Automated tagging for landmark identification

• US 8,340,438 B2
• Filed: 12/17/2009
• Issued: 12/25/2012
• Est. Priority Date: 12/17/2009
• Status: Active Grant

• Current Assignee: Deere & Company
• Original Assignee: Deere & Company
• Inventors: Anderson, Noel Wayne
• Primary Examiner(s): CHAWAN, SHEELA C
• Application Number:
  US12/640,898
• Publication Number:
  US 20110150348A1
• Time in Patent Office: 1,104 Days
• Field of Search: 382/173, 382/219, 382/224, 382/190, 382/305, 455/517, 455/456.1, 455/435.1, 455/410, 455/558, 455/551, 455/433, 455/411, 455/41.2, 701/123, 701/211, 701/301, 704/238, 704/250, 700/248, 326/37, 326/39, 326/10, 326/9, 370/335, 370/310, 370/328, 370/329, 348/E7.086
• US Class Current: 382/224
• CPC Class Codes: G01C 11/06 by comparison of two or more pictures of the same area
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G05D 1/0251 extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision stereoscopic image analysis H04N13/00; depth recovery from images G06T7/593
• CPC Class Codes: G05D 1/0255 using acoustic signals, e.g. ultra-sonic singals sonar systems designed for anti-collision purposes G01S15/93
• CPC Class Codes: G05D 1/027 comprising intertial navigation means, e.g. azimuth detector inertial navigation G01C21/16; inertial navigation combined with non-inertial navigation instruments G01C21/165
• CPC Class Codes: G05D 1/0272 comprising means for registering the travel distance, e.g. revolutions of wheels measuring distance traversed on the ground by vehicles, e.g. using odometers G01C22/00
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: G06F 18/2178 based on feedback of a supervisor
• CPC Class Codes: G06V 20/10 Terrestrial scenes scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59

Abstract

The different illustrative embodiments provide a method for identifying landmarks in an image. An image of a worksite is received. The image is analyzed to determine a suggested identity of a worksite feature in the image. The suggested identity of the worksite feature is sent over a communications unit. A confirmation of the suggested identity of the worksite feature is received to form a confirmed identity. The confirmed identity and a number of attributes associated with the confirmed identity is stored in a database.

Claims

1. A method for identifying landmarks in an image, the method comprising:

receiving an image of a worksite;

analyzing the image to determine a suggested identity of a worksite feature in the image;

sending the suggested identity of the worksite feature over a communications unit;

receiving a confirmation of the suggested identity of the worksite feature to form a confirmed identity; and

storing the confirmed identity and a location associated with the worksite feature in a database, wherein analyzing the image to determine the suggested identity of the worksite feature in the image comprises obtaining a number of worksite images, identifying a common feature in at least two of the number of worksite images, and identifying a relative location of the common feature identified in the at least two of the number of worksite images.

2. The method of claim 1, wherein the image is received from an environmental data collection system which is moved to a plurality of environment data collection locations by at least one of an autonomous vehicle, a human, an animal, or a human controlled vehicle.

3. The method of claim 1, wherein the confirmation of the suggested identity of the worksite feature is received from a user via a user interface.

4. The method of claim 1, wherein the database comprises a number of candidate objects and object attributes associated with each candidate object of the number of candidate objects, and further comprising:

responsive to receiving the image of the worksite, accessing the database to select the suggested identity of the worksite feature from the number of candidate objects using the object attributes.

5. The method of claim 4, wherein the step of analyzing the image comprises:

selecting a given candidate object from the number of candidate objects that has a highest number of shared attributes with the image to determine the suggested identity of the worksite feature.

6. The method of claim 5, wherein the database further comprises a scaled worksite map comprising additional information pertaining to the worksite feature that is provided by a user using the user interface.

7. The method of claim 1, further comprising:

associating the confirmed identity and a number of attributes for the worksite feature with the location on a worksite map.

8. The method of claim 1, further comprising:

determining whether scaling information is available for the common feature identified; and

responsive to a determination that scaling information is available, applying the scaling information to provide distance information on the worksite and a size of the common feature.

9. A system for identifying landmarks in an image, the system comprising:

a worksite features database;

a user interface configured to interact with a user; and

a data processing system configured to execute a data classification process to analyze an image to determine a suggested identity of a worksite feature in the image using the worksite features database, send the suggested identity of the worksite feature over a communications unit, receive a confirmation of the suggested identity of the worksite feature to form a confirmed identity, and store the confirmed identity and a number of attributes associated with the confirmed identity in the worksite features database, wherein the data classification process to analyze the image to determine the suggested identity of the worksite feature in the image comprises obtain a number of worksite images, identify a common feature in at least two of the number of worksite images, and identify a relative location of the common feature identified in the at least two of the number of worksite images.

10. The system of claim 9, wherein the image is received from an environmental data collection system which is moved to a plurality of environment data collection locations by at least one of an autonomous vehicle, a human, an animal, or a human controlled vehicle.

11. The system of claim 9, wherein the confirmation of the suggested identity of the worksite feature is received from a user via the user interface.

12. The system of claim 9, wherein the worksite features database comprises a number of candidate objects and object attributes associated with each candidate object of the number of candidate objects that is accessed to determine the suggested identity of the worksite feature from the number of candidate objects using the object attributes.

13. The system of claim 12, where the data processing system is further configured to execute the data classification process to select a given candidate object from the number of candidate objects that has a highest number of shared attributes with the image to determine the suggested identity of the worksite feature.

14. The system of claim 9, wherein the data processing system is further configured to execute the data classification process to associate the confirmed identity and the number of attributes for the worksite feature with a location on a worksite map.

15. A method for identifying worksite features by a system comprising a data processor and memory, the method comprising:

the system obtaining a number of worksite images;

the system identifying a common feature in at least two of the number of worksite images;

the system identifying a relative location of the common feature identified;

the system applying scaling information to a worksite map to provide distance information for the worksite and a size of the common feature identified, wherein the number of worksite images are compiled by an image sequencer to generate a three dimensional model of the worksite, and wherein the image sequencer extracts a three dimensional object from the three dimensional model as the common feature to identify a relative location of the common feature.

16. The method of claim 15, further comprising:

determining whether there are any remaining common features in the number of worksite images; and

responsive to a determination that there are remaining common features, identifying a next common feature in at least two of the number of worksite images.

17. The method of claim 15, wherein the number of worksite images is obtained from a vision system of an autonomous vehicle.

18. The method of claim 15, wherein the number of worksite images is obtained from a human operator over a user interface.