Comparison of classic object-detection techniques for automated sewer defect detection
نویسندگان
چکیده
Abstract Sewer systems play a key role in cities to ensure public assets and safety. Timely detection of defects can effectively alleviate system deterioration. Conventional manual inspection is labor-intensive, error-prone expensive. Object powerful deep learning technique that complement and/or replace conventional inspection, especially complex environments. This study compares two classic object-detection methods, namely faster region-based convolutional neural network (R-CNN) You Only Look Once (YOLO), for the localization five types sewer defects. Model performances are evaluated based on their accuracy processing speed under parameterization impacts dataset size training parameters. Results show R-CNN achieved higher prediction accuracy. Training maximum number epochs (MaxE) had dominant model YOLO, respectively. The increased along with increasing data R-CNN, but did not vary significantly YOLO. models' abilities detect disjoint residential wall were highest, whereas crack tree root more difficult detect. results help better understand strengths weaknesses methods provide useful user guidance practical applications automated defect detection.
منابع مشابه
Learning Visual Object Detection for Sewer Robots
The goal of the proposed detection system is to search for and identify objects in sewage pipes using a visual sensor. A camera attached to an autonomous sewer robot provides the image data that are interpreted by an attention driven recognition module. Local appearances in the input image are represented in an environment specific subspace that is learned by principal component analysis. In ad...
متن کاملislanding detection methods for microgrids
امروزه استفاده از منابع انرژی پراکنده کاربرد وسیعی یافته است . اگر چه این منابع بسیاری از مشکلات شبکه را حل می کنند اما زیاد شدن آنها مسائل فراوانی برای سیستم قدرت به همراه دارد . استفاده از میکروشبکه راه حلی است که علاوه بر استفاده از مزایای منابع انرژی پراکنده برخی از مشکلات ایجاد شده توسط آنها را نیز منتفی می کند . همچنین میکروشبکه ها کیفیت برق و قابلیت اطمینان تامین انرژی مشترکان را افزایش ...
15 صفحه اولTowards Automated Defect Detection: Object-oriented Modeling of Construction Specifications
This paper describes an ongoing research on the representation and reasoning about construction specifications, which is part of a bigger research project that aims at developing a formalism for automating the identification of deviations and defects on construction sites. We specifically describe the requirements on product and process models and an approach for representing and reasoning abou...
متن کاملA Comparison of the Mahalanobis-Taguchi System to A Standard Statistical Method for Defect Detection
The Mahalanobis-Taguchi System is a diagnosis and forecasting method for multivariate data. Mahalanobis distance is a measure based on correlations between the variables and different patterns that can be identified and analyzed with respect to a base or reference group. This paper presents a comparison of the Mahalanobis-Taguchi System and a standard statistical technique for defect detection ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Hydroinformatics
سال: 2022
ISSN: ['1465-1734', '1464-7141']
DOI: https://doi.org/10.2166/hydro.2022.132