Learning signs from vehicle probes
Systems, methods, and apparatuses are disclosed for identifying road signs along a roadway segment from vehicle probe data. Probe data is received from vehicle sensors at a road segment, wherein the probe data includes observed static objects along the road segment. Road signs are identified within the observed static objects of the probe data using a logistic regression algorithm. The geographic location of the identified road signs are determined using a linear regression algorithm.
1. A method comprising:
receiving, using a processor, probe data from vehicle sensors from a plurality of vehicles at a road segment, the probe data comprising observed static objects along the road segment;
identifying, using a logistic regression algorithm, road signs within the observed static objects of the probe data; and
determining, using a linear regression algorithm, a geographic location for each identified road sign along the road segment.
2. The method of claim 1 , wherein one of the road signs is a speed limit sign.
3. The method of claim 2 , wherein the speed limit sign is a fixed speed limit sign.
4. The method of claim 2 , wherein the speed limit sign is a variable speed limit sign.
5. The method of claim 1 , further comprising:
ascertaining, for each road sign, whether each of the road signs is a fixed road sign or a variable road sign.
6. The method of claim 1 , further comprising:
reporting the determined geographic location of the road signs over a connected network to a traffic developer, a map developer, or a navigation device.
7. The method of claim 1 , further comprising:
reporting data comprising the determined geographic location of the identified road signs over a connected network to a navigation device within an autonomous vehicle or a highly automated driving vehicle;
processing the reported data within the autonomous vehicle or the highly automated driving vehicle; and
generating a driving command or alerting an operator of the autonomous vehicle or the highly automated driving vehicle based on the processed data.
8. The method of claim 1 , further comprising:
training the logistic regression algorithm through a verification of the identified road signs with ground truth data.
9. The method of claim 1 , further comprising:
training the linear regression algorithm through a verification of the determined geographic location of each identified road sign with ground truth data.
10. The method of claim 1 , further comprising:
map-matching each road sign to an edge of the road segment or a specific lane of the road segment.
11. A method comprising:
receiving, using a processor, probe data from vehicle sensors from a plurality of vehicles at a road segment, the probe data comprising observed static objects along the road segment;
identifying, using a logistic regression algorithm, speed signs within the observed static objects of the probe data;
ascertaining, for each speed sign, whether the speed sign is a fixed speed sign or a variable speed sign;
determining, using a linear regression algorithm, a geographic location for each identified speed sign along the road segment; and
reporting the determined geographic location of the speed signs over a connected network to a traffic developer, a map developer, or a navigation device.
12. An apparatus comprising:
at least one processor; and
at least one memory including computer program code for one or more programs; the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to at least perform:
receive probe data from vehicle sensors from a plurality of vehicles at a road segment, the probe data comprising observed static objects along the road segment;
identify, using a logistic regression algorithm, road signs within the observed static objects of the probe data; and
determine, using a linear regression algorithm, a geographic location for each identified road sign along the road segment.
13. The apparatus of claim 12 , wherein one of the road signs is a speed limit sign.
14. The apparatus of claim 13 , wherein the speed limit sign is a fixed speed limit sign.
15. The apparatus of claim 13 , wherein the speed limit sign is a variable speed limit sign.
16. The apparatus of claim 12 , wherein the at least one memory and the computer program code are configured to cause the apparatus to further perform:
ascertain, for each road sign, whether the road sign is a fixed road sign or a variable road sign.
17. The apparatus of claim 12 , wherein the at least one memory and the computer program code are configured to cause the apparatus to further perform:
report the determined geographic location of the road signs over a connected network to a traffic developer, a map developer, or a navigation device.
18. The apparatus of claim 12 , wherein the at least one memory and the computer program code are configured to cause the apparatus to further perform:
train the logistic regression algorithm through a verification of the identified road signs with ground truth data.
19. The apparatus of claim 12 , wherein the at least one memory and the computer program code are configured to cause the apparatus to further perform:
train the linear regression algorithm through a verification of the determined geographic location of each identified road sign with ground truth data.
20. The apparatus of claim 12 , wherein the at least one memory and the computer program code are configured to cause the apparatus to further perform:
map-match each road sign to an edge of the road segment or a specific lane of the road segment.