Information processing apparatus, information processing method, and information processing program

1. An information processing apparatus comprising:

at least one first processor configured to carry out a first process on data input from at least one sensor to produce first processed data;

a selector configured to select, according to a first predetermined condition, at least one of a plurality of second processes; and

at least one second processor configured to receive the first processed data from the at least one first processor and to carry out the selected at least one of the plurality of second processes on the first processed data to produce second processed data, each process of the plurality of second processes having a lower processing load than the first process.

2. The information processing apparatus according to claim 1 , wherein

the selector is configured to select at least one of the plurality of second processes according to a peripheral environmental condition as the first predetermined condition.

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

the at least one first processor is further configured to extract one or more features of the data input from the at least one sensor based, at least in part, on a feature extraction parameter that has been learned by a machine learning process.

4. The information processing apparatus according to claim 3 , further comprising:

at least one storage unit configured to store a plurality of feature extraction parameters different from each other,

wherein the at least one first processor is further configured to select, according to a second predetermined condition, the feature extraction parameter from the plurality of feature extraction parameters stored in the at least one storage unit.

5. The information processing apparatus according to claim 4 , wherein

the feature extraction parameter is selected from the plurality of feature extraction parameters stored in the at least one storage unit according to a peripheral environmental condition as the second predetermined condition.

6. The information processing apparatus according to claim 5 , wherein

the feature extraction parameter is selected from the plurality of feature extraction parameters stored in the at least one storage unit according to weather information.

7. The information processing apparatus according to claim 1 , wherein

the at least one second processor is further configured to determine an object detected by the at least one sensor based, at least in part, on a determination parameter that has been learned by a machine learning process.

8. The information processing apparatus according to claim 7 , further comprising:

at least one storage unit configured to store a plurality of determination parameters different from each other,

wherein the at least one second processor is further configured to select, according to the first predetermined condition, the determination parameter from the plurality of determination parameters stored in the at least one storage unit.

9. The information processing apparatus according to claim 7 , wherein

the at least one sensor includes a first sensor and a second sensor, and

the at least one first processor is further configured to:

receive first data from the first sensor; and

receive second data from the second sensor;

carry out the first process on the first data and the second data to produce the first processed data; and

provide the first processed data to the at least one second processor.

10. The information processing apparatus according to claim 9 , wherein

the first sensor is an image sensor, and

the second sensor is at least one of a millimeter-wave radar, a light detection and ranging sensor, or an ultrasonic sensor.

11. The information processing apparatus according to claim 7 , wherein

the at least one second processor is configured to determine an object detected by the at least one sensor based, at least in part, on a determination model that has been trained by a machine learning process.

12. The information processing apparatus according to claim 1 , wherein

the selector is configured to select at least one of the plurality of second processes according to a time of day as the first predetermined condition.

13. The information processing apparatus according to claim 1 , wherein the information processing apparatus is mounted on a vehicle.

14. The information processing apparatus according to claim 13 , wherein

the at least one second processor is further configured to determine an object detected by the at least one sensor based, at least in part, on a determination parameter that has been learned by a machine learning process, and

output a signal based, at least in part, on the determined object to at least one of an Advanced Driver Assistance System or an automatic drive system of the vehicle.

15. The information processing apparatus according to claim 1 , wherein

the at least one first processor comprises an FPGA, and

the at least one second processor comprises at least one of an FPGA, a CPU, a DSP, or a GPU.

16. The information processing apparatus according to claim 1 , wherein

the first process comprises a multi-dimensional product-sum operation, and

the second process comprises a classification of an object or recurrence.

17. The information processing apparatus according to claim 1 , wherein the plurality of second processes are different from each other.

18. An information processing method that is carried out by a computer, the method comprising:

performing a first process on data input from at least one sensor to produce first processed data;

selecting, according to a predetermined condition, at least one of a plurality of second processes, wherein the plurality of second processes are different from each other and each process of the plurality of second processes has a lower processing load than the first process; and

performing the selected at least one of the plurality of second processes on the first processed data to produce second processed data.

19. At least one non-transitory computer-readable storage medium storing processor executable instructions that, when executed by at least one computer hardware processor, cause the at least on computer hardware processor to preform:

a first processing sequence that performs a first process on data input from at least one sensor to produce first processed data;

a selecting sequence that selects, according to a predetermined condition, at least one of a plurality of second processes, wherein the plurality of second processes are different from each other and each process of the plurality of second processes has a lower processing load than the first process; and

a second processing sequence that performs the selected at least one of the plurality of second processes on the first processed data to produce second processed data.