Determining traffic control features based on telemetry patterns within digital image representations of vehicle telemetry data

1. A method comprising:

determining, for a traffic area, vehicle telemetry information comprising speeds and locations relating to transportation vehicles;

generating a telemetry digital image comprising pixels representing the telemetry information for the traffic area; and

determining a traffic control feature associated with the traffic area by processing the pixels representing the telemetry information from the telemetry digital image utilizing a deep learning architecture.

2. The method of claim 1 , wherein determining the vehicle telemetry information comprises determining the speeds and the locations of the transportation vehicles as the transportation vehicles pass through the traffic area.

3. The method of claim 1 , further comprising:

identifying, from the vehicle telemetry information, a plurality of speed-location combinations indicating speeds of transportation vehicles at corresponding locations within the traffic area;

determining frequencies with which the plurality of speed-location combinations occur within the traffic area; and

generating the telemetry digital image to represent the frequencies of the plurality of speed-location combinations.

4. The method of claim 3 , wherein generating the telemetry digital image further comprises:

generating a first pixel of the telemetry digital image based on a first frequency of a first speed-location combination; and

generating a second pixel of the telemetry digital image based on a second frequency of a second speed-location combination.

5. The method of claim 1 , wherein determining the traffic control feature within the traffic area comprises utilizing a convolutional neural network to classify the telemetry digital image into a classification of traffic control features based on the pixels representing the telemetry information.

6. The method of claim 5 , further comprising training the convolutional neural network to determine the traffic control feature by:

generating, utilizing the convolutional neural network, a predicted traffic control feature based on a training digital image representation of training vehicle telemetry information, wherein the training digital image representation includes a training telemetry pattern;

determining a measure of loss associated with the convolutional neural network by comparing the predicted traffic control feature with a ground truth traffic control feature associated with the training telemetry pattern; and

modifying one or more weights of the convolutional neural network to reduce the measure of loss.

7. The method of claim 1 , wherein the determining the traffic control feature for the traffic area comprises:

identifying a pattern of the pixels representing the telemetry information; and

determining a traffic control feature corresponding to the pattern.

8. A non-transitory computer readable medium comprising instructions that, when executed by at least one processor, cause a computer device to:

determine, for a traffic area, vehicle telemetry information comprising speeds and locations relating to transportation vehicles;

generate a telemetry digital image comprising pixels representing the telemetry information for the traffic area; and

determine a traffic control feature associated with the traffic area by processing the pixels representing the telemetry information from the telemetry digital image utilizing a deep learning architecture.

9. The non-transitory computer readable medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computer device to determine the vehicle telemetry information by determining the speeds and the locations of the transportation vehicles as the transportation vehicles pass through the traffic area.

10. The non-transitory computer readable medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computer device to:

identify, from the vehicle telemetry information, a plurality of speed-location combinations indicating speeds of transportation vehicles at corresponding locations within the traffic area;

determine frequencies with which the plurality of speed-location combinations occur within the traffic area; and

generate the telemetry digital image to represent the frequencies of the plurality of speed-location combinations.

11. The non-transitory computer readable medium of claim 10 , further comprising instructions that, when executed by the at least one processor, cause the computer device to generate the telemetry digital image by:

generating a first pixel of the telemetry digital image based on a first frequency of a first speed-location combination; and

generating a second pixel of the telemetry digital image based on a second frequency of a second speed-location combination.

12. The non-transitory computer readable medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computer device to determine the traffic control feature within the traffic area by utilizing a convolutional neural network to classify the telemetry digital image into a classification of traffic control features based on the pixels representing the telemetry information.

13. The non-transitory computer readable medium of claim 12 , further comprising instructions that, when executed by the at least one processor, cause the computer device to train the convolutional neural network to determine the traffic control feature by:

generating, utilizing the convolutional neural network, a predicted traffic control feature based on a training digital image representation of training vehicle telemetry information, wherein the training digital image representation includes a training telemetry pattern;

determining a measure of loss associated with the convolutional neural network by comparing the predicted traffic control feature with a ground truth traffic control feature associated with the training telemetry pattern; and

modifying one or more weights of the convolutional neural network to reduce the measure of loss.

14. The non-transitory computer readable medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computer device to determine the traffic control feature for the traffic area by:

identifying a pattern of the pixels representing the telemetry information; and

determining a traffic control feature corresponding to the pattern.

15. A system comprising:

at least one processor; and

a non-transitory computer readable medium comprising instructions that, when executed by the at least one processor, cause the system to:

determine, for a traffic area, vehicle telemetry information comprising speeds and locations relating to transportation vehicles;

generate a telemetry digital image comprising pixels representing the telemetry information for the traffic area; and

determine a traffic control feature associated with the traffic area by processing the pixels representing the telemetry information from the telemetry digital image utilizing a deep learning architecture.

16. The system of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the system to determine the vehicle telemetry information by determining the speeds and the locations of the transportation vehicles as the transportation vehicles pass through the traffic area.

17. The system of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the system to:

identify, from the vehicle telemetry information, a plurality of speed-location combinations indicating speeds of transportation vehicles at corresponding locations within the traffic area;

determine frequencies with which the plurality of speed-location combinations occur within the traffic area; and

generate the telemetry digital image to represent the frequencies of the plurality of speed-location combinations.

18. The system of claim 17 , further comprising instructions that, when executed by the at least one processor, cause the system to generate the telemetry digital image by:

generating a first pixel of the telemetry digital image based on a first frequency of a first speed-location combination; and

generating a second pixel of the telemetry digital image based on a second frequency of a second speed-location combination.

19. The system of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the system to determine the traffic control feature within the traffic area by utilizing a convolutional neural network to classify the telemetry digital image into a classification of traffic control features based on the pixels representing the telemetry information.

20. The system of claim 19 , further comprising instructions that, when executed by the at least one processor, cause the system to train the convolutional neural network to determine the traffic control feature by:

generating, utilizing the convolutional neural network, a predicted traffic control feature based on a training digital image representation of training vehicle telemetry information, wherein the training digital image representation includes a training telemetry pattern;

determining a measure of loss associated with the convolutional neural network by comparing the predicted traffic control feature with a ground truth traffic control feature associated with the training telemetry pattern; and

modifying one or more weights of the convolutional neural network to reduce the measure of loss.