Missing traffic face detector
Systems, devices, products, apparatuses, and/or methods, for detecting a missing traffic face, including: obtaining sensor data that includes a plurality of images associated with a geographic location including a roadway and associated with a plurality of image capture locations in the geographic location, determining in a subset of images of the plurality of images, a plurality of image areas associated with at least one predicted traffic face, determining a plurality of rays that project through 3-D spaces of the geographic location associated with the plurality of image areas from a subset of image capture locations of the plurality of image capture locations associated with the subset of images, and identifying at least one location of a traffic face in the geographic location based on a sum of unit vectors of the plurality of rays that project through the 3-D spaces of the geographic location at the at least one location of the traffic face.
1. A computer-implemented mapping system, comprising:
at least one processor programmed to perform operations comprising:
obtaining sensor data comprising a plurality of images associated with a geographic area including a roadway, a first image of the plurality of images being associated with a first image capture location in the geographic area and a second image of the plurality of images being associated with a second image capture location in the geographic area;
obtaining map data describing the geographic area, the map data indicating a plurality of mapped traffic control devices;
determining, using the sensor data, a location of a perceived traffic control device in the geographic area, the determining of the location of the perceived traffic control device comprising:
determining from the plurality of images, a plurality of image areas, a first image area from the plurality of image areas being associated with a first predicted traffic control device and a second image area from the plurality of image areas being associated with a second predicted traffic control device;
determining a first ray projecting through a first three-dimensional space from the first image capture location, the first three-dimensional space being in the geographic area that is associated with the first image area;
determining a second ray projecting through a second three-dimensional space from the second image capture location, the second three-dimensional space being in the geographic area; and
identifying the perceived traffic control device using the first ray and the second ray;
determining that the perceived traffic control device is not indicated by the map data; and
generating updated map data, the updated map data indicating the perceived traffic control device.
2. The computer-implemented mapping system of claim 1 , the operations further comprising determining an area of nearest overlap between a plurality of rays comprising the first ray and the second ray, the area of nearest overlap corresponding to the location of the perceived traffic control device.
3. The computer-implemented mapping system of claim 1 , the operations further comprising validating the location of the perceived traffic control device by verifying that a map area of the map data includes the location of the perceived traffic control device.
4. The computer-implemented mapping system of claim 1 , the generating of the updated map data comprising determining a height associated with the location of the perceived traffic control device.
5. The computer-implemented mapping system of claim 4 , the height being determined to within a height threshold indicated by the map data.
6. The computer-implemented mapping system of claim 1 , the operations further comprising determining an orientation associated with the location of the perceived traffic control device, the orientation being determined to within a predetermined threshold of a traffic control device orientation indicated by the map data.
7. A computer-implemented mapping method, comprising:
obtaining sensor data by at least one processor, the sensor data comprising a plurality of images associated with a geographic area including a roadway, a first image of the plurality of images being associated with a first image capture location in the geographic area and a second image of the plurality of images being associated with a second image capture location in the geographic area;
obtaining map data by the at least one processor, the map data describing the geographic area, the map data indicating a plurality of mapped traffic control devices;
determining, by the at least one processor, a location of a perceived traffic control device in the geographic area, the determining of the location of the perceived traffic control device comprising:
determining from the plurality of images, a plurality of image areas, a first image area from the plurality of image areas being associated with a first predicted traffic control device and a second image area from the plurality of image areas being associated with a second predicted traffic control device;
determining a first ray projecting through a first three-dimensional space from the first image capture location, the first three-dimensional space being in the geographic area that is associated with the first image area;
determining a second ray projecting through a second three-dimensional space from the second image capture location, the second three-dimensional space being in the geographic area; and
identifying the perceived traffic control device using the first ray and the second ray;
determining, by the at least one processor, that the perceived traffic control device is not indicated by the map data; and
generating, by the at least one processor, updated map data, the updated map data indicating the perceived traffic control device.
8. The computer-implemented mapping method of claim 7 , further comprising determining an area of nearest overlap between a plurality of rays comprising the first ray and the second ray, the area of nearest overlap corresponding to the location of the perceived traffic control device.
9. The computer-implemented mapping method of claim 7 , further comprising validating the location of the perceived traffic control device by verifying that a map area of the map data includes the location of the perceived traffic control device.
10. The computer-implemented mapping method of claim 7 , the generating of the updated map data comprising determining a height associated with the location of the perceived traffic control device.
11. The computer-implemented mapping method of claim 10 , the height being determined to within a first height threshold indicated by the map data.
12. The computer-implemented mapping method of claim 7 , further comprising determining an orientation associated with the location of the perceived traffic control device, the orientation being determined to within a predetermined threshold of a traffic control device orientation indicated by the map data.
13. A non-transitory computer-readable medium comprising instructions thereon that, when executed by at least one processor, cause the at least one processor to perform operations comprising:
obtaining sensor data comprising a plurality of images associated with a geographic area including a roadway, a first image of the plurality of images being associated with a first image capture location in the geographic area and a second image of the plurality of images being associated with a second image capture location in the geographic area;
obtaining map data describing the geographic area, the map data indicating a plurality of mapped traffic control devices;
determining, using the sensor data, a location of a perceived traffic control device in the geographic area, the determining of the location of the perceived traffic control device comprising:
determining from the plurality of images, a plurality of image areas, a first image area from the plurality of image areas being associated with a first predicted traffic control device and a second image area from the plurality of image areas being associated with a second predicted traffic control device;
determining a first ray projecting through a first three-dimensional space from the first image capture location, the first three-dimensional space being in the geographic area that is associated with the first image area;
determining a second ray projecting through a second three-dimensional space from the second image capture location, the second three-dimensional space being in the geographic area; and
identifying the perceived traffic control device using the first ray and the second ray;
determining that the perceived traffic control device is not indicated by the map data; and
generating updated map data, the updated map data indicating the perceived traffic control device.
14. The medium of claim 13 , the operations further comprising determining an area of nearest overlap between a plurality of rays comprising the first ray and the second ray, the area of nearest overlap corresponding to the location of the perceived traffic control device.
15. The medium of claim 13 , the operations further comprising validating the location of the perceived traffic control device by verifying that a map area of the map data includes the location of the perceived traffic control device.
16. The medium of claim 13 , the generating of the updated map data comprising determining a height associated with the location of the perceived traffic control device, the height being determined to within a height threshold indicated by the map data.
17. The medium of claim 13 , the operations further comprising determining an orientation associated with the location of the perceived traffic control device, the orientation being determined to within a predetermined threshold of a traffic control device orientation indicated by the map data.