Traffic simulator adjustment

1 . A method, comprising:

determining a number of vehicles depicted in one or more images of at least a portion of a transportation network;

classifying each of the vehicles depicted in the one or more images by type of vehicle;

determining, from the one or more images, respective lengths of segments in the transportation network corresponding to each of the vehicles based on average length of the type of vehicle;

determining an observed traffic density and an observed network flow corresponding to the transportation network based on the number of vehicles and the respective lengths of the segments;

determining a traffic density estimation and a network flow estimation corresponding to the transportation network, using a traffic simulator; and

adjusting the traffic simulator based on the observed traffic density, the traffic density estimation, the observed network flow, and the network flow estimation.

2 . The method of claim 1 , wherein the one or more images are at least 30-centimeters in resolution and comprise one or more of aerial images or satellite images.

3 . The method of claim 1 , wherein the transportation network includes one or more links without corresponding ground-based traffic measurements.

4 . The method of claim 1 , wherein the determining of the observed traffic density and the observed network flow corresponding to the transportation network comprises using one or more computer vision techniques including one or more of:

image classification,

object detection,

semantic segmentation,

instance segmentation,

panoptic segmentation, or

visual simultaneous localization and mapping.

5 . The method of claim 1 , wherein the determining of the observed traffic density and the observed network flow corresponding to the transportation network comprises using object detection implemented on sliding windows of a size.

6 . The method of claim 1 , wherein the adjusting the traffic simulator comprises:

determining one or more of network flow estimation error, travel time estimation error, or traffic density estimation error.

7 . A system, comprising:

one or more processors configured to perform operations comprising:

determining a number of vehicles depicted in one or more images of at least a portion of a transportation network;

classifying each of the vehicles depicted in the one or more images by type of vehicle;

determining an observed traffic density and an observed network flow corresponding to the transportation network based on the number of vehicles depicted in the one or more images and respective lengths of segments in the transportation network corresponding to each of the vehicles based on average length of the type of vehicle; and

adjusting one or more of a traffic density estimation or a network flow estimation determined by a traffic simulator based on the observed traffic density and the observed network flow.

8 . The system of claim 7 , wherein the one or more images are at least 30-centimeters in resolution and comprise one or more of aerial images or satellite images.

9 . The system of claim 7 , wherein the transportation network includes one or more links without corresponding ground-based traffic measurements.

10 . The system of claim 7 , wherein the determining of the observed traffic density and the observed network flow comprises using one or more computer vision techniques including one or more of:

image classification,

object detection,

semantic segmentation,

instance segmentation,

panoptic segmentation, or

visual simultaneous localization and mapping.

11 . The system of claim 7 , wherein the determining of the observed traffic density and the observed network flow comprises using object detection implemented on sliding windows of a size.

12 . The system of claim 7 , wherein the adjusting the one or more of the traffic density estimation or the network flow estimation determined by the traffic simulator comprises:

determining one or more of network flow estimation error, travel time estimation error, or traffic density estimation error.

13 . One or more non-transitory computer-readable storage media configured to store instructions that, in response to being executed, cause a system to perform operations, the operations comprising:

determining a number of vehicles depicted in an image of at least a portion of a transportation network;

classifying each of the vehicles depicted in the image by type of vehicle;

determining, from the image, respective lengths of segments in the transportation network corresponding to each of the vehicles based on average length of the type of vehicle;

determining an observed traffic density and an observed network flow corresponding to the transportation network based on the number of vehicles and the respective lengths of segments;

determining a traffic density estimation and a network flow estimation corresponding to the transportation network, using a traffic simulator; and

adjusting the traffic simulator based on the observed traffic density, the traffic density estimation, the observed network flow, and the network flow estimation.

14 . The one or more non-transitory computer-readable storage media of claim 13 , wherein the image is at least 30-centimeters in resolution and is one or more of an aerial image or a satellite image.

15 . The one or more non-transitory computer-readable storage media of claim 13 , wherein the transportation network includes one or more links without corresponding ground-based traffic measurements.

16 . The one or more non-transitory computer-readable storage media of claim 13 , wherein the determining of the observed traffic density and the observed network flow comprises using one or more computer vision techniques including one or more of:

image classification,

object detection,

semantic segmentation,

instance segmentation,

panoptic segmentation, or

visual simultaneous localization and mapping.

17 . The one or more non-transitory computer-readable storage media of claim 13 , wherein the adjusting the traffic simulator comprises:

determining one or more of network flow estimation error, travel time estimation error, or traffic density estimation error.