High speed stereoscopic pavement surface scanning system and method
Disclosed is a mobile pavement surface scanning system for detecting pavement distress. In an embodiment the system comprises one or more light sources mounted on the mobile vehicle for illuminating a pavement, one or more stereoscopic image capturing devices mounted on the vehicle for capturing sequential images of an illuminated pavement surface, and a plurality of positioning sensors mounted on the mobile vehicle, the positioning sensors adapted to encode movement of the mobile vehicle and provide a synchronization signal for the sequential images captured by the one or more stereoscopic image capture devices. One or more computer processors are adapted to synchronize the intensity image pairs captured by each camera in the one or more stereoscopic image capturing devices, perform a 3D reconstruction of the pavement from the intensity image pairs using stereoscopic principles, generate a depth image and an intensity image pair from the 3D reconstruction, and process at least one of the depth image and the intensity image utilizing one or more distress detection modules to detect a type of pavement distress.
1. A mobile pavement surface scanning system for detecting pavement distress, comprising:
one or more light sources mounted to a mobile vehicle for illuminating a pavement surface;
one or more stereoscopic image capturing devices mounted to the mobile vehicle for capturing sequential images of the illuminated pavement surface;
a plurality of positioning sensors mounted to the mobile vehicle, the positioning sensors adapted to encode movement of the mobile vehicle and provide a synchronization signal for the sequential images captured by the one or more stereoscopic image capture devices; and
one or more computer processors configured to:
synchronize the sequential images captured by each camera of the one or more stereoscopic image capturing devices;
generate intensity image pairs from the synchronized sequential images;
perform a 3D reconstruction of the illuminated pavement surface from the intensity image pairs using stereoscopic principles;
generate a depth image and an intensity image pair from the 3D reconstruction; and
process at least one of the depth image and the intensity image utilizing one or more distress detection modules to detect a type of pavement distress.
2. The system of claim 1 , wherein the one or more distress detection modules comprise a computer vision module for detecting pavement distress utilizing at least one of the depth image and an intensity image pair.
3. The system of claim 2 , wherein the one or more distress detection modules further comprise a machine learning module, and the computer vision module is adapted to generate a learning feed forward to the machine learning module.
4. The system of claim 1 , wherein the one or more distress detection modules comprise a machine learning module for detecting pavement distress utilizing at least one of the depth image and an intensity image pair.
5. The system of claim 4 , wherein the machine learning module includes a learning feedback loop to enable the machine learning module to improve detection of pavement distresses.
6. The system of claim 5 , wherein the machine learning module comprises an artificial intelligence (AI) engine executing a learning algorithm to detect and classify distresses based on its iterative training.
7. The system of claim 6 , wherein the machine learning module is adapted to provide a feedback signal to dynamically change a parameter of a component on the mobile vehicle for capturing the sequential images on the illuminated pavement surface.
8. The system of claim 7 , wherein the feedback signal is processed to change a parameter of the one or more light sources mounted to the mobile vehicle.
9. The system of claim 7 , wherein the feedback signal is processed to change a parameter of the one or more stereoscopic image capturing devices.
10. The system of claim 6 , wherein the machine learning module is adapted to select a type of image processing filter in dependence upon the type of pavement distress being detected.
11. The system of claim 10 , wherein the machine learning module is adapted to categorize the type of pavement distress detected, and to store the geo-reference for the detected pavement distress in real time as the survey data is stored.
12. A method of scanning a pavement surface for detecting pavement distress, comprising:
providing one or more light sources mounted to a mobile vehicle for illuminating a pavement surface;
providing one or more stereoscopic image capturing devices mounted to the mobile vehicle for capturing sequential images of the illuminated pavement surface;
providing a plurality of positioning sensors mounted to the mobile vehicle, the positioning sensors adapted to encode movement of the mobile vehicle and provide a synchronization signal for the sequential images captured by the one or more stereoscopic image capture devices; and
providing one or more computer processors configured to:
synchronize the sequential images captured by each camera of the one or more stereoscopic image capturing devices;
generate intensity image pairs from the synchronized sequential images;
perform a 3D reconstruction of the illuminated pavement surface from the intensity image pairs using stereoscopic principles;
generate a depth image and an intensity image pair from the 3D reconstruction; and
process at least one of the depth image and the intensity image utilizing one or more distress detection modules to detect a type of pavement distress.
13. The method of claim 12 , wherein the one or more distress detection modules comprise a computer vision module for detecting pavement distress utilizing at least one of the depth image and an intensity image pair.
14. The method of claim 13 , wherein the one or more distress detection modules further comprise a machine learning module, and the computer vision module is adapted to generate a learning feed forward to the machine learning module.
15. The method of claim 12 , wherein the one or more distress detection modules comprise a machine learning module for detecting pavement distress utilizing at least one of the depth image and an intensity image pair.
16. The method of claim 15 , wherein the machine learning module includes a learning feedback loop to enable the machine learning module to improve detection of pavement distresses.
17. The method of claim 16 , wherein the machine learning module comprises an artificial intelligence (AI) engine executing a learning algorithm to detect and classify distresses based on its iterative training.
18. The method of claim 17 , wherein the machine learning module is adapted to provide a feedback signal to dynamically change a parameter of a component on the mobile vehicle for capturing the sequential images on the illuminated pavement surface.
19. The method of claim 18 , wherein the feedback signal is processed to change a parameter of the one or more light sources mounted to the mobile vehicle.
20. The method of claim 18 , wherein the feedback signal is processed to change a parameter of the one or more stereoscopic image capturing devices.
21. The method of claim 17 , wherein the machine learning module is adapted to select a type of image processing filter in dependence upon the type of pavement distress being detected.
22. The method of claim 21 , wherein the machine learning module is adapted to categorize the type of pavement distress detected, and to store the geo-reference for the detected pavement distress in real time as the survey data is stored.