Adaptive illumination control via activity classification
Disclosed herein are embodiments for implementing active illumination control via activity classification. An embodiment includes a processor configured to perform operations comprising receiving first sensor data generated by at least one of the plurality of sensors. Based at least in part on the first sensor data, the processor may select a first lighting profile, and instruct the light-emitting element to emit light in accordance with the first lighting profile. The processor may be further configured to receive second sensor data generated by the at least one of the plurality of sensors and to update an activity classification stored in a memory, in response to the second sensor data being different from the first sensor data. The processor may transition from the first lighting profile to a second lighting profile, in response to the updating, and may instruct the light-emitting element to emit light in accordance with the second lighting profile.
1 . A mobile adaptive illumination device, comprising:
a memory configured to store a plurality of lighting profiles; and
a processor configured to execute instructions stored in the memory, the instructions, when executed by the processor, configuring the processor to:
instruct a light-emitting element to emit light in accordance with a first lighting profile selected from among the plurality of lighting profiles based upon first sensor data generated by at least one sensor from among a plurality of sensors,
transition, from the first lighting profile to a second lighting profile from among the plurality of lighting profiles in response to second sensor data generated by the at least one sensor being different from the first sensor data, and
instruct the light-emitting element to emit light in accordance with the second lighting profile.
2 . The mobile adaptive illumination device of claim 1 , wherein the plurality of lighting profiles comprise:
different electrical input characteristics for the light-emitting element;
different luminous flux or luminous intensity values for the light-emitting element;
different ratios of light output to calculated or detected ambient light for the light-emitting element; or
different ranges of values or thresholds for specific events for the light-emitting element.
3 . The mobile adaptive illumination device of claim 1 , wherein a difference between the first sensor data and the second sensor data signifies a change in an environmental condition detected by the at least one sensor.
4 . The mobile adaptive illumination device of claim 1 , wherein the instructions, when executed by the processor, configure the processor to:
determine a classification of an activity in which a wearable version of the mobile adaptive illumination device is being used for emitting the light in response to the first sensor data;
update the classification in response to the second sensor data being different from the first sensor data;
predict a second lighting profile from among the plurality of lighting profiles in response the updated classification; and
transition from the first lighting profile to the second lighting profile.
5 . The mobile adaptive illumination device of claim 4 , wherein the instructions, when executed by the processor, configure the processor to execute at least one machine learning (ML) model to determine the classification and to predict the second lighting profile, the at least one ML model being trained from at least one training set stored in the memory.
6 . The mobile adaptive illumination device of claim 5 , wherein the at least one training set stored in the memory comprises:
a classification training set configured to train the at least one ML model to determine the classification; and
a prediction training set configured to train the at least one ML model to predict the second lighting profile.
7 . The mobile adaptive illumination device of claim 1 , wherein the instructions, when executed by the processor, configure the processor to substitute the first lighting profile with the second lighting profile in the memory to transition from the first lighting profile to the second lighting profile.
8 . A method for adaptively controlling light emitted by a light-emitting element of a mobile adaptive illumination device, the method comprising:
instructing the light-emitting element to emit the light in accordance with a first lighting profile selected from among a plurality of lighting profiles based upon first sensor data generated by at least one sensor from among a plurality of sensors;
transitioning from the first lighting profile to a second lighting profile from among the plurality of lighting profiles in response to second sensor data generated by the at least one sensor being different from the first sensor data; and
instructing the light-emitting element to emit light in accordance with the second lighting profile.
9 . The method of claim 8 , wherein the plurality of lighting profiles comprise:
different electrical input characteristics for the light-emitting element;
different luminous flux or luminous intensity values for the light-emitting element;
different ratios of light output to calculated or detected ambient light for the light-emitting element; or
different ranges of values or thresholds for specific events for the light-emitting element.
10 . The method of claim 8 , wherein a difference between the first sensor data and the second sensor data signifies a change in an environmental condition detected by the at least one sensor.
11 . The method of claim 8 , wherein the transitioning comprises:
determining a classification of an activity in which the light-emitting element is being used for emitting the light in response to the first sensor data;
updating the classification in response to the second sensor data being different from the first sensor data;
predicting a second lighting profile from among the plurality of lighting profiles in response to the updated classification; and
transitioning from the first lighting profile to the second lighting profile.
12 . The method of claim 11 , wherein the transitioning further comprises executing at least one machine learning (ML) model to determine the classification and to predict the second lighting profile, the at least one ML model being trained from at least one training set stored in a memory.
13 . The method of claim 12 , wherein the at least one training set stored in the memory comprises:
a classification training set configured to train the at least one ML model to determine the classification; and
a prediction training set configured to train the at least one ML model to predict the second lighting profile.
14 . The method of claim 8 , wherein the transitioning comprises substituting the first lighting profile with the second lighting profile in a memory to transition from the first lighting profile to the second lighting profile.
15 . A system for adaptively controlling light, the system comprising:
a light-emitting element configured to emit the light; and
a processor configured to:
instruct the light-emitting element to emit the light in accordance with a first lighting profile selected from among a plurality of lighting profiles based upon first sensor data generated by at least one sensor from among a plurality of sensors,
transition from the first lighting profile to a second lighting profile from among the plurality of lighting profiles in response to second sensor data generated by the at least one sensor being different from the first sensor data, and
instruct the light-emitting element to emit light in accordance with the second lighting profile.
16 . The system of claim 15 , wherein a difference between the first sensor data and the second sensor data signifies a change in an environmental condition detected by the at least one sensor.
17 . The system of claim 15 , wherein the processor is further configured to:
determine a classification of an activity in which the system is being used for emitting the light in response to the first sensor data;
update the classification in response to the second sensor data being different from the first sensor data;
predict the second lighting profile from among the plurality of lighting profiles in response the updated classification; and
transition from the first lighting profile to the second lighting profile.
18 . The system of claim 17 , wherein the processor is further configured execute at least one machine learning (ML) model to determine the classification and to predict the second lighting profile, the at least one ML model being trained from at least one training set stored in a memory.
19 . The system of claim 18 , wherein the at least one training set stored in a memory comprises a classification training set configured to train the at least one ML model to determine the classification and a prediction training set configured to train the at least one ML model to predict the second lighting profile.
20 . The system of claim 15 , wherein the processor is further configured substitute the first lighting profile with the second lighting profile in a memory to transition from the first lighting profile to the second lighting profile.