“A low power vision based sewer faults detection device using a tinyML to produce highly accurate sewer faults classification.
In the U.S, there is around 2 million kilometer of sewer pipes around the country that supported 240 millions U.S citizen. Every year, at least 23 000–75 000 sewer pipe failures are reported in the United States, which releases up to 3–10 billion gallons of untreated sewage to the environment. This leads to a high economic loss, water pollution, and threatens communal health.
These sewer pipes need yearly maintained to keep functioning properly and avoid sewer overflow. In most cases, sewer inspection is perform on site by an expert inspector, who usually use a remote control robot with camera to manually inspect the internal structure of the sewer. This process is time consuming and often time can lead to flawed inspection of the sewer pipe due to the difficult and tiresome nature of the work.”