PRECISELY LOCATING FEATURES ON GEOSPATIAL IMAGERY

• US 20110123066A9
• Filed: 07/10/2009
• Published: 05/26/2011
• Est. Priority Date: 07/09/2004
• Status: Active Grant

• Current Assignee: Terrago Technologies Incorporated (In-Q-Tel)
• Original Assignee: Terrago Technologies Incorporated (In-Q-Tel)
• Inventors: Knoblock, Craig A., Shahabi, Cyrus, Chen, Ching-Chien, Kapoor, Dipsy
• Granted Patent: US 8,675,995 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06T 2207/10032 Satellite or aerial image; Remote sensing
• CPC Class Codes: G06T 2207/30184 Infrastructure
• CPC Class Codes: G06T 7/75 involving models

Abstract

Methods for locating a feature on geospatial imagery and systems for performing those methods are disclosed. An accuracy level of each of a plurality of geospatial vector datasets available in a database can be determined. Each of the plurality of geospatial vector datasets corresponds to the same spatial region as the geospatial imagery. The geospatial vector dataset having the highest accuracy level may be selected. When the selected geospatial vector dataset and the geospatial imagery are misaligned, the selected geospatial vector dataset is aligned to the geospatial imagery. The location of the feature on the geospatial imagery is then determined based on the selected geospatial vector dataset and outputted via a display device.

Claims

1. A method for locating a feature on geospatial imagery, the method comprising:

selecting a first geospatial vector dataset of a plurality of geospatial vector datasets, the first geospatial vector dataset having a highest accuracy level of each geospatial vector dataset in the plurality of geospatial vector datasets;

aligning the selected geospatial vector dataset to the geospatial imagery;

determining the location of the feature on the geospatial imagery based on the selected geospatial vector dataset; and

outputting the location of the feature via a display device.

2. The method of claim 1, wherein a margin of error in the proximity of the determined location of the feature and an actual location of the feature is dependent, at least in part, on the accuracy level of the first geospatial vector dataset.

3. The method of claim 1, further comprising determining an accuracy level of each of the plurality of geospatial vector datasets stored in memory, each of the plurality of geospatial vector datasets corresponding to the same spatial region as the geospatial imagery.

4. The method of claim 3, wherein the accuracy level of each of the plurality of geospatial vector datasets is based, at least in part, on a type of dataset respectively included in each of the plurality of geospatial vector datasets.

5. The method of claim 3, wherein the plurality of geospatial vector datasets include one or more of a building footprint vector dataset, a parcel vector dataset, or a road vector dataset.

6. The method of claim 1, wherein the aligning is performed when the selected geospatial vector dataset and the geospatial imagery are misaligned.

7. The method of claim 1, wherein the aligning comprises:

detecting a first group of control points in the selected geospatial vector dataset and a second group of control points on the corresponding locations on geospatial imagery; and

distorting the selected geospatial vector dataset such that the first group of control points is aligned with the second group of control points,

8. The method of claim 7, wherein detecting the first group of control points comprises:

locating salient points in the selected geospatial vector dataset; and

designating one or more representative points as control points in the first group, each representative point corresponding to a cluster of salient points.

9. The method of claim 7, wherein detecting the second group of control points comprises:

inferring a template from the selected geospatial vector data based on the first group of control points and the locations, shapes, and directions of surrounding roads or parcels;

inferring pixels of the geospatial imagery corresponding to roads;

matching the shape of the template shape with inferred pixels; and

designating the matched inferred pixels as corresponding control points in the second group.

10. The method of claim 7, wherein the distorting comprises rubber-sheeting the selected geospatial vector dataset.

11. A device for locating a feature on geospatial imagery, the device comprising:

a memory for storing a program;

a processor for executing the program;

an evaluation module stored the memory and executable by the processor to determine an accuracy level of each of a plurality of geospatial vector datasets available in a database and to select the geospatial vector dataset having the highest accuracy level, each of the plurality of geospatial vector datasets corresponding to the same spatial region as the geospatial imagery;

an alignment engine stored in the memory and executable by the processor to align the selected geospatial vector dataset to the geospatial imagery when the selected geospatial vector dataset and the geospatial imagery are misaligned; and

a locator module stored in the memory and executable by the processor to determine the location of the feature on the geospatial imagery based on the selected geospatial vector dataset or based on combined geospatial extents inferred from multiple geospatial vector datasets.

12. The device of claim 11, wherein the plurality of geospatial vector datasets include one or more of a building footprint vector dataset, a parcel vector dataset, or a road vector dataset.

13. The device of claim 11, wherein the evaluation module determines the accuracy level of each of the plurality of geospatial vector based, at least in part, on a type of dataset respectively included in each of the plurality of geospatial vector datasets.

14. The device of claim 11, wherein the alignment engine comprises:

a detection module stored in the memory and executable by the processor to detect a first group of control points in the selected geospatial vector dataset and a second group of control points on the geospatial imagery; and

a distortion module stored in the memory and executable by the processor configured to distort the selected geospatial vector dataset such that the first group of control points is aligned with the second group of control points.

15. The device of claim 14, wherein the detection module can be executed to detect the first group of control points by locating salient points in the selected geospatial vector dataset and designating one or more representative points as control points in the first group, each representative point corresponding to a cluster of salient points.

16. The device of claim 14, wherein the detection module can be executed to detect the second group of control points by:

inferring a template from the selected geospatial vector data based on the first group of control points and the locations, shapes, and directions of surrounding roads or parcels;

inferring pixels of the geospatial imagery corresponding to roads;

matching the shape of the template shape with inferred pixels; and

designating the matched inferred pixels as corresponding control points in the second group.

17. The device of claim 14, wherein the distortion module can be executed to distort the selected geospatial vector dataset by rubber-sheeting the selected geospatial vector dataset.

18. A computer readable storage medium having a program embodied thereon, the program executable by a processor to perform a method for locating a feature on geospatial imagery, the method comprising:

selecting a first geospatial vector dataset of the plurality of geospatial vector datasets, the first geospatial vector dataset having a highest accuracy level of each geospatial vector dataset in the plurality of geospatial vector datasets;

aligning the first geospatial vector dataset to the geospatial imagery when the first geospatial vector dataset and the geospatial imagery are misaligned; and

determining the location of the feature on the geospatial imagery based on the selected geospatial vector dataset.

19. The computer readable storage medium of claim 18, the method further comprising determining an accuracy level of each of the plurality of geospatial vector datasets stored in memory, each of the plurality of geospatial vector datasets corresponding to the same spatial region as the geospatial imagery.

20. The computer readable storage medium of claim 18, wherein the aligning in the method comprises:

detecting a first group of control points in the selected geospatial vector dataset and a second group of control points on the geospatial imagery; and

distorting the selected geospatial vector dataset such that the first group of control points is aligned with the second group of control points.

21. The computer readable storage medium of claim 20, wherein detecting the first group of control points comprises:

locating salient points in the selected geospatial vector dataset; and

designating one or more representative points as control points in the first group, each representative point corresponding to a cluster of salient points.

22. The computer readable storage medium of claim 20, wherein detecting the second group of control points comprises:

inferring a template from the selected geospatial vector data based on the first group of control points and the locations, shapes, and directions of surrounding roads or parcels;

inferring pixels of the geospatial imagery corresponding to roads;

matching the shape of the template shape with inferred pixels; and

designating the matched inferred pixels as corresponding control points in the second group.

23. The computer readable storage medium of claim 20, wherein distorting the selected geospatial vector dataset comprises rubber-sheeting the selected geospatial vector dataset.