| CPC G06T 7/0008 (2013.01) [F16L 55/26 (2013.01); G06F 16/535 (2019.01); G06F 16/55 (2019.01); G06F 16/58 (2019.01); G06V 10/82 (2022.01)] | 6 Claims |
|
1. A system for performing automated inspection of a sewer line using machine learning, the system comprising:
an inspection data database configured to receive and store sewer inspection data including images of the sewer line and sewer inspection metadata associated to the images;
an inspection upload module configured to receive the sewer inspection data and upload the sewer inspection data to the inspection data database for storage thereof;
an identification module receiving the sewer inspection data from the inspection data database and configured to generate therefrom identification data including characteristics of the sewer line identified and categorized, the identification module using at least one machine learning model configured to process the sewer inspection data and to determine whether at least one sewer specific characteristic is identifiable in the images of the sewer inspection data and, in the affirmative, identify and categorize the at least one sewer specific characteristic in the images of the sewer inspection data, using the combination of the images and the sewer inspection metadata of the sewer inspection data, wherein the at least one machine learning model comprises a plurality of hierarchical classes where a top class performs the determination of whether the at least one sewer specific characteristic is identifiable and, in the affirmative, the identification thereof and lower classes perform categorization in decreasing abstraction levels; and
a report production module receiving the identification data from the identification module and displaying a generated inspection report including at least a portion of the identification data on a graphical user interface,
wherein the report production module is further configured to receive feedback data relative to the identification data based on inputs inputted via an analyst computing device displaying the graphical user interface to an analyst,
wherein the at least one machine learning model is trained using a training data set stored in a training database and comprising examples including exemplary images of the sewer line and metadata associated to the exemplary images and wherein the training data set is updated using the sewer inspection data including images and sewer specific inspection metadata labelled using the feedback data.
|