Object search by description
Systems and methods search video data for objects that satisfy a general object description. A database is populated with identified objects and object characteristics detected in video data with at least one identifier that specifies video image data. At least one search parameter is received that presents a general object description. The database is queried based upon the received at least one search parameter. At least one identifier is returned from the database based upon the at least one search parameter.
1. A method of image data storage and retrieval, the method comprising:
acquiring video image data from a plurality of cameras, the acquired video image data comprising an identifier indicative of a camera of the plurality of cameras that acquired the video image data and a time stamp of when the video image data was acquired;
detecting a plurality of objects in the acquired video image data from the plurality of cameras;
detecting, for each detected object, object characteristics in the acquired video image data;
obtaining, for each detected object, other object characteristics from a source other than the acquired video image data;
aggregating, for each detected object, (i) the object characteristics detected in the acquired video image data and (ii) at least a portion of the object characteristics obtained from a source other than the acquired video image data;
storing, in a database, each detected object, each detected object's aggregated characteristics and each detected object's associated identifier;
receiving search parameters and Boolean operators at a searcher engine operating on a processor, wherein the search parameters correspond to a user's estimate of an object's characteristics;
querying the database for object characteristics based upon the received search parameters and Boolean operators;
returning identifiers meeting the query based upon the received search parameters and Boolean operators;
computing a similarity score for each returned identifier, wherein the similarity score corresponds with how closely a detected object's characteristics match the query;
sorting the returned identifiers by similarity score; and
refining the sorted identifiers by removing identifiers that did not originate from one or more selected cameras in the plurality of cameras during a selected period of time; and
presenting the sorted and refined identifiers as images, wherein each image displays the detected object and is linked to corresponding stored video image data of the detected object.
2. The method of claim 1 , wherein the plurality of objects and object characteristics are detected in real time with the acquisition of the video image data.
3. A system for video image data storage and retrieval, the system comprising:
a plurality of cameras that operate to acquire video image data from a plurality of locations;
an object detection engine that receives the acquired video image data and identifies objects and object characteristics within the video image data;
an object database stored on a computer readable medium that stores the identified objects and object characteristics with an identification of the video image data from which the objects and object characteristics are identified;
a user interface operable by a processor that is configured to receive search parameters and Boolean operators, wherein the search parameters correspond to a user's estimate of an object's characteristics; and
a searcher engine operable by the processor to receive the search parameters and Boolean operators from the user interface and query the object database based upon the search parameters and Boolean operators, receive returned query results comprising at least one object, at least one object characteristic, and at least one identification of the video image data from which the objects and object characteristics are identified;
wherein the returned query results are sorted in an order of a similarity scored that corresponds with how closely a detected object's characteristics matches the query, and
wherein the returned query results are refined by removing results that did not originate from one or more selected cameras in the plurality of cameras during a selected period of time; and
wherein the sorted and refined results are presented as images that display the detected object and that are linked to corresponding stored video image data of the detected object.
4. The system of claim 3 , wherein the object detection engine operates in real time to identify objects and object characteristics within the video image data.
5. The system of claim 4 , further comprising:
an object aggregator that (i) receives the identified objects and object characteristics from the object detection engine, (ii) receives other object characteristics from a source other than the acquired video image data, and (iii) links each identified object to associated object characteristics and other object characteristics, wherein the linked information is stored in the object database.
6. The system of claim 5 , further comprising:
a video database operating on a computer readable medium that stores the video image data in association with each of the identifications of the video image data from which the objects and object characteristics are identified.
7. The system of claim 6 , wherein the user interface presents each of the identifications associated with the objects and object characteristics of the returned results, and the user interface is configured to access and present the video image data from the video database associated with each of the identifications.