Automatic detection of sewer defects based on yolov5

As cities modernize, sewer systems continue to expand. However, pipe problems may lead to accidents such as sewage overflow. The traditional sewerage pipe detection technology suffers from low accuracy and inefficiency and mainly relies on manual visual identification, which is prone to subjective errors. In this paper, a new Sewer-Yolov58 model is proposed to solve this problem, which is improved based on the original Yolov5 for real-time detection of sewerage problems to detect pipeline problems in time and is favorable for the subsequent repair work. Through comparison experiments with other models, the results show that the improved Sewer-Yolov58 model has a more efficient and accurate detection effect.