A system for managing images obtains an image that is captured by an image capture device at an image capture position and an image capture time; and stores the image, the image capture position, and the image capture time. The system further determines a position of a subject included in the image based on the image capture position. The system further stores index information comprising a target identifier of the subject, the position of the subject, and the image capture time in association with the stored image. The system further determines index information corresponding to the search instruction when obtaining a search instruction of the image; and extracts the image corresponding to the determined index information.

One variation of a method for tracking and maintaining inventory in a store includes: accessing a image of an inventory structure in the store; identifying a top shelf, in the inventory structure, depicted in the image; identifying a set of product units occupying the top shelf based on features detected in the image; identifying a second shelf, in the set of shelves in the inventory structure, depicted in the image, the second shelf arranged below the top shelf in the inventory structure; based on features detected in the image, detecting an understock condition at a slot—assigned to a product type—on the second shelf; and, in response to the set of product units comprising a product unit of the product type, generating a prompt to transfer the product unit of the product type from the top shelf into the slot on the second shelf at the inventory structure.

A system and method are provided for performing operations comprising: receiving one or more images from an image capture device of a medical treatment location; applying a trained machine learning model to the one or more images to detect presence of a patient in the medical treatment location, the trained machine learning model being trained to establish a relationship between one or more features of images of the medical treatment location and patient presence; generating context assessment for the medical treatment location based on the detected presence of the patient; and transmitting, over a network, the context assessment for presentation on a user interface of a client device.

Systems and methods are provided for analyzing messages generated by a plurality of computing devices associated with a plurality of users in a messaging system to generate training data to train a machine learning model to determine a probability that a media content item was generated inside an enclosed location or outside, receiving a media content item from a computing device, analyzing the media content item using the trained machine learning model to determine a probability that the media content item was generated inside an enclosed location or outside, determining, based on the probability generated by the trained machine learning model, that the media content item was generated inside an enclosed location, and determining an inside temperature associated with the venue based on messages generated by a plurality of computing devices in a messaging system comprising media content items and temperature information for the venue or a similar venue type.

Provided are an image recognition apparatus, an image recognition method, and a program for enabling recognition of many kinds of objects with high precision. An overall recognition unit executes, for at least one given object, a process of recognizing the position of the object in an image. A partial image extraction unit extracts, from the image, a partial image which is a part of the image associated with the recognized position. A partial recognition unit executes a process of recognizing what is one or more objects represented by the partial image, the one or more objects including an object other than the given object the position of which is recognized.

Various of the disclosed embodiments relate to systems and methods for processing surgical data to facilitate further downstream operations. For example, some embodiments may include machine learning systems trained to recognize whether video from surgical visualization tools, such as endoscopes, depicts a field of view inside or outside the patient body. The system may excise or whiteout frames of video appearing outside the patient so as to remove potentially compromising personal information, such as the identities of members of the surgical team, the patients identity, configurations of the surgical theater, etc. Appropriate removal of such non-surgical data may facilitate downstream processing, e.g., by complying with regulatory requirements as well as by removing extraneous data potentially inimical to further downstream processing, such as training a downstream classifier.

The subject matter of this specification can be implemented in, among other things, methods, systems, computer-readable storage medium. A method can include receiving, by a processing device, image data including one or more image frames indicative of a current state of a drive-thru area. The processing device determines a vehicle disposed within the drive-thru area based on the image data. The processing device receives order data with a pending meal order. The processing device determines a first association between the vehicle and the pending meal order based on the image data. The processing devices determine a meal delivery procedure associated with the based on the association between the vehicle and the pending meal order. The processing device performs may perform the meal delivery procedure. The processing device may provide the meal delivery procedure for display on a graphical user interface (GUI).

Systems and methods for estimating a layout of a room are disclosed. The room layout can comprise the location of a floor, one or more walls, and a ceiling. In one aspect, a neural network can analyze an image of a portion of a room to determine the room layout. The neural network can comprise a convolutional neural network having an encoder sub-network, a decoder sub-network, and a side sub-network. The neural network can determine a three-dimensional room layout using two-dimensional ordered keypoints associated with a room type. The room layout can be used in applications such as augmented or mixed reality, robotics, autonomous indoor navigation, etc.

A moving robot including: a lidar sensor to acquire terrain information; a memory to store node data nodes; and a controller to determine whether at least one open movement direction exists based on sensing data of the lidar sensor and the node data, to generate a new node in the node data and add the generated node to a node group, to determine any of the open movement directions as a movement direction, to control the robot to travels an area corresponding to the node group, to control a suction unit to suck foreign matter around the main body when traveling in the node group, to initialize the node group, to determine whether at least one node is to be updated, moving the robot to any one of the nodes to be updated, and to complete generation of a map.

The subject matter of this specification can be implemented in, among other things, methods, systems, computer-readable storage medium. A method includes a processing device receiving image data having one or more image frames indicative of a state of a meal preparation area. The method further includes the processing device determining, based on the image data, one of a meal preparation item or a meal preparation action associated with the state of the meal preparation area. The method further includes the processing device determining, based on the image data, a performance metric associated with the meal preparation item or the meal preparation item or the meal preparation action. The method further includes the processing device causing a notification corresponding to the performance metric to be displayed on a graphical user interface (GUI).