Image-based vehicle speed estimation
Methods and systems for estimating the speed of passing vehicles based on License Plate Recognition (LPR) image information are described herein. The distance traversed by a vehicle between image frames is estimated based on a difference between a pixel location of a tracking point on the vehicle in a first image and a second pixel location of the tracking point in second image of the vehicle. In some embodiments, the displacement identified in the images is converted to a projected displacement on the roadway surface based on the mapping between pixel locations within the field of view of the image sensor and locations on the surface of the roadway. The projected displacement is corrected by accounting for the difference in height of the camera module and tracking point over the roadway surface. An estimate of vehicle speed is calculated from the corrected displacement and the elapsed time between image frames.
1. A method comprising:
receiving a plurality of images of a vehicle passing over a surface of a roadway from at least one camera module of a license plate recognition imaging system, wherein the surface of the roadway is within a field of view of an image sensor of the at least one camera module;
determining an estimate of speed of the vehicle passing over the roadway based at least in part on a difference between a first pixel location of a portion of the vehicle in a first of the plurality of images and a second pixel location of the portion of the vehicle in a second of the plurality of images, wherein the determining the estimate of speed of the vehicle involves a correction to the difference between the first pixel location and the second pixel location based on a plurality of passes of a vehicle through the field of view of the image sensor, each pass of the vehicle at a constant, known speed; and
storing the estimate of speed of the vehicle in a memory.
2. The method of claim 1 , wherein the determining the estimate of speed of the vehicle passing over the roadway is also based on a mapping between pixel locations within the field of view of the image sensor and locations on the surface of the roadway.
3. The method of claim 2 , wherein the determining the estimate of speed of the vehicle involves determining a correction of the estimate of speed of the vehicle based at least in part on a distance between the surface of the roadway and the image sensor and a distance between the surface of the roadway and the portion of the vehicle.
4. The method of claim 2 , further comprising:
determining the mapping between pixel locations and locations on the surface of the roadway based at least in part on a calibration of a grid pattern located on the surface of the roadway is within the field of view of the image sensor to an image of the grid pattern generated by the image sensor.
5. The method of claim 4 , wherein the calibration involves a mapping of locations on the grid pattern to pixel locations of the image of the grid pattern.
6. The method of claim 5 , wherein the mapping involves interpolation between locations on the grid pattern and pixel locations of the image of the grid pattern.
7. The method of claim 1 , wherein the portion of the vehicle includes any of a license plate, a taillight, and a bumper.
8. The method of claim 1 , wherein the determining of the estimate of speed of the vehicle involves three of more images of the vehicle passing over the roadway.
9. The method of claim 8 , wherein the determining of the estimate of speed of the vehicle involves discarding an estimate of speed of the vehicle based on two of the three or more images of the vehicle passing over the roadway.
10. The method of claim 1 , further comprising:
determining a distribution of vehicle speeds over the surface of the roadway based at least in part on the estimate of speed of the vehicle.
11. The method of claim 1 , wherein the plurality of images of the vehicle includes color images or infrared images.
12. An apparatus comprising:
a processor; and
a memory storing an amount of program code that, when executed, causes the apparatus to
receive a plurality of images of a vehicle passing over a surface of a roadway from at least one camera module of a license plate recognition imaging system, wherein the surface of the roadway is within a field of view of an image sensor of the at least one camera module;
determine an estimate of speed of the vehicle passing over the roadway based at least in part on a difference between a first pixel location of a portion of the vehicle in a first of the plurality of images and a second pixel location of the portion of the vehicle in a second of the plurality of images, wherein the determining the estimate of speed of the vehicle involves determining a correction of the estimate of speed of the vehicle based at least in part on a distance between the surface of the roadway and the image sensor and a distance between the surface of the roadway and the portion of the vehicle; and
store the estimate of speed of the vehicle in a memory.
13. The apparatus of claim 12 , wherein the determining the estimate of speed of the vehicle involves a correction to the difference between the first pixel location and the second pixel location.
14. The apparatus of claim 13 , the memory also storing an amount of program code that, when executed, causes the apparatus to:
determine the correction to the difference between the first pixel location and the second pixel location based on a plurality of passes of a vehicle through the field of view of the image sensor, each pass of the vehicle at a constant, known speed.
15. The apparatus of claim 12 , the memory also storing an amount of program code that, when executed, causes the apparatus to:
determine a mapping between pixel locations and locations on the surface of the roadway based at least in part on a calibration of a grid pattern located on the surface of the roadway within the field of view of the image sensor to an image of the grid pattern generated by the image sensor.
16. The apparatus of claim 15 , wherein the calibration involves a mapping of locations on the grid pattern to pixel locations of the image of the grid pattern.
17. The apparatus of claim 16 , wherein the mapping involves interpolation between locations on the grid pattern and pixel locations of the image of the grid pattern.
18. The apparatus of claim 12 , the memory also storing an amount of program code that, when executed, causes the apparatus to:
determine a distribution of vehicle speeds over the surface of the roadway based at least in part on the estimate of speed of the vehicle.
19. A non-transitory, computer-readable medium, comprising:
code for causing a computer to receive a plurality of images of a vehicle passing over a surface of a roadway from at least one camera module of a license plate recognition imaging system, wherein the surface of the roadway is within a field of view of an image sensor of the at least one camera module;
code for causing the computer to determine an estimate of speed of the vehicle passing over the roadway based at least in part on a difference between a first pixel location of a portion of the vehicle in a first of the plurality of images and a second pixel location of the portion of the vehicle in a second of the plurality of images, wherein the determining the estimate of speed of the vehicle involves determining a correction of the estimate of speed of the vehicle based at least in part on a distance between the surface of the roadway and the image sensor and a distance between the surface of the roadway and the portion of the vehicle; and
code for causing the computer to store the estimate of speed of the vehicle in a memory.
20. The non-transitory, computer-readable medium of claim 19 , wherein the determining the estimate of speed of the vehicle passing over the roadway is also based on a mapping between pixel locations within the field of view of the image sensor and locations on the surface of the roadway.
21. The non-transitory, computer-readable medium of claim 20 , further comprising:
code for causing the computer to determine the mapping between pixel locations and locations on the surface of the roadway based at least in part on a calibration of a grid pattern located on the surface of the roadway within the field of view of the image sensor to an image of the grid pattern generated by the image sensor.