Sayer, Robert David

In some examples, systems and methods for multiple-sensor object tracking are provided. For example, a method includes: receiving a plurality of tracks generated based on a plurality of images from a plurality of sensor feeds, the plurality of sensor feeds including a first sensor feed and a second sensor feed, the plurality of tracks including a first track detected in a first image from the first sensor feed and a second track detected in a second image from the second sensor feed; determining a candidate association between the first track and the second track; generating an association confidence score corresponding to the candidate association based at least in part on a track history; evaluating whether the candidate association meets one or more association criteria; and in response to the candidate association meeting the one or more association criteria, merging the first track and the second track to generate a merged track; and updating the plurality of tracks to include the merged track replacing the first track and the second track.

In some examples, systems and methods for multiple-sensor object tracking are provided. For example, a method includes: receiving one or more first image transformations generated based on a plurality of previous images from a plurality of sensor feeds respectively; receiving a plurality of images from the plurality of sensor feeds; generating a transformation update based on the one or more image transformations and the plurality of images using an image registration model; generating a second image transformation based on the transformation update and the one or more first image transformations; applying the second image transformation to the plurality of images to generate a set of transformed images; and identifying a plurality of objects using a multiple object tracking model based on the set of transformed images.

Computer-implemented systems and methods including language models for providing an application-aware model-based assistant. A computer-implemented method, for communicating with a front end device to generate application specific recommended actions, may include: determining lists of available global and application actions; receiving a user query; generating a first prompt for a language model and providing a first response for display to the user; generating a second prompt for a language model; and in response to receiving an output: parsing the output to generate a list of recommended actions, and providing a second response for display to the user, where the second response includes the third list of recommended actions.

A method performed by one or more processors comprises displaying code, receiving user selection of a portion of code, determining one or more settable data items, generating a template, displaying the template, receiving a user input value for the settable data items by the template, and executing the code with each of the settable data items set to the received user input value. A data processing pipeline is configured to pass a data item to a first transformer to provide first transformed data, store the first transformed data in a temporary memory, write the first transformed data to the data storage system, and pass the transformed data from the temporary memory to a second transformer.

An artificial intelligence system (AIS) can improve relevance of LLM responses through selection of appropriate examples to provide in an enhanced user prompt. The system may receive user inputs indicating a task to be performed by the LLM, determine a set of examples based at least on an initial user prompt and to potentially include in an enhanced user prompt, and determine which examples in the set of examples are ideal to include in the enhanced user prompt to increase the usefulness of the LLM response. The AIS can generate an enhanced prompt for the LLM based on the user input and identified ideal examples. The enhanced prompt can include at least a portion of the initial user input and each of the identified ideal examples.

Systems and methods for image matching are provided. An example method includes receiving an incoming image of a first imaging modality; receiving a reference image of a second imaging modality, the second imaging modality being different from the first imaging modality; generating a reference view of the reference image based on one or more priors associated with the incoming image; detecting a plurality of features corresponding to a plurality of feature points in the incoming image using a first algorithm that generates relatively even distribution of the plurality of feature points; generating a plurality of feature descriptors corresponding to the plurality of features, at least one of the plurality of feature descriptors being associated with at least one of a plurality of orientation bins.

In some examples, systems and methods for mixed reality are provided. For example, a method includes: generating a three-dimensional image based on target area data from one or more first data sources; receiving object data associated with one or more digital objects from one or more second data sources; generating an object representation including a representation of at least one of the one or more digital objects based on the object data associated with one or more digital objects; overlaying the object representation on the three-dimensional image to generate a three-dimensional representation; and projecting the three-dimensional representation including the overlaid object representation via a virtual reality device; wherein the method is performed by one or more processors.

In some examples, systems and methods for document writing and/or document generation are provided. For example, a method includes: identifying one or more document types associated with a request, each document type being associated with a document template; extracting one or more pieces of evidence from one or more data records based on the request; accessing one or more routes for document generations, each route of the one or more routes using one or more template-specific computing models; generating one or more documents using the one or more routes; and outputting a selected document that is selected from the one or more generated documents.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …