A system can include a computer including a processor and a memory, the memory storing instructions executable by the processor to receive point cloud data. The instructions further include instructions to generate a plurality of feature maps based on the point cloud data, each feature map of the plurality of feature maps corresponding to a parameter of the point cloud data. The instructions further include instructions to aggregate the plurality of feature maps into an aggregated feature map. The instructions further include instructions to generate, via a feedforward neural network, at least one of a segmentation output or a classification output based on the aggregated feature map.

This application relates to automated processes for determining item placement compliance within retail locations. For example, a computing device may obtain an image of a fixture within a store. The image may be captured by a camera with a field of view directed at the fixture. The computing device may apply a segmentation process to the image to determine a portion of the image. Further, the computing device may determine a correlation between the portion of the image and each of a plurality of item image templates. Each item image template may include an image of an item the retail location sells in the retail location. The computing device may determine, based on the correlations, one of the plurality of item image templates and its corresponding item. The computing device may then determine whether the item should be located at the fixture based on a planogram.

This application relates to automated processes for determining item placement compliance within retail locations. For example, a computing device may obtain an image of a fixture within a store. The image may be captured by a camera with a field of view directed at the fixture. The computing device may apply a segmentation process to the image to determine a portion of the image. Further, the computing device may determine a correlation between the portion of the image and each of a plurality of item image templates. Each item image template may include an image of an item the retail location sells in the retail location. The computing device may determine, based on the correlations, one of the plurality of item image templates and its corresponding item. The computing device may then determine whether the item should be located at the fixture based on a planogram.

The invention provides a technique capable of effectively and appropriately removing noise from various kinds of images including noise and artifacts and images in which a noise pattern changes due to a difference in imaging conditions. Based on a noise removal technique using AI, noise characteristics including artifacts are analyzed for each image, the image is classified based on an analysis result, an optimal neural network for a noise processing is applied for each classification, and the noise and the artifacts are reduced.

The invention provides a technique capable of effectively and appropriately removing noise from various kinds of images including noise and artifacts and images in which a noise pattern changes due to a difference in imaging conditions. Based on a noise removal technique using AI, noise characteristics including artifacts are analyzed for each image, the image is classified based on an analysis result, an optimal neural network for a noise processing is applied for each classification, and the noise and the artifacts are reduced.

In a general aspect, a data management system for spatial phase imaging is described. A data management system for spatial phase imaging includes: a storage engine configured to receive and store input data in a record format, the input data including: pixel-level first-order primitives generated based on electromagnetic (EM) radiation received from an object located in a field-of-view of an image sensor device; and pixel-level second-order primitives generated based on the first-order primitives. The data management system further includes: an analytics engine configured to determine a plurality of features of the object based on the pixel-level first-order primitives and the pixel-level second-order primitives; and an access engine configured to provide a user access to the plurality of features of the object determined by the analytics engine and to the input data stored by the storage engine.

In a general aspect, a data management system for spatial phase imaging is described. A data management system for spatial phase imaging includes: a storage engine configured to receive and store input data in a record format, the input data including: pixel-level first-order primitives generated based on electromagnetic (EM) radiation received from an object located in a field-of-view of an image sensor device; and pixel-level second-order primitives generated based on the first-order primitives. The data management system further includes: an analytics engine configured to determine a plurality of features of the object based on the pixel-level first-order primitives and the pixel-level second-order primitives; and an access engine configured to provide a user access to the plurality of features of the object determined by the analytics engine and to the input data stored by the storage engine.

A computer-implemented method of generating metadata from an image may comprise sending the image to an object detection service, which generates detections metadata from the image. The image may also be sent to a visual features extractor, which extracts visual features metadata from the image. The generated detections metadata may then be sent to an uncertainty score calculator, which computes an uncertainty score from the detections metadata. The uncertainty score may be related to a level of uncertainty within the detections metadata. The image, the visual features metadata, the detections metadata and the uncertainty score may then be stored in a database accessible over a computer network.

A computer-implemented method of generating metadata from an image may comprise sending the image to an object detection service, which generates detections metadata from the image. The image may also be sent to a visual features extractor, which extracts visual features metadata from the image. The generated detections metadata may then be sent to an uncertainty score calculator, which computes an uncertainty score from the detections metadata. The uncertainty score may be related to a level of uncertainty within the detections metadata. The image, the visual features metadata, the detections metadata and the uncertainty score may then be stored in a database accessible over a computer network.

Disclosed herein is a computer-implemented method, a respective device, and a non-transitory computer-readable medium. The method includes: obtaining color values, texture values and digital images of a target coating, retrieving from a database one or more preliminary matching formulas based on the color and/or texture values obtained for the target coating, determining sparkle points within the respective obtained images and within the respective images associated with the one or more preliminary matching formulas, creating subimages of each sparkle point from the respective images, providing the created subimages to a convolutional neural network, the convolutional neural network being trained to correlate a respective subimage of a respective sparkle point with a pigment and/or pigment class, and determining, based on an output of the neural network, at least one of the one or more preliminary matching formulas as the formula(s) best matching the target coating.