Methods of artificial intelligence-assisted infrastructure assessment using mixed reality systems
A smart, human-centered technique that uses artificial intelligence and mixed reality to accelerate essential tasks of the inspectors such as defect measurement, condition assessment and data processing. For example, a bridge inspector can analyze some remote cracks located on a concrete pier, estimate their dimensional properties and perform condition assessment in real-time. The inspector can intervene in any step of the analysis/assessment and correct the operations of the artificial intelligence. Thereby, the inspector and the artificial intelligence will collaborate/communicate for improved visual inspection. This collective intelligence framework can be integrated in a mixed reality supported see-through headset or a hand-held device with the availability of sufficient hardware and sensors. Consequently, the methods reduce the inspection time and associated labor costs while ensuring reliable and objective infrastructure evaluation. Such methods offer contributions to infrastructure inspection, maintenance, management practice, and safety for the inspection personnel.
1 . A hybrid system for contactless structure inspection, the hybrid system comprising:
a front-end module, the front-end module comprising:
a mixed-reality headset configured to scan a surrounding area, capture images within the surrounding area, or both; and
a user-input actuator in communication with the mixed-reality headset, the user input actuator being configured to receive a selection from a user to investigate a portion of the surrounding area;
a back-end module, wherein the back-end module comprises at least one server communicatively coupled with the mixed reality headset;
wherein the mixed reality headset creates a bounding box around the portion of the surrounding area, such that only the mixed reality headset transmits only the bounding box to the back-end module for investigation
wherein the mixed reality headset is configured to use projective geometry to project an object onto the bounding box; and
wherein the server is configured to calculate a likelihood of a defect for the selected one of the suggested images and to transmit a calculated likelihood of the defect to the mixed reality headset.
2 . The hybrid system of claim 1 , wherein the hybrid system is configured to implement an attention-guided technique.
3 . The hybrid system of claim 2 , wherein the server further comprises a deep learning module having a trained data set of defects in structures.
4 . The hybrid system of claim 3 , wherein the server is configured to receive the captured image of the portion of the surrounding area from the mixed reality headset.
5 . The hybrid system of claim 4 , wherein the deep learning module configured to compare the captured image of the portion of the surrounding area with the trained data set of defects in structure to determine a presence of a defect.
6 . The hybrid system of claim 5 , wherein the server is configured to segment the captured image of the portion of the surrounding area only within the bounding box, thereby focusing the comparison performed via the deep learning module on the segmented image within the bounding box.