Tracking product items in an automated-checkout store

1. A method for tracking a product item in an automated-checkout store, comprising:

receiving, by a computer system from a plurality of sensors including at least one or more cameras, one or more weight sensors, one or more pressure sensors, and one or more capacitive sensors, data collected by the sensors;

identifying, by the computer system, an account associated with a person who enters the store;

receiving, by the computer system, data on movement of the product item collected by the plurality of the sensors;

determining, by the computer system, an interaction between the person and the product item based on the data collected by the plurality of the sensors;

extracting, by the computer system, from the data received from the plurality of the sensors, a plurality of features associated with the product item, wherein the features comprise a conductivity, a color, a position, and a surface force image, the conductivity is used to determine a type of material that makes up at least a part of the product, and the surface force image is used to determine a footprint of the product that includes a shape of a bottom surface of the product;

determining, by the computer system, using a machine-learning model, an identity of the product item based on the extracted features including the conductivity, the color, the position, and the surface force image, wherein the machine-learning model is trained based on training data collected from the plurality of the sensors;

storing, by the computer system, information associating the product item with the person; and

deducting, by the computer system, a payment amount from the identified account, wherein the payment amount is based on a price of the product item associated with the person.

2. The method of claim 1 , wherein one or more of the sensors are affixed to one or more structures in the automated-checkout store, the one or more structures comprising any of:

a ceiling;

a floor;

a shelf;

a rack; and

a refrigerator.

3. The method of claim 1 , wherein the plurality of sensors further comprise one or more of:

a force sensor;

a vibration sensor;

a proximity sensor; and

a resistance-based film sensor.

4. The method of claim 1 , further comprising:

determining, by the computer system based on the data received from a first sensor of the plurality of the sensors, a first identity for the product item associated with a first confidence score;

determining, by the computer system based on the data received from a second sensor of the plurality of the sensors, a second identity for the product item associated with a second confidence score; and

selecting one of the first identity and the second identity as the identity of the product item based on a comparison of the first confidence score and the second confidence score.

5. The method of claim 1 , further comprising:

obtaining, by the computer system based on the data received from the plurality of the sensors, a plurality of values associated with a characteristic of the product item, wherein each of the values is determined based on the data received from one of the plurality of the sensors; and

determining, by the computer system, a final value corresponding to the characteristic based at least in part on a weighted average of the plurality of values.

6. The method of claim 1 , further comprising:

determining, by the computer system based on the data received from one or more of the plurality of the sensors, a movement path within the automated-checkout store associated with the person.

7. The method of claim 1 , wherein the determining an interaction between the person and the product item comprises:

determining, based on the data received from one or more of the plurality of the sensors, that the person is located in proximity to the product item in a period of time;

detecting one or more movements of a hand of the person with respect to the product item; and

determining the interaction based on the one or more detected movements.

8. A system for tracking a product item in an automated-checkout store comprising a computer system and a plurality of sensors including at least one or more cameras, one or more weight sensors, one or more pressure sensors, and one or more capacitive sensors, the computer system comprising a processor and a non-transitory computer-readable storage medium storing instructions executable by the processor to cause the system to perform operations comprising:

receiving, by the computer system from the plurality of the sensors, data collected by the plurality of the sensors;

identifying, by the computer system, an account associated with a person who enters the store;

receiving, by the computer system, data on movement of the product item collected by the plurality of the sensors;

determining, by the computer system, an interaction between the person and the product item based on the data collected by the plurality of the sensors;

extracting, by the computer system, from the data received from the one or more plurality of the sensors, a plurality of features associated with the product item, wherein the features comprise a conductivity, a color, a position, and a surface force image, the conductivity is used to determine a type of material that makes up at least a part of the product, and the surface force image is used to determine a footprint of the product that includes a shape of a bottom surface of the product;

determining, by the computer system, using a machine-learning model, an identity of the product item based on the extracted features including the conductivity, the color, the position, and the surface force image, wherein the machine-learning model is trained based on training data collected from the plurality of the sensors;

storing, by the computer system, information associating the product item with the person; and

deducting, by the computer system, a payment amount from the identified account, wherein the payment amount is based on a price of the product item associated with the person.

9. The system of claim 8 , wherein one or more of the sensors are affixed to one or more structures in the automated-checkout store, the one or more structures comprising any of:

a ceiling;

a floor;

a shelf;

a rack; and

a refrigerator.

10. The system of claim 8 , wherein the plurality of sensors further comprise one or more of:

a force sensor;

a vibration sensor;

a proximity sensor; and

a resistance-based film sensor.

11. The system of claim 8 , wherein the operations further comprise:

determining, by the computer system based on the data received from a first sensor of the plurality of the sensors, a first identity for the product item associated with a first confidence score;

determining, by the computer system based on the data received from a second sensor of the plurality of the sensors, a second identity for the product item associated with a second confidence score; and

selecting one of the first identity and the second identity as the identity of the product item based on a comparison of the first confidence score and the second confidence score.

12. The system of claim 8 , wherein the operations further comprise:

obtaining, by the computer system based on the data received from the plurality of the sensors, a plurality of values associated with a characteristic of the product item, wherein each of the values is determined based on the data received from one of the plurality of the sensors; and

determining, by the computer system, a final value corresponding to the characteristic based at least in part on a weighted average of the plurality of values.

13. The system of claim 8 , wherein the operations further comprise:

determining, by the computer system based on the data received from one or more of the plurality of the sensors, a movement path within the automated-checkout store associated with the person.

14. The system of claim 8 , wherein the determining an interaction between the person and the product item comprises:

determining, based on the data received from one or more of the plurality of the sensors, that the person is located in proximity to the product item in a period of time;

detecting one or more movements of a hand of the person with respect to the product item; and

determining the interaction based on the one or more detected movements.

15. A non-transitory computer-readable storage medium for tracking a product item in an automated-checkout store, configured with instructions executable by one or more processors to cause the one or more processors to perform operations comprising:

receiving, from a plurality of sensors including at least one or more cameras, one or more weight sensors, one or more pressure sensors, and one or more capacitive sensors, data collected by the sensors;

identifying an account associated with a person who enters the store;

receiving, by the computer system, data on movement of the product item collected by the plurality of the sensors;

determining an interaction between the person and the product item based on the data collected by the plurality of the sensors;

extracting, by the computer system, from the data received from the plurality of the sensors, a plurality of features associated with the product item, wherein the features comprise a conductivity, a color, a position, and a surface force image, the conductivity is used to determine a type of material that makes up at least a part of the product, and the surface force image is used to determine a footprint of the product that includes a shape of a bottom surface of the product;

determining, by the computer system, using a machine-learning model, an identity of the product item based on the extracted features including the conductivity, the color, the position, and the surface force image, wherein the machine-learning model is trained based on training data collected from the plurality of the sensors;

storing information associating the product item with the person; and

deducting a payment amount from the identified account, wherein the payment amount is based on a price of the product item associated with the person.

16. The non-transitory computer-readable storage medium of claim 15 , wherein the operations further comprise:

determining, by the computer system based on the data received from one or more of the plurality of the sensors, a movement path within the automated-checkout store associated with the person.

17. The non-transitory computer-readable storage medium of claim 15 , wherein the determining an interaction between the person and the product item comprises:

determining, based on the data received from the plurality of the sensors, that the person is located in proximity to the product item in a period of time;

detecting one or more movements of a hand of the person with respect to the product item; and

determining the interaction based on the one or more detected movements.

18. The non-transitory computer-readable storage medium of claim 15 , wherein the plurality of sensors further comprise any of:

a force sensor;

a vibration sensor;

a proximity sensor; and

a resistance-based film sensor.

19. The non-transitory computer-readable storage medium of claim 15 , wherein the operations further comprise:

determining, by the computer system based on the data received from a first sensor of the plurality of the sensors, a first identity for the product item associated with a first confidence score;

determining, by the computer system based on the data received from a second sensor of the plurality of the sensors, a second identity for the product item associated with a second confidence score; and

selecting one of the first identity and the second identity as the identity of the product item based on a comparison of the first confidence score and the second confidence score.

20. The non-transitory computer-readable storage medium of claim 15 , wherein the operations further comprise:

obtaining, by the computer system based on the data received from the plurality of the sensors, a plurality of values associated with a characteristic of the product item, wherein each of the values is determined based on the data received from one of the plurality of the sensors; and

determining, by the computer system, a final value corresponding to the characteristic based at least in part on a weighted average of the plurality of values.