A hyperspectral stereoscopic CubeSat with computer vision and artificial intelligence capabilities consists of a device and a data processing methodology. The device comprises a number of VIS-NIR-TIR hyperspectral sensors, a central processor with memory, a supervisor system running independently of the imager system, radios, a solar panel and battery system, and an active attitude control system. The device is launched into low earth orbit to capture, process, and transmit stereoscopic hyperspectral imagery in the visible and infrared portions of the electromagnetic spectrum. The processing methodology therein comprises computer vision and convolutional neural network algorithms to perform spectral feature identification and data transformations.

Techniques are disclosed for using a trained machine learning (ML) pipeline to identify categories associated with target data items even though the identified categories may not already be present in the hierarchy. The ML pipeline may include trained cluster-based and classification-based machine learning models, among others. If the results of the cluster-based and classification-based machine learning models are the same, then the target data items is assigned to a hierarchical classification consistent with the identical results of the machine learning model. An assigned hierarchical classification may be validated by the operation of subsequent trained ML models that determine whether parent and child categories in the identified classification are properly associated with one another.

In a target image generated by multi-resolution processing, a pixel of interest and a group of reference pixels are designated. In a corresponding image belonging to a level that is one level above, pixel value patterns are compared between a corresponding region of interest and corresponding reference regions so as to calculate weights. A modified pixel-of-interest value is determined by means of multiplying the reference pixel values by the weights.

A system includes a user device and a computing system. The user device accesses a plurality of images captured by a camera and identifies, from the plurality of images, a particular image that depicts a portion of a user interaction object. The user device transmits the particular image across a wireless communications network. The computing system accesses the particular image depicting the portion of the user interaction object and determines a data item from the particular image. The computing system compares the data item to one or more accounts of the user and sends instructions to the user device to automatically display an alert message on the electronic display based on the comparison of the data item to the one or more accounts.

An Automated Teller Machine (ATM) for detecting security vulnerabilities by removing noise artifacts from documents receives a transaction request when a document is inserted into the ATM, where the document contains a noise artifact at least partially obstructing a portion of the document. The ATM generates an image of the document, where the image displays at least one data item comprising a sender's name, a receiver's name, and a number representing an amount. The ATM determines whether the noise artifact obstructs at least partially one data item. In response to determining that the noise artifact obstructs at least partially one data item, the ATM generates a test clean image of the document by removing the noise artifact from the image. In response to determining that the noise artifact is removed, the ATM approves the transaction request.

Implementations are described herein for localizing individual plants by aligning high-elevation images using invariant anchor points while disregarding variant feature points, such as deformable plants. High-elevation images that capture the plurality of plants at a resolution at which wind-triggered deformation of individual plants is perceptible between the high-elevation images may be obtained. First regions of the high-elevation images that depict the plurality of plants may be classified as variant features that are unusable as invariant anchor points. Second regions of the high-elevation images that are disjoint from the first set of regions may be classified as invariant anchor points. The high-elevation images may be aligned based on invariant anchor point(s) that are common among at least some of the high-elevation images. Based on the aligned high-elevation images, individual plant(s) may be localized within one of the high-elevation images for performance of one or more agricultural tasks.

Systems, methods, and computer-readable media for providing a localization processing service for enabling localization of a navigation network-restricted subsystem are provided.

In accordance with one or more embodiments herein, a system for creating a decision support material indicating damage to at least a part of an anatomical joint of a patient, wherein the created decision support material comprises one or more damage images, is provided. The system comprises a storage media and at least one processor, wherein the at least one processor is configured to i) receive a series of radiology images of the at least part of the anatomical joint from the storage media; ii) obtain a three-dimensional image representation of the at least part of the anatomical joint which is based on at least a part of said series of radiology images, by generating said three-dimensional image representation in an image segmentation process based on said series of radiology images, or receiving said three-dimensional image representation from a storage media; iii) identify tissue parts of the anatomical joint in at least one of at least a part of said series of radiology images and/or the three-dimensional image representation using image analysis; iv) determine damage to the identified tissue parts in the anatomical joint by analyzing at least one of at least a part of said series of radiology images and/or the three-dimensional image representation of the at least part of the anatomical joint; v) determine suitable sizes and suitable implanting positions for one or more graft plugs based on the determined damage; vi) mark damage to the anatomical joint and suitable sizes and implanting positions for the one or more graft plugs in the obtained three-dimensional image representation of the anatomical joint; and vii) generate a decision support material, where the determined damage to the at least part of the anatomical joint and the suitable sizes and implanting positions for the one or more graft plugs are marked in at least one of the one or more damage images of the decision support material, and at least one of the one or more damage images is generated based on the obtained three-dimensional image representation of the at least part of the anatomical joint.

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.

The disclosure provides a method, a system, and a computer program product for detecting a speed funnel in a region. The method comprises obtaining a plurality of traffic object observations for the region and determining at least one first learned traffic object, based on feature-based clustering of the plurality of traffic object observations. The method also includes generating at least one candidate traffic object group by grouping the at least one first learned traffic object and a second learned traffic object and performing validation of the at least one candidate traffic object group based on a statistical model. The method further includes generating at least one validated candidate traffic object group as a result of the validation of the at least one candidate traffic object group and merging the at least one validated candidate traffic object group with a second validated candidate traffic object group to detect the speed funnel.