Systems and methods are described for generating image content. The systems and methods may include, in response to receiving a request to cause a sensor of a computing device to identify image content associated with optical data captured by the sensor, detecting a first sensor data stream having a first image resolution, and detecting a second sensor data stream having a second image resolution. The systems and method may also include identifying, by processing circuitry of the computing device, at least one region of interest in the first sensor data stream, determining cropping coordinates that define a first plurality of pixels in the at least one region of interest in the first sensor data stream, and generating a cropped image representing the at least one region of interest.

Systems and methods are described for generating image content. The systems and methods may include, in response to receiving a request to cause a sensor of a computing device to identify image content associated with optical data captured by the sensor, detecting a first sensor data stream having a first image resolution, and detecting a second sensor data stream having a second image resolution. The systems and method may also include identifying, by processing circuitry of the computing device, at least one region of interest in the first sensor data stream, determining cropping coordinates that define a first plurality of pixels in the at least one region of interest in the first sensor data stream, and generating a cropped image representing the at least one region of interest.

In one general aspect, a method can include capturing, using an image sensor, a first raw image at a first resolution, converting the first raw image to a digitally processed image using an image signal processor, and analyzing at least a portion of the digitally processed image based on a processing condition. The method can include determining that the first resolution does not satisfy the processing condition; and triggering capture of a second raw image at the image sensor at a second resolution greater than the first resolution.

The application discloses a method and device for personalized search of visual media. Semantic analysis is conducted on a visual media query text of a user to obtain visual semantic information, time information and/or location information. Semantic similarity matching is conducted on a result of the semantic analysis and attribute data of each visual medium within a specified search range to obtain a query similarity of the visual medium. The visual medium is an image or a video, and the attribute data include personalized visual semantic information, personalized time information and/or personalized location information. A corresponding visual media query result is generated based on the query similarity. By adopting the application, users are provided with visual media which is a result of a personalized.

The application discloses a method and device for personalized search of visual media. Semantic analysis is conducted on a visual media query text of a user to obtain visual semantic information, time information and/or location information. Semantic similarity matching is conducted on a result of the semantic analysis and attribute data of each visual medium within a specified search range to obtain a query similarity of the visual medium. The visual medium is an image or a video, and the attribute data include personalized visual semantic information, personalized time information and/or personalized location information. A corresponding visual media query result is generated based on the query similarity. By adopting the application, users are provided with visual media which is a result of a personalized.

A feature extractor and novel training objective are provided for content-based image retrieval. For example, a computer-implemented method includes applying a query image and a search image to a neural network of a feature extraction network of a computing device, the query image indicating an object to be searched for in the search image. The feature extraction network includes the neural network, a spatial feature neural network receiving a first output of the neural network pertaining to the search image, and an embedding network receiving a second output of the neural network pertaining to the query image. The method includes generating spatial search features from the spatial feature neural network, generating a query feature from the embedding network, applying the query feature to an artificial neural network (ANN) index, and determining an optimal matching result of an object in the search image based on an operation using the ANN index.

A feature extractor and novel training objective are provided for content-based image retrieval. For example, a computer-implemented method includes applying a query image and a search image to a neural network of a feature extraction network of a computing device, the query image indicating an object to be searched for in the search image. The feature extraction network includes the neural network, a spatial feature neural network receiving a first output of the neural network pertaining to the search image, and an embedding network receiving a second output of the neural network pertaining to the query image. The method includes generating spatial search features from the spatial feature neural network, generating a query feature from the embedding network, applying the query feature to an artificial neural network (ANN) index, and determining an optimal matching result of an object in the search image based on an operation using the ANN index.

An information processing apparatus according to the present invention includes: a display control unit that displays, on a screen, a map of a search area, a camera icon indicating a location of a surveillance camera in the map, and a person image of a search target person; an operation receiving unit that receives an operation of superimposing, on the screen, one of the person image or the camera icon on the other; and a processing request unit that requests a matching process between the person image and a surveillance video captured by the surveillance camera corresponding to the camera icon based on the operation.

An image registration method includes: acquiring a target image comprising a target object; inputting the target image to a preset network model, and outputting position information and rotation angle information of the target object; obtaining a reference image comprising the target object by querying a preset image database according to the position information and the rotation angle information; and performing image registration on the target image and the reference image to obtain a corresponding position of the target object of the target image in the reference image.

An image registration method includes: acquiring a target image comprising a target object; inputting the target image to a preset network model, and outputting position information and rotation angle information of the target object; obtaining a reference image comprising the target object by querying a preset image database according to the position information and the rotation angle information; and performing image registration on the target image and the reference image to obtain a corresponding position of the target object of the target image in the reference image.