GLOBAL-SCALE OBJECT DETECTION USING SATELLITE IMAGERY

• US 20160026848A1
• Filed: 07/27/2015
• Published: 01/28/2016
• Est. Priority Date: 07/25/2014
• Status: Active Grant

• Current Assignee: Maxar Intelligence Incorporated (Galileo Parent, Inc.)
• Original Assignee: DigitalGlobe, Inc. (Galileo Parent, Inc.)
• Inventors: Hamid, Muhammad, O'Hara, Stephen
• Granted Patent: US 9,922,265 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06V 10/462 Salient features, e.g. scale invariant feature transforms [SIFT]
• CPC Class Codes: G06V 20/176 Urban or other man-made structures

Abstract

A system for performing global scale object detection using satellite imagery, comprising an object detection server that receives and analyzes image data to identify objects within an image via a curated computational method, and a curation interface that enables a user to curate image information for use in object identification, and a method for a curated computational method for performing global scale object detection.

Claims

1. A system for performing global scale object detection using satellite imagery, comprising:

an object detection server comprising at least a plurality of programming instructions stored in a memory and operating on a processor of a network-connected computing device and configured to receive at least a plurality of image information from an image database, and configured to analyze at least a portion of the image information, and configured to produce at least a plurality of object vector representations based at least in part on at least a portion of the analysis results; and

a curation interface comprising at least a plurality of programming instructions stored in a memory and operating on a processor of a computing device and configured to receive at least a portion of a plurality of image information, and configured to receive interaction from a human user and to modify at least a portion of the plurality of image information based at least in part on at least a portion of the user interaction.

2. The system of claim 1, further wherein the curation interface is further configured to receive at least a plurality of object vector representations, and is configured to modify at least a portion of the object vector representations based at least in part on at least a portion of the user interaction.

3. A method for performing global scale object detection using satellite imagery, comprising the steps of:

querying, using an object detection server comprising at least a plurality of programming instructions stored in a memory and operating on a processor of a network-connected computing device and configured to receive at least a plurality of image information from an image database, and configured to analyze at least a portion of the image information, and configured to produce at least a plurality of object detection identifiers based at least in part on at least a portion of the analysis results, a database for a plurality of image information;

extracting a plurality of scale-invariant transform descriptors based at least in part on at least a portion of the plurality of image information;

performing k-means clustering on at least a portion of the plurality of image information;

producing a plurality of locally-constrained linear codes based at least in part on at least a portion of the plurality of image information; and

performing spatial pooling based at least in part on at least a portion of the plurality of locally-constrained linear codes to produce a plurality of object vector representations, the object vector representations corresponding to at least a plurality of objects identified within at least a portion of the plurality of image information.