Selective 3d registration

Abstract

A sampling and weighting technique is presented. Given a 3D model that is composed out of n separated entities, a set of parameters is obtained for each entity. A weight is calculated for each entity, giving higher weight for entities corresponding to rarer parameters. Entities are assigned to components based on their corresponding parameters. Entities are sampled based on the weights or based on the components. A new 3D model is constructed from the sampled entities.

1 . A method, comprising:
 obtaining a 3D model composed of n entities;   obtaining a set of parameters for each of the n entities, thereby obtaining n sets of parameters corresponding to the n entities;   calculating a crowdedness value for each set of parameters, thereby obtaining n crowdedness values corresponding to the n entities;   calculating a weight for each entity based on the crowdedness value corresponding to the entity, thereby obtaining n weights corresponding to the n entities;   processing information related to the n entities based on the n weights.   
     
     
         2 . The method of  claim 1 , where the weight is calculated as an inverse function of the crowdedness value. 
     
     
         3 . A method, comprising:
 obtaining a 3D model composed of n entities;   obtaining a set of parameters for each of the n entities, thereby obtaining n sets of parameters corresponding to the n entities;   assigning the n entities to m components based on the set of parameters of each entity, thereby obtaining m components, where each component is a subset of the n entities;   sampling a subset of entities from each component, therefore obtaining m subsets of entities;   uniting the m subsets of entities to obtain a single set of sampled entities;   constructing a new 3D model out of the set of sampled entities;   processing information related to the new 3D model.   
     
     
         4 . A software product stored on a non-transitory computer readable medium and comprising data and computer implementable instructions for carrying out the method of  claim 1 . 
     
     
         5 . A software product stored on a non-transitory computer readable medium and comprising data and computer implementable instructions for carrying out the method of  claim 3 . 
     
     
         6 . An apparatus, comprising:
 at least one 3D camera, configured to capture a 3D model composed of n entities;   at least one processor, configured to:
 obtain a set of parameters for each of the n entities, thereby obtaining n sets of parameters corresponding to the n entities; 
 calculate a crowdedness value for each set of parameters, thereby obtaining n crowdedness values corresponding to the n entities; 
 calculate a weight for each entity based on the crowdedness value corresponding to the entity, thereby obtaining n weights corresponding to the n entities; 
 process information related to the n entities based on the n weights. 
   
     
     
         7 . The apparatus of  claim 6 , where the weight is calculated as an inverse function of the crowdedness value. 
     
     
         8 . An apparatus, comprising:
 at least one 3D camera, configured to capture a 3D model composed of n entities;   at least one processor, configured to:
 obtain a set of parameters for each of the n entities, thereby obtaining n sets of parameters corresponding to the n entities; 
 assign the n entities to m components based on the set of parameters of each entity, thereby obtaining m components, where each component is a subset of the n entities; 
 sample a subset of entities from each component, therefore obtaining m subsets of entities; 
 unite the m subsets of entities to obtain a single set of sampled entities; 
 construct a new 3D model out of the set of sampled entities; 
 process information related to the new 3D model.