Information processing device and information processing method

1 . An information processing device, comprising:

a control unit configured to:

control a sensor unit to capture an image based on a set of parameters of the sensor unit;

recognize the captured image based on a set of learning models;

collect data to update at least one of the set of learning models or the set of parameters;

update the at least one of the set of learning models or the set of parameters based on the data;

generate a first distance image from the captured image based on the updated set of learning models;

control a distance measuring unit to generate a second distance image;

evaluate a recognition result based on the first distance image, the second distance image, and the at least one of the updated set of parameters or the updated set of learning models, wherein the recognition result is associated with the recognition of the captured image; and

recognize the captured image with the at least one of the updated set of parameters or the updated set of learning models, based on the evaluation of the recognition result.

2 . The information processing device according to claim 1 , wherein the set of parameters includes at least one of an exposure time, a shutter speed, an analog gain, a filter processing operation, or gradation correction of the sensor unit.

3 . The information processing device according to claim 1 , wherein

the control unit is further configured to collect the data based on at least one of an environment of the sensor unit, an attribute of a user, or specification of the information processing device,

the sensor unit captures the image in the environment, and

the sensor unit captures the image based on a user input associated with the user.

4 . The information processing device according to claim 1 , wherein the control unit is further configured to collect the data based on change of at least one of a state of the information processing device or the set of parameters of the sensor unit.

5 . The information processing device according to claim 1 , wherein

the control unit is further configured to update the at least one of the set of parameters or the set of learning models model at a specific time, and

the specific time corresponds to at least one of power of the information processing device or a delay for the recognition.

6 . The information processing device according to claim 5 , wherein the control unit is further configured to:

execute a first update process on the at least one of the set of parameters or the set of learning models at a first time instant, wherein the first update process is executed at the first time instant based on a first condition; and

execute a second update process on the at least one of the set of parameters or the set of learning models at a second time instant, wherein the second update process is executed at the second time instant based on a second condition.

7 . The information processing device according to claim 6 , wherein the control unit is further configured to:

execute the first update process based on a first learning model of the set of learning models; and

execute the second update process based on a second learning model of the set of learning models, wherein the second learning model is larger than the first learning model.

8 . The information processing device according to claim 1 , wherein

the control unit is further configured to evaluate the at least one of the updated set of parameters or the updated set of learning models based on evaluation data,

the evaluation data corresponds to at least one of an environment of the sensor unit or an attribute of a user,

the sensor unit captures the image in the environment, and

the sensor unit captures the image based on a user input associated with the user.

9 . The information processing device according to claim 8 , wherein

the evaluation data includes image data captured by the sensor unit, and

the image data includes correct answer information associated with recognition of the image data.

10 . The information processing device according to claim 8 , wherein the control unit is further configured to:

obtain a first recognition result based on recognition of the evaluation data by a server-side learning model, wherein

the first recognition result is different from the recognition result, and

the server-side learning model is generated by a server device based on the data;

recognize the evaluation data based on the at least one of the updated set of parameters or the updated set of learning models;

generate a second recognition result based on the recognition of the evaluation data, wherein the second recognition result corresponds to the recognition result; and

evaluate the second recognition result based on the first recognition result.

11 . The information processing device according to claim 10 , wherein a structure of the server-side learning model is one of same as a structure of the set of learning models or larger than the structure of the set of learning models.

12 . An information processing method, comprising:

controlling a sensor unit to capture an image based on a set of parameters of the sensor unit;

recognizing the captured image based on a set of learning models;

collecting data to update at least one of the set of learning models or the set of parameters;

updating the at least one of the set of learning models or the set of parameters based on the data;

generating a first distance image from the captured image based on the updated set of learning models;

controlling a distance measuring unit to generate a second distance image;

evaluating a recognition result based on the first distance image, the second distance image, and the at least one of the updated set of parameters or the updated set of learning models, wherein the recognition result is associated with the recognition of the captured image; and

recognizing the captured image with the at least one of the updated set of parameters or the updated set of learning models, based on the evaluation of the recognition result.

13 . A non-transitory computer-readable medium having stored thereon, computer-executable instructions which, when executed by a processor, cause the processor to execute operations, the operations comprising:

controlling a sensor unit to capture an image based on a set of parameters of the sensor unit;

recognizing the captured image based on a set of learning models;

collecting data to update at least one of the set of learning models or the set of parameters;

updating the at least one of the set of learning models or the set of parameters based on the data;

generating a first distance image from the captured image based on the updated set of learning models;

controlling a distance measuring unit to generate a second distance image;

evaluating a recognition result based on the first distance image, the second distance image, and the at least one of the updated set of parameters or the updated set of learning models, wherein the recognition result is associated with the recognition of the captured image; and

recognizing the captured image with the at least one of the updated set of parameters or the updated set of learning models based on the evaluation of the recognition result.