Apparatus and methods for predicting state of visibility for a road object

1. A non-transitory computer-readable storage medium having computer program code instructions stored therein, the computer program code instructions, when executed by at least one processor, cause the at least one processor to:

receive road sign attribute data indicating at least one attribute of a road sign;

receive weather forecast data indicating a weather forecast of a location in which the road sign is disposed; and

using the road sign attribute data and the weather forecast data, identify a state of visibility for the road sign.

2. The non-transitory computer-readable storage medium of claim 1 , wherein the at least one attribute is the location of the road sign, an orientation of the road sign, a size of the road sign, a classification of the road sign, yaw, pitch, and roll angles of the road sign, a height of the road sign, a color of the road sign, or a combination thereof.

3. The non-transitory computer-readable storage medium of claim 1 , wherein the weather forecast data includes a forecasted precipitation type, a forecasted precipitation intensity, a forecasted air temperature, a forecasted precipitation rate, a forecasted wind direction, or a combination thereof.

4. The non-transitory computer-readable storage medium of claim 1 , wherein the computer program code instructions, when executed by the at least one processor, cause the at least one processor to identify the state of visibility by determining a level of obscureness using the road sign attribute data and the weather forecast data, the level of obscureness indicating a degree of which sign information displayed by the road sign is obscured.

5. The non-transitory computer-readable storage medium of claim 4 , wherein the computer program code instructions, when executed by the at least one processor, cause the at least one processor to determine the level of obscureness by:

inputting the road sign attribute data and the weather forecast data to a machine learning model; and

deriving the level of obscureness from the machine learning model.

6. The non-transitory computer-readable storage medium of claim 5 , wherein the machine learning model is random forest, logistic, decision trees, neural networks, or a combination thereof.

7. The non-transitory computer-readable storage medium of claim 5 , wherein the computer program code instructions, when executed by the at least one processor, cause the at least one processor to, subsequent to or prior to generating the level of obscureness:

receive ground truth data indicating a true state of which the sign information is displayed; and

train the machine learning model using the ground truth data.

8. The non-transitory computer-readable storage medium of claim 4 , wherein the computer program code instructions, when executed by the at least one processor, cause the at least one processor to determine a duration of which the level of obscureness is maintained subsequent to determining the level of obscureness.

9. The non-transitory computer-readable storage medium of claim 4 , wherein the computer program code instructions, when executed by the at least one processor, cause the at least one processor to generate a map including at least one indicator indicating the level of obscureness.

10. The non-transitory computer-readable storage medium of claim 4 , wherein the computer program code instructions, when executed by the at least one processor, cause the at least one processor to:

determine whether the level obscureness reaches a threshold; and

responsive to determining that the level of obscureness reaching the threshold, generate a signal informing a local municipality.

11. The non-transitory computer-readable storage medium of claim 4 , wherein the computer program code instructions, when executed by the at least one processor, cause the at least one processor to:

determine whether the level obscureness reaches a threshold; and

responsive to determining that the level of obscureness reaching the threshold, generate a signal configured to cause deployment of a drone.

12. The non-transitory computer-readable storage medium of claim 4 , wherein the level of obscureness is generated based on visibility of the sign information with respect to a human eye.

13. The non-transitory computer-readable storage medium of claim 4 , wherein the level of obscureness is generated based on visibility of the sign information with respect to a sensor.

14. The non-transitory computer-readable storage medium of claim 4 , wherein the computer program code instructions, when executed by the at least one processor, cause the at least one processor to, responsive to the level of obscureness reaching a threshold:

using the road sign attribute data and the weather forecast data, predict at least one attribute of an object obscuring the road sign; and

using the at least one attribute of the object, predict whether the sign information can be identified.

15. The non-transitory computer-readable storage medium of claim 14 , wherein the at least one attribute of the object is a location of the object with respect to the road sign, a size of the object, a density of the object, or a combination thereof.

16. An apparatus comprising at least one processor and at least one non-transitory memory including computer program code instructions, the computer program code instructions configured to, when executed, cause the apparatus to:

receive a request for navigating a mobile device to a destination;

identify a travel link to the destination;

receive attribute data indicating at least one attribute of a road object associated with the travel link;

receive weather forecast data indicating a weather forecast of a location in which the road object is disposed; and

using the attribute data and the weather forecast data, identify a state of visibility for the road object.

17. The apparatus of claim 16 , wherein the instructions, when executed, further cause the apparatus to generate a signal for a navigation related function based on the state of visibility, and wherein the signal includes information regarding an alternative travel link to the destination that avoids the road object.

18. The apparatus of claim 16 , wherein the instructions, when executed, further cause the apparatus to generate a signal for a navigation related function based on the state of visibility, wherein the mobile device is associated with a vehicle comprising a plurality of sensors, and wherein the signal causes the vehicle to transition use of a first set among the plurality of sensors to a second set among the plurality of sensors, alter weight of one or more of the plurality of sensors, or a combination thereof.

19. The apparatus of claim 16 , wherein the instructions, when executed, further cause the apparatus to generate a signal for a navigation related function based on the state of visibility, wherein the mobile device is associated with a vehicle configured to operate in a manual mode or an autonomous mode, and wherein the signal causes the vehicle to transition from the autonomous mode to the manual mode.

20. An apparatus comprising at least one processor and at least one non-transitory memory including computer program code instructions, the computer program code instructions configured to, when executed, cause the apparatus to:

predict a likelihood of at least one road sign existing within a travel link; and

for a road sign predicted to exist within the travel link:

predict a location of the road sign and at least one attribute of the road sign using one or more attributes associated with the travel link;

receive weather forecast data indicating a weather forecast of the location; and

identify a state of visibility for the road sign using the at least one attribute and the weather forecast data.

21. A method of training a machine learning model for predicting a state of visibility for a road sign, the method comprising:

receiving historical data for the road sign, the historical data including, for each of at least one past time or duration:

road sign attribute data indicating at least one attribute of the road sign;

historical weather data indicating a historical weather condition of a location in which the road sign is disposed; and

ground truth data indicating a true state of which sign information is displayed by the road sign; and

training the machine learning model to predict the state of visibility using the historical data.