The 7th International Conference on Next Generation Computing 2021 (2021.11)바로가기
페이지
pp.167-170
저자
Minh Dang, Kyungbok Min, Hyeonjoon Moon
언어
한국어(KOR)
URL
https://www.earticle.net/Article/A448036
원문정보
초록
영어
Sewer pipes are an essential public infrastructure of countries worldwide. They support wastewater transportation for processing or disposal. The harsh environments inside the sewer pipes can lead to the occurrence of various defects. Current crack detection approaches mainly focus on the surveillance camera (CCTV) to assess the condition of the sewer pipes. This process is considered a tiresome and laborious process. Therefore, a robust and efficient sewer defect detection system based on the transformer architecture is introduced in this manuscript. In addition, the system can provide explainable visualization for its predictions using the transformer's attention.
목차
Abstract I. INTRODUCTION II. DATASET A. CCTV Video Collection B. Crack Detection Dataset Creation III. METHODOLOGY A. Pre-processing Module B. Transformer-based Crack Detection Model C. Attention Visualization IV. EXPERIMENTAL RESULTS A. Pre-processing Results B. Transformer-based Crack Detection Performance CONCLUSION ACKNOWLEDGMENT REFERENCES