A method of detecting and responding to a visitor to a smart home environment via an electronic greeting system of the smart home environment, including determining that a visitor is approaching an entryway of the smart home environment; initiating a facial recognition operation while the visitor is approaching the entryway; initiating an observation window in response to the determination that a visitor is approaching the entryway; obtaining context information from one or more sensors of the smart home environment during the observation window; and at the end of the time window, initiating a response to the detected approach of the visitor based on the context information and/or an outcome of the facial recognition operation.

In general, one innovative aspect of the subject matter described in this specification can be embodied in a computer-implemented method. The method includes, detecting, by an imaging device, the presence of an object to be imaged. The method further includes, measuring, by the imaging device, a first characteristic of the object to be imaged, and measuring, by the imaging device, a second characteristic of the object to be imaged. The method further includes, determining, by a computing device, that at least one of the first characteristic of the object or the second characteristic of the object exceeds a threshold; and in response to determining, indicating, by the computing device, whether the object to be imaged is one of a spoofed object or an actual object.

A system and method of confirming administration of medication is provided. The method comprises the steps of receiving information identifying a particular medication prescription regimen, determining one or more procedures for administering such prescription regimen and identifying one or more activity sequences associated with such procedures. Activity sequences of actual administration of such prescription regimen are captured and then compared to the identified activity sequences to determine differences therebetween. A notice is provided if differences are determined.

Disclosed examples include accessing sensor data; recognizing, by executing an instruction with programmable circuitry, a feature in the sensor data based on a convolutional neural network; and transitioning, by executing an instruction with the programmable circuitry, a mobile device between at least two of motion feature detection, audio feature detection, or camera feature detection after the feature is recognized in the sensor data, the mobile device to operate at a different level of power consumption after the transition than before the transition.

Fabrication processing is executed in a chip of an image sensor. An image capturing device includes an image capturing unit (11) mounted on a vehicle and configured to generate image data by performing image capturing of a peripheral region of the vehicle, a scene recognition unit (214) configured to recognize a scene of the peripheral region based on the image data, and a drive control unit (12) configured to control drive of the image capturing unit based on the scene recognized by the scene recognition unit.

Using an image analysis model within an image intended for distribution online, an image portion depicting personally identifiable information is identified, the personally identifiable information comprising image data usable to identify a specific individual. Using an online profile, a person depicted in the image portion is identified. A transaction is posted in a publicly-accessible distributed encrypted ledger, the transaction comprising an encrypted request to allow the image to be distributed online. According to a response to the request, the image portion is obfuscated, the obfuscating comprising altering data of the image portion, the altering making the image portion unusable to identify the person.

Methods and apparatus for applying data analytics such as deep learning algorithms to sensor data. In one embodiment, an electronic device such as a camera apparatus including a deep learning accelerator (DLA) communicative with an image sensor is disclosed, the camera apparatus configured to evaluate unprocessed sensor data from the image sensor using the DLA. In one variant, the camera apparatus provides sensor data directly to the DLA, bypassing image signal processing in order to improve the effectiveness the DLA, obtain DLA results more quickly than using conventional methods, and further allow the camera apparatus to conserve power.

A facial structure estimation apparatus includes a controller 13. The controller 13 stores, as learning data, a parameter indicating a relationship between a face image and a structure of the face image. The controller 13 learns a relationship between a first face image and a facial structure corresponding to the first face image. The controller 13 learns a relationship between a second face image of a certain person and a facial structure corresponding to the second face image. The controller 13 learns a relationship between a second face image of the certain person detected using infrared light and a facial structure corresponding to the second face image.

An image sensor comprises a plurality of pixels. Pixels are capable of detecting a change in an amount of light intensity and pixels are capable of detecting an amount of light intensity. In a first mode the sensor outputs data from the first one or more of the pixels. In a second mode the sensor outputs data from the second one or more of the pixels. The first mode may be a lower power operation mode and the second mode may be a higher power operation mode. At least one of the first mode and the second mode is selected by a processor based on at least one of a result of processing data output in the first mode and a result of processing data output in the second mode.

The subject technology receives a selection of a selectable graphical item from a plurality of selectable graphical items, the selectable graphical item comprising an augmented reality content generator for applying a 3D effect, the 3D effect including at least one beautification operation. The subject technology captures image data and depth data using a camera. The subject technology applies, to the image data and the depth data, the 3D effect including the at least one beautification operation based at least in part on the augmented reality content generator, the beautification operation being performed as part of applying the 3D effect. The subject technology generates a 3D message based at least in part on the applied 3D effect including the at least one beautification operation. The subject technology renders a view of the 3D message based at least in part on the applied 3D effect including the at least one beautification operation.