Intelligent self-powered camera

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for monitoring wildlife using a self-powered camera. The methods, systems, and apparatus include actions of detecting an object near a camera, in response to detecting the object near the camera, classifying the object as a particular type of animal based on an appearance of the object in an image captured by the camera, determining whether to provide a notification regarding the image based on the particular type of animal that the object is classified as, and in response to determining to provide a notification regarding the image based on the particular type of animal that the object is classified as, providing the notification regarding the image.

1 . (canceled) 
     
     
         2 . A computer-implemented method comprising:
 providing an image captured by a camera to a neural network that is trained to classify whether an object is a particular type of wildlife;   receiving an indication from the neural network that the image represents an animal of the particular type of wildlife;   determining, by the camera and using the indication that the image represents an animal of the particular type of wildlife, to provide a notification regarding the image; and   providing, by the camera, the notification regarding the image.   
     
     
         3 . The method of  claim 2 , wherein the particular type of wildlife is a subset of one or more wildlife types for which the neural network has been trained. 
     
     
         4 . The method of  claim 2 , comprising:
 cropping the image captured by the camera to include a portion of the image that represents the object.   
     
     
         5 . The method of  claim 2 , wherein determining to provide the notification regarding the image comprises:
 determining the particular type of wildlife satisfies a rule specified by a user.   
     
     
         6 . The method of  claim 5 , wherein the rule includes data indicating the particular type of wildlife. 
     
     
         7 . The method of  claim 5 , wherein the rule includes data indicating a size corresponding to the particular type of wildlife. 
     
     
         8 . The method of  claim 5 , wherein the rule includes data indicating a physical characteristic corresponding to the particular type of wildlife. 
     
     
         9 . The method of  claim 2 , wherein providing the notification comprises:
 providing, in a communication to a user device, the notification regarding the image and another image that depicts another particular type of wildlife for which the neural network is trained to classify.   
     
     
         10 . The method of  claim 2 , comprising:
 determining a current time satisfies a notifying time threshold; and   providing, by the camera and in response to determining the current time satisfies the notifying time threshold, the notification regarding the image.   
     
     
         11 . The method of  claim 10 , wherein the notifying time threshold is an elapsed time since providing a previous notification. 
     
     
         12 . The method of  claim 2 , wherein the notification includes a portion of the image. 
     
     
         13 . The method of  claim 2 , comprising:
 providing the image in response to receiving a request for the image from a user device.   
     
     
         14 . A system comprising:
 one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:   providing an image captured by a camera to a neural network that is trained to classify whether an object is a particular type of wildlife;   receiving an indication from the neural network that the image represents an animal of the particular type of wildlife;   determining, by the camera and using the indication that the image represents an animal of the particular type of wildlife, to provide a notification regarding the image; and   providing, by the camera, the notification regarding the image.   
     
     
         15 . The system of  claim 14 , wherein the particular type of wildlife is a subset of one or more wildlife types for which the neural network has been trained. 
     
     
         16 . The system of  claim 14 , wherein the operations comprise:
 cropping the image captured by the camera to include a portion of the image that represents the object.   
     
     
         17 . The system of  claim 14 , wherein determining to provide the notification regarding the image comprises:
 determining the particular type of wildlife satisfies a rule specified by a user.   
     
     
         18 . The system of  claim 17 , wherein the rule includes data indicating the particular type of wildlife. 
     
     
         19 . The system of  claim 17 , wherein the rule includes data indicating a size corresponding to the particular type of wildlife. 
     
     
         20 . The system of  claim 17 , wherein the rule includes data indicating a physical characteristic corresponding to the particular type of wildlife. 
     
     
         21 . A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:
 providing an image captured by a camera to a neural network that is trained to classify whether an object is a particular type of wildlife;   receiving an indication from the neural network that the image represents an animal of the particular type of wildlife;   determining, by the camera and using the indication that the image represents an animal of the particular type of wildlife, to provide a notification regarding the image; and   providing, by the camera, the notification regarding the image.