Granted Patent B2

US 10,657,418 · App. 15/854,803 · Granted May 19, 2020

Inventor: Mattias Marder (Haifa, IL)

Assignee: International Business Machines Corporation

G06K9/6256G06K9/00624G06K9/00771G06K9/18G06K9/6267G06K9/78G06N20/00G06K2209/01

Abstract

Claims (57)

1. A computer-implemented method for configuring devices comprising:

monitoring an area with a device comprising a camera and a computing device;

capturing data at the device, wherein the captured data includes at least one image or video captured by the camera;

transmitting the captured data to a remote system;

receiving configuration data at the device, wherein the configuration data has been generated by processing the captured data at the remote system using a plurality of different machine learning techniques and generating the configuration data based on at least one of the plurality of different machine learning techniques, wherein the configuration data includes a machine learning model for detecting at least one object in the image or video; and

configuring the device using the received configuration data; and

detecting, at the device, at least one object using the machine learning model during monitoring of the area.

2. The method of claim 1 , further comprising:

repeating the capturing and transmitting; and

wherein the received configuration data was generated based on statistics related to detection of objects by each of the plurality of different machine learning techniques.

3. The method of claim 2 , wherein the received configuration data has further been generated based on at least one identified schema of object locations or identities that was identified based on the generated statistics related to detection of objects by each of the plurality of different machine learning techniques and by generating a data set including at least one of: data relating to objects detected up to a time at which the data set was generated and data relating to the objects included in the identified schema.

4. The method of claim 1 , wherein the objects to be detected include at least one of: products on store shelves, components to be assembled, vehicles or vessels to be tracked, humans or animals to be recognized or tracked.

5. The method of claim 1 , wherein the received configuration data includes information relating to at least some of a plurality of objects in an area generated by:

determining, from an image of the area including the plurality of objects, an indicator of an object and any gaps between objects;

obtaining information relating to an object associated with an indicator of an object;

determining if a gap is present in relation to the associated object;

determining a number of instances of an object in the area; and

generating information relating to at least some of the plurality of objects in the area based on the obtained information relating to the object associated with the indicator of the object, the presence of gaps between objects, and the number of instances of the object in the area.

6. A computer program product for configuring devices, the computer program product comprising a non-transitory computer readable storage having program instructions embodied therewith, the program instructions executable by a computer, to cause the computer to perform a method comprising:

monitoring an area with a device comprising a camera and a computing device;

capturing data at the device, wherein the captured data includes at least one image or video captured by the camera;

transmitting the captured data to a remote system;

receiving configuration data at the device, wherein the configuration data has been generated by processing the captured data at the remote system using a plurality of different machine learning techniques and generating the configuration data based on at least one of the plurality of different machine learning techniques, wherein the configuration data includes a machine learning model for detecting at least one object in the image or video; and

configuring the device using the received configuration data; and

detecting, at the device, at least one object using the machine learning model during monitoring of the area.

7. The computer program product of claim 6 , further comprising:

repeating the capturing and transmitting; and

wherein the received configuration data was generated based on statistics related to detection of objects by each of the plurality of different machine learning techniques.

8. The computer program product of claim 7 , wherein the received configuration data has further been generated based on at least one identified schema of object locations or identities that was identified based on the generated statistics related to detection of objects by each of the plurality of different machine learning techniques and by generating a data set including at least one of: data relating to objects detected up to a time at which the data set was generated and data relating to the objects included in the identified schema.

9. The computer program product of claim 6 , wherein the objects to be detected include at least one of: products on store shelves, components to be assembled, vehicles or vessels to be tracked, humans or animals to be recognized or tracked.

10. The computer program product of claim 6 , wherein the received configuration data includes information relating to at least some of a plurality of objects in an area generated by:

determining, from an image of the area including the plurality of objects, an indicator of an object and any gaps between objects;

obtaining information relating to an object associated with an indicator of an object;

determining if a gap is present in relation to the associated object;

determining a number of instances of an object in the area; and

generating information relating to at least some of the plurality of objects in the area based on the obtained information relating to the object associated with the indicator of the object, the presence of gaps between objects, and the number of instances of the object in the area.

11. A system for detecting objects, the system comprising a camera and a computing device, the computing device comprising a processor, memory accessible by the processor, and computer program instructions stored in the memory and executable by the processor to perform:

monitoring an area with the system;

capturing data at the system, wherein the captured data includes at least one image or video captured by the camera;

transmitting the captured data to a remote system;

receiving configuration data at the device, wherein the configuration data has been generated by processing the captured data at the remote system using a plurality of different machine learning techniques and generating the configuration data based on at least one of the plurality of different machine learning techniques, wherein the configuration data includes a machine learning model for detecting at least one object in the image or video; and

configuring the device using the received configuration data; and

detecting, at the device, at least one object using the machine learning model during monitoring of the area.

12. The system of claim 11 , further comprising:

repeating the capturing and transmitting; and

wherein the received configuration data was generated based on statistics related to detection of objects by each of the plurality of different machine learning techniques.

13. The system of claim 12 , wherein the received configuration data has further been generated based on at least one identified schema of object locations or identities that was identified based on the generated statistics related to detection of objects by each of the plurality of different machine learning techniques and by generating a data set including at least one of: data relating to objects detected up to a time at which the data set was generated and data relating to the objects included in the identified schema.

14. The system of claim 11 , wherein the objects to be detected include at least one of: products on store shelves, components to be assembled, vehicles or vessels to be tracked, humans or animals to be recognized or tracked.

15. The system of claim 11 , wherein the received configuration data includes information relating to at least some of a plurality of objects in an area generated by:

determining, from an image of the area including the plurality of objects, an indicator of an object and any gaps between objects;

obtaining information relating to an object associated with an indicator of an object;

determining if a gap is present in relation to the associated object;

determining a number of instances of an object in the area; and

generating information relating to at least some of the plurality of objects in the area based on the obtained information relating to the object associated with the indicator of the object, the presence of gaps between objects, and the number of instances of the object in the area.

16. The method of claim 1 , wherein the machine learning model comprises a unique dataset covering the monitored area.

17. The computer program product of claim 6 , wherein the machine learning model comprises a unique dataset covering the monitored area.

18. The system of claim 11 , wherein the machine learning model comprises a unique dataset covering the monitored area.

Assignments (1)

Continuity (1)

Cited By (16)

US 12,198,396 US 12,216,610 US 12,223,428 US 12,236,689 US 12,307,350 US 12,346,816 US 12,367,405 US 12,455,739 US 12,462,575 US 12,522,243 US 12,536,131 US 12,554,467 US 12,591,240 US 12,618,976 US 12,623,691 US 12,709,294