method further comprises generating an evaluation of the detected event on the basis of logical compatibility between the detected event and a knowledge base (130), and using a Reinforcement Learning (RL) algorithm to refine the at least one hyperparameter of the autoencoder, wherein a reward function of the RL algorithm is calculated on the basis of the generated evaluation (140). Also disclosed are a system (900) for performing event detection, and a method (1100) and node (1200) for managing an event detection process.