System and method for automated surface assessment
Embodiments described herein provide a system for assessing the surface of an object for detecting contamination or other defects. During operation, the system obtains an input image indicating the contamination on the object and generates a synthetic image using an artificial intelligence (AI) model based on the input image. The synthetic image can indicate the object without the contamination. The system then determines a difference between the input image and the synthetic image to identify an image area corresponding to the contamination. Subsequently, the system generates a contamination map of the contamination by highlighting the image area based on one or more image enhancement operations.
1. A method for mitigating contamination on surface of an object, comprising:
determining contamination on the surface of the object from one or more images depicting the object;
determining, using an artificial intelligence (AI) model, a contamination map indicating the contamination, wherein the contamination map comprises depth information of the object;
projecting the contamination map on a three-dimensional representation of the object; and
determining, based on the projection, a set of operations to mitigate the contamination from the surface of the object.
2. The method of claim 1 , wherein the set of operations includes movement trajectories of a decontamination device, wherein the movement trajectories follow a geometric shape of the object.
3. The method of claim 2 , wherein the decontamination device is a cleaning nozzle of a decontamination system, and wherein the movement trajectories include movement of the cleaning nozzle that can clean the contamination from the surface of the object.
4. The method of claim 1 , further comprising determining distance and angle required for the set of operations based on the depth information of the object.
5. The method of claim 1 , wherein determining the set of operations further comprises:
determining a set of viewpoints for the object based on the depth information of the object; and
determining a subset of operations for a respective viewpoint of the object.
6. The method of claim 1 , wherein a pose of the object is different from a pose of a training object in a training image, and wherein the AI model is trained using the training image.
7. The method of claim 1 , wherein determining the contamination map further comprises aligning the depth information with corresponding visual information in the one or more images.
8. The method of claim 1 , wherein determining the contamination on the surface of the object comprises excluding background information and non-contaminated elements of the object.
9. The method of claim 1 , wherein projecting the contamination map further comprises:
representing a three-dimensional geometry of the object in the representation of the object; and
highlighting corresponding portions of the contamination on the representation based on the contamination map.
10. The method of claim 9 , wherein determining the set of operations further comprises determining that the highlighted portions of the representation are covered by the set of operations.
11. A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for mitigating contamination on surface of an object, the method comprising:
determining contamination on the surface of the object from one or more images depicting the object;
determining, using an artificial intelligence (AI) model, a contamination map indicating the contamination, wherein the contamination map comprises depth information of the object;
projecting the contamination map on a three-dimensional representation of the object; and
determining, based on the projection, a set of operations to mitigate the contamination from the surface of the object.
12. The computer-readable storage medium of claim 11 , wherein the set of operations includes movement trajectories of a decontamination device, wherein the movement trajectories follow a geometric shape of the object.
13. The computer-readable storage medium of claim 12 , wherein the decontamination device is a cleaning nozzle of a decontamination system, and wherein the movement trajectories include movement of the cleaning nozzle that can clean the contamination from the surface of the object.
14. The computer-readable storage medium of claim 11 , wherein the method further comprises determining distance and angle required for the set of operations based on the depth information of the object.
15. The computer-readable storage medium of claim 11 , wherein determining the set of operations further comprises:
determining a set of viewpoints for the object based on the depth information of the object; and
determining a subset of operations for a respective viewpoint of the object.
16. The computer-readable storage medium of claim 11 , wherein a pose of the object is different from a pose of a training object in a training image, and wherein the AI model is trained using the training image.
17. The computer-readable storage medium of claim 11 , wherein determining the contamination map further comprises aligning the depth information with corresponding visual information in the one or more images.
18. The computer-readable storage medium of claim 11 , wherein determining the contamination on the surface of the object comprises excluding background information and non-contaminated elements of the object.
19. The computer-readable storage medium of claim 11 , wherein projecting the contamination map further comprises:
representing a three-dimensional geometry of the object in the representation of the object; and
highlighting corresponding portions of the contamination on the representation based on the contamination map.
20. The computer-readable storage medium of claim 19 , wherein determining the set of operations further comprises determining that the highlighted portions of the representation are covered by the set of operations.