Methods, systems and apparatus, including computer programs encoded on computer storage media for generation of autonomous unmanned aerial vehicle flight plans based on triggered sensor information. One of the methods includes accessing information correlated from sensors monitoring features of weather events, and determining an upcoming weather event, the determination comprising one or more areas expected to be affected by the weather event. A likelihood of damage associated with the weather event is determined to be greater than a threshold in the areas. The weather event is monitored while areas in which the likelihood is greater than the threshold are updated accordingly. Subsequent to the weather event, properties to be inspected by unmanned aerial vehicles are determined based on severity information associated with the weather event. Job information is generated, the job information being associated with inspecting the determined properties, the job information including jobs each assignable to operators for implementation.

The present invention relates to a method and system for facilitating access to recorded data. The system comprises an interface and a processing device. The interface is arranged to receive data and the processing device is arranged to separate the received data in data subsets, compress each data subset and assign an identifier to each compressed data subset, thereby creating data units each comprising a compressed data subset and an associated identifier, the processing device further being arranged to establish an index on the basis of the assigned identifiers.

In variants, the method for property condition analysis can include: determining a measurement, optionally determining a set of property attributes, determining a condition score, optionally providing the condition score, and optionally training a condition scoring model.

Commentary rating determination systems and methods determine a commentary rating for commentary about a subject media content event that has been generated by a community member. An exemplary embodiment receives video information acquired by a 360° video camera, identifies a physical object from the received video information, determines a physical attribute associated with the identified physical object, wherein the determined physical attribute describes a characteristic of the identified physical object, compares the determined physical attribute of the identified physical object with a plurality of predefined physical object attributes stored in a database, and in response to identifying one of the plurality of predefined physical object attributes that matches the determined physical attribute, associates the quality value of the identified one of the plurality of predefined physical object attributes with the identified physical object. Then, the commentary rating is determined for the commentary based on the associated quality value.

A visual localization method and apparatus are provided. The method includes obtaining a captured first image, determining a first pose based on the first image and an aerial model, determining whether a ground model corresponding to the first pose exists in an aerial-ground model, and when the ground model corresponding to the first pose exists, determining a second pose based on the ground model. The aerial-ground model includes the aerial model and the ground model mapped to the aerial model, a coordinate system of the ground model is the same as a coordinate system of the aerial model, and localization accuracy of the second pose is higher than localization accuracy of the first pose. Performing fine visual localization based on the ground model can improve accuracy and a success rate of localization.

It is determined whether a traffic light is recognized in an image based on each of a result of a recognition operation by a traffic light first recognition unit (a recognition operation of the traffic light for an image acquired by a camera using a learned model based on pre-annotated data) and a result of a recognition operation by a traffic light second recognition unit (a recognition operation of the traffic light for an image acquired by the camera based on a feature amount of the traffic light). This makes it possible to sufficiently obtain the recognition accuracy of the traffic light, and to appropriately perform an instruction to a pedestrian according to the state of the traffic light.

Commentary rating determination systems and methods determine a commentary rating for commentary about a subject media content event that has been generated by a community member. An exemplary embodiment receives video information acquired by a 360° video camera, identifies a physical object from the received video information, determines a physical attribute associated with the identified physical object, wherein the determined physical attribute describes a characteristic of the identified physical object, compares the determined physical attribute of the identified physical object with a plurality of predefined physical object attributes stored in a database, and in response to identifying one of the plurality of predefined physical object attributes that matches the determined physical attribute, associates the quality value of the identified one of the plurality of predefined physical object attributes with the identified physical object. Then, the commentary rating is determined for the commentary based on the associated quality value.

An Artificial Intelligence (AI) roof deterioration analysis system that tracks changes in roofs over time by evaluating a series of features in high-resolution images.

Systems and methods for domain adaptation for structured output via disentangled representations are provided. The system receives a ground truth of a source domain. The ground truth is used in a task loss function for a first convolutional neural network that predicts at least one output based on inputs from the source domain and a target domain. The system clusters the ground truth of the source domain into a predetermined number of clusters, and predicts, via a second convolutional neural network, a structure of label patches. The structure includes an assignment of each of the at least one output of the first convolutional neural network to the predetermined number of clusters. A cluster loss is computed for the predicted structure of label patches, and an adversarial loss function is applied to the predicted structure of label patches to align the source domain and the target domain on a structural level.

A technique is introduced for utilizing data associated with a monitored premises to determine a likelihood of a crime, or other activity, occurring at the premises. In an example embodiment, premises data is received from one or more sources including sensor devices located at the premises and other data sources including third-party databases. The premises data is processed using a machine learning model, such as an artificial neural network, to generate a risk score that is indicative of the likelihood of a crime occurring at the premises in real-time or in the future. The introduced technique for risk evaluation can be implemented in conjunction with a premises security system, for example, to route alarms generated by monitoring devices located at the premises.