Technologies for generating computer models, devices, systems, and methods utilizing the same

Abstract

Technologies for generating 3D and using models are described. In some embodiments the technologies employ a content creation device to produce a 3D model of an environment based at least in part on depth data and color data, which may be provided by one or more cameras. Contextual information such as location information, orientation information, etc., may also be collected or otherwise determined, and associated with points of the 3D model. Access points to the imaged environments may be identified and labeled as anchor points within the 3D model. Multiple 3D models may then be combined into an aggregate model, wherein anchor points of constituent 3D models in the aggregate model are substantially aligned. Devices, systems, and computer readable media utilizing such technologies are also described.

What is claimed is: 
     
         1 . A content creation device comprising a processor, a memory, a camera module, at least one sensor, and a content creation module (CCM), wherein:
 the camera module comprises a depth camera to obtain depth data of a real world environment and a visual camera to obtain color data of the real world environment;   the at least one sensor is to obtain contextual information; and   said CCM comprises circuitry to:
 produce a three dimensional model of said real world environment based at least in part on said depth data; 
 analyze at least one of said depth data and color data to detect one or more access points in said real world environment; 
 correlate a portion of said three dimensional model with a detected access point; and 
 correlate said contextual information with the portion of said three dimensional model corresponding to a detected access point. 
   
     
     
         2 . The content creation device of  claim 1 , wherein said at least one sensor comprises one or more of a gyroscope, a global positioning sensor, or an accelerometer. 
     
     
         3 . The content creation device of  claim 1 , wherein:
 said depth data is stored in one or more first frames in said memory;   said color data is stored in one or more second frames in said memory; and   said CCM is to detect said one or more access points at least in part by executing image processing operations on at least one of said first or second frames.   
     
     
         4 . The content creation device of  claim 3 , wherein:
 said image processing operations comprise performing object detection on at least one of said first or second frames;   said CCM is further to identify a type of said detected access point at least in part by comparing an output of said object detection operations to a database of predefined access points.   
     
     
         5 . The content creation device of  claim 1 , wherein:
 said depth data is stored in one or more first frames in said memory;   said color data is stored in one or more second frames in said memory;   said CCM is further to execute image processing operations on at least one of said first or second frames to detect one or more objects in said real world environment;   said three dimensional model includes a representation of a detected object within said real world environment.   
     
     
         6 . The content creation device of  claim 5 , wherein:
 said image processing operations to detect one or more objects comprise performing object detection on at least one of said first or second frames, and said CCM is to identify a type of detected object at least in part by comparing an output of said image processing operations to a database of predefined objects;   said CCM is further to:
 determine object parameters corresponding to an identified detected object; and 
 correlate said object parameters with a representation of an identified detected object in said three dimensional model. 
   
     
     
         7 . The content creation device of  claim 1 , wherein:
 said CCM is further to combine a plurality of constituent three dimensional models to produce an aggregate model, the plurality of constituent three dimensional models comprising a first constituent model of a first real world location and a second constituent model of a second real world location, the first and second real world locations being arranged in a real world arrangement; and   in said aggregate model, said first and second constituent models are arranged in substantially the same manner as the real world arrangement.   
     
     
         8 . The content creation device of  claim 7 , wherein:
 said first constituent model is associated with first metadata identifying one or more first anchor points in said first constituent model, each first anchor point corresponding to an access point in said first real world location;   said second constituent model is associated with second metadata identifying one or more second anchor points in said second constituent model, each second anchor point corresponding to an access point in said first real world location; and   said CCM is further to produce said aggregate model at least in part by joining at said first and second constituent models, such that in said aggregate model a first anchor point of said first constituent model is substantially aligned with a second anchor point of said second constituent model.   
     
     
         9 . The content creation device of  claim 8 , wherein:
 said first constituent model comprises a plurality of first anchor points; and   said CCM is further to combine said plurality of constituent models such that in said aggregate model, a selected one of the plurality of first anchor points is substantially aligned with a second anchor point of said second constituent model.   
     
     
         10 . A method for producing a three dimensional model, comprising, with a content creation device:
 producing a three dimensional model of a real world environment based at least in part on depth data of said real world environment;   analyzing at least one of said depth data and color data of said real world environment to detect one or more access points in said real world environment;   correlating a portion of said three dimensional model with a detected access point; and   correlating contextual information of at least one sensor with the portion of said three dimensional model corresponding to said detected access point.   
     
     
         11 . The method of  claim 10 , further comprising:
 obtaining said depth data in one or more first frames with a depth camera; and   obtaining said color data with one or more second frames with a visual camera;   wherein:
 said analyzing at least one of said depth data and color data to detect one or more access points comprises executing image processing operations on at least one of said first or second frames; and 
 said three dimensional model includes a representation of a detected access point. 
   
     
     
         12 . The method of  claim 11 , further comprising:
 performing object detection operations on at least one of said first or second frames to detect objects in said real world environment, and   identifying a type of detected object at least in part by comparing an output of said object detection operations to a database of predefined access points.   
     
     
         13 . The method of  claim 10 , further comprising:
 analyzing at least one of said depth data and color data to detect an object within said real world environment;   wherein said analyzing comprises executing image processing operations on at least one of said first or second frames.   
     
     
         14 . The method of  claim 13 , wherein:
 said image processing operations comprise performing object detection on at least one of said first or second frames to detect one or more detected objects; and   the method further comprises:
 identifying a detected object at least in part by comparing an output of said image processing operations to a database of predefined objects; 
 determining object parameters corresponding to an identified detected object; and 
 correlating said object parameters with a representation of an identified detected object in said three dimensional model. 
   
     
     
         15 . The method of  claim 10 , further comprising, with the content creation device:
 combining a plurality of constituent three dimensional models to produce an aggregate model, the plurality of constituent three dimensional models comprising a first constituent model of a first real world location and a second constituent model of a second real world location, the first and second real world locations being arranged in a real world arrangement;   wherein in said aggregate model, said first and second constituent models are arranged in substantially the same manner as the real world arrangement.   
     
     
         16 . The method of  claim 15 , wherein:
 said first constituent model is associated with first metadata identifying one or more first anchor points in said first constituent model, each first anchor point corresponding to an access point in said first real world location;   said second constituent model is associated with second metadata identifying one or more second anchor points in said second constituent model, each second anchor point corresponding to an access point in said first real world location; and   combining said plurality of constituent three dimensional models to produce said aggregate model comprises joining said first and second constituent models such that in said aggregate model, a first anchor point of said first constituent model is substantially aligned with a second anchor point of said second constituent model.   
     
     
         17 . At least one computer readable medium comprising instructions which when executed by a processor of a content creation device result in the performance of the following operations comprising:
 producing a three dimensional model of a real world environment based at least in part on depth data of said real world environment;   analyzing at least one of said depth data and color data of said real world environment to detect one or more access points in said real world environment;   correlating a portion of said three dimensional model with a detected access point; and   correlating contextual information of at least one sensor with the portion of said three dimensional model corresponding to said detected access point.   
     
     
         18 . The at least one computer readable medium of  claim 17 , wherein said instructions when executed further result in the performance of the following operations comprising:
 obtaining said depth data in one or more first frames with a depth camera; and   obtaining said color data with one or more second frames with a visual camera;   
       wherein:
 said analyzing at least one of said depth data and color data to detect one or more access points comprises executing image processing operations on at least one of said first or second frames to detect access points within said real world environment; and 
 said three dimensional model includes a representation of a detected access point. 
 
     
     
         19 . The at least one computer readable medium of  claim 18 , wherein said instructions when executed further result in the performance of the following operations comprising:
 performing object detection operations on at least one of said first or second frames to detect objects in said real world environment, and   identifying a type of detected object at least in part by comparing an output of said object detection operations to a database of predefined access points.   
     
     
         20 . The at least one computer readable medium of  claim 19 , wherein said instructions when executed further result in the performance of the following operations comprising
 determining object parameters corresponding to an identified detected object; and   correlating said object parameters with a representation of an identified detected object in said three dimensional model.   
     
     
         21 . The at least one computer readable medium of  claim 17 , wherein said instructions when executed further result in the performance of the following operations comprising:
 combining a plurality of constituent three dimensional models to produce an aggregate model, the plurality of constituent three dimensional models comprising a first constituent model of a first real world location and a second constituent model of a second real world location, the first and second real world locations being arranged in a real world arrangement;   wherein in said aggregate model, said first and second constituent models are arranged in substantially the same manner as the real world arrangement.   
     
     
         22 . The at least one computer readable medium of  claim 21 , wherein:
 said first constituent model is associated with first metadata identifying one or more first anchor points in said first constituent model, each first anchor point corresponding to an access point in said first real world location;   said second constituent model is associated with second metadata identifying one or more second anchor points in said second constituent model, each second anchor point corresponding to an access point in said first real world location; and   combining said plurality of constituent three dimensional models to produce said aggregate model comprises joining said first and second constituent models such that in said aggregate model, a first anchor point of said first constituent model is substantially aligned with a second anchor point of said second constituent model.   
     
     
         23 . The at least one computer readable medium of  claim 22 , wherein:
 said first constituent model comprises a plurality of first anchor points; and   in said aggregate model, a selected one of the plurality of first anchor points is substantially aligned with a second anchor point of said second constituent model.   
     
     
         24 . The at least one computer readable medium of  claim 23 , wherein:
 each of the plurality of first anchor points of said first constituent model is associated with first contextual information;   each second anchor point of the second constituent model is associated with second contextual information; and   said instructions when executed further result in the performance of the following operations comprising:
 identifying said selected one of the plurality of first anchor points based at least on a comparison of the first contextual information of each of said plurality of first anchor points with second contextual information associated with each second anchor point. 
   
     
     
         25 . The at least one computer readable medium of  claim 21 , wherein said aggregate model is a video game world, and said instructions when executed further result in the performance of the following operations comprising:
 introducing video game characters into said video game world.