Systems and methods for video archive and data extraction
Systems and methods for full motion video search are provided. In one aspect, a method includes receiving one or more search terms. The search terms include one or more of a characterization of the amount of man-made features in a video image and a characterization of the amount of natural features in the video image. The method further includes searching a full motion video database based on the one or more search terms.
1. A method of adding a video entity to a full motion video database supporting search capabilities, the method comprising:
determining a starting cell in the full motion video database;
if the starting cell is not full, adding the video entity to the starting cell;
if the starting cell contains a plurality of child cells:
determining a child cell from the plurality of child cells based on the video entity, and
recursively add the video entity using the child cell as a starting cell; and
if the starting cell is full:
determine a split axis by splitting the starting cell,
create two new child cells along the split axis,
move one or more entities from the starting cell to the two new child cells, and
add the video entity to one of the two new child cells.
2. The method of claim 1 , further comprising classifying at least a portion of the video entity as including one or more of manmade features and natural features.
3. The method of claim 1 , wherein the classification is based at least in part on edge coherence.
4. The method of claim 1 , further comprising identifying one or more buildings in at least a portion of the video entity.
5. The method of claim 4 , further comprising identifying one or more of a size, color, shape solidity, rooftop lack of detail, strong edges, and cast shadows of the identified one or more buildings.
6. The method of claim 4 , further comprising receiving a full motion video search request, wherein the search request indicates one or more of a building size, building color, building geo-location attributes, building shape, a building rooftop detail, a building edge characterization, and a building cast shadow characterization.
7. The method of claim 2 , further comprising receiving a full motion video search request, wherein the search request indicates a characterization of the amount of man-made features in a scene or a characterization of the amount of natural features in the scene.