Camera platform incorporating schedule and stature
Camera platform techniques are described. In an implementation, a plurality of digital images and data describing times, at which, the plurality of digital images are captured is received by a computing device. Objects of clothing are recognized from the digital images by the computing device using object recognition as part of machine learning. A user schedule is also received by the computing device that describes user appointments and times, at which, the appointments are scheduled. A user profile is generated by the computing device by training a model using machine learning based on the recognized objects of clothing, times at which corresponding digital images are captured, and the user schedule. From the user profile, a recommendation is generated by processing a subsequent user schedule using the model as part of machine learning by the computing device.
1 . A method implemented by a computing device, the method comprising:
receiving, by the computing device, digital images including objects, times at which the digital images are captured, and a user schedule including appointments corresponding to the times the digital images are captured;
recognizing, by the computing device, the objects;
training, by the computing device, a machine learning model to generate a recommendation based on the objects recognized, the times at which the digital images are captured, and the user schedule; and
generating, by the computing device, the recommendation via the machine learning model.
2 . The method as described in claim 1 , wherein the receiving includes locations at which the digital images are captured and wherein the training of the machine learning model to generate the recommendation is based on the locations.
3 . The method as described in claim 1 , wherein the user schedule is a training schedule including weather conditions at times and locations of the appointments.
4 . The method as described in claim 1 , wherein the recommendation is output as augmented reality content.
5 . The method as described in claim 4 , wherein the augmented reality content is output via a user interface along with a direct view of a physical environment of the computing device.
6 . The method as described in claim 1 , wherein the recommendation is clothing.
7 . The method as described in claim 1 , wherein the recommendation is selectable via a user interface to begin a purchase from a service provider system via a network.
8 . The method as described in claim 1 , further comprising presenting, by the computing device, the recommendation as an augmented reality overlay within a live camera feed captured by the computing device.
9 . The method as described in claim 8 , wherein the presenting of the recommendation includes stabilizing the augmented reality overlay relative to scene content using at least one of orientation sensor data of the computing device and image-based feature tracking across one or more frames.
10 . The method as described in claim 1 , further comprising generating, by the computing device, size data, stature data, and style data from the digital images, and wherein the generating of the recommendation is based at least in part on the generated size data, stature data, and style data.
11 . The method as described in claim 1 , wherein the receiving of the digital images comprises receiving depth image data, the method further comprising performing, by the computing device, skeletal tracking on the depth image data to estimate a three-dimensional skeletal model of a person depicted in the digital images, and wherein the generating of the recommendation is further based at least in part on the skeletal tracking.
12 . A computing device comprising:
a processing system; and
a computer-readable storage medium having stored instructions that, responsive to execution by the processing system, induce the processing system to perform operations comprising:
receiving digital images including objects, times at which the digital images are captured, and a user schedule including appointments corresponding to the times the digital images are captured;
recognizing the objects;
training a machine learning model to generate a recommendation based on the objects recognized, the times at which the digital images are captured, and the user schedule; and
generating the recommendation via the machine learning model.
13 . The computing device as described in claim 12 , wherein at least one of a size, a stature, or a style are described in the recommendation.
14 . The computing device as described in claim 12 , wherein the recommendation is for an object.
15 . The computing device as described in claim 14 , wherein the object is clothing.
16 . The computing device as described in claim 12 , wherein the recommendation is output as augmented reality content.
17 . The computing device as described in claim 16 , wherein the augmented reality content is output via a user interface along with a direct view of a physical environment of the computing device.
18 . The computing device as described in claim 17 , wherein the direct view is part of a live feed.
19 . A non-transitory computer-readable storage medium storing executable instructions, which when executed by a processing device, induce the processing device to perform operations comprising:
receiving digital images including objects, times at which the digital images are captured, and a user schedule including appointments corresponding to the times the digital images are captured;
recognizing the objects;
training a machine learning model to generate a recommendation based on the objects recognized, the times at which the digital images are captured, and the user schedule; and
generating the recommendation via the machine learning model.
20 . The non-transitory computer-readable storage medium as described in claim 19 , wherein the recommendation is for an object.