利用無人機與機器學習於邊坡巡檢與分析之研究

A Research of UAV and Machine Learning on Slope Sliding

吳仲恩(Jhong-En Wu)；潘乃欣(Nai-Hsin Pan)

無人機 ； 水保設施 ； HSB ； 深度學習 ； 影像辨識 ； Unmanned Aerial Vehicle ； Water and Soil Felicities ； HSB ； Deep Learning ； Image Classification

物業管理學報

14卷1期（2023 / 03 / 30）

29 - 40

繁體中文;英文

水保設施因為多座落於山區且數量及分布廣泛，因此造成許多設施交通可及性低，進而使得在水保設施在例行性巡檢或是於災後防治管理的困難度大大增加，因此增進管理設施之效率便十分重要。此研究使用無人機（UAV）進行航拍，以克服水保設施中無法拍攝到的範圍以及達到大量拍攝的目的。並基於現有之對水保設施的異常樣態分級與維護建議上，以python所建置的深度學習演算法中進行自動化辨識與維護建議。在辨識完成後，利用HSB色彩空間進行異常樣態的面積概算。在自動辨識中正規化方法成效達到0.966及神經網路之成效為0.959。在異常樣態面積概算部分，在使用HSB色彩空間下概算，並與現有之面積概算方法比較，其誤差約為7%，此誤差經專家評估其影響性低。

Water and soil conservation felicities are located in mountain area and distributed widely, which is lead to spend more time on traffic, and there have the difficulty of the routine detection or post-disaster response management will be higher. This is the importance to improve felicities management. This research will use UAV to surmount the area that people can't reach to take picture and achieve the propose of numerous photographing. In the other hand, this research would build an automatically process based on deep learning algorism from Python, in order to give an automatic classification and suggestion. Then, area of abnormal situation in case will use HSB(Hue, Saturation, Brightness) models to roughly calculated. In automatic identification, got 0.966points by Regularization process. And got points 0.959 by Neural Network. After expert of this filed checked these two scores, the identify level from automatic model is same with expert's. In the section of area of abnormal situation rough calculation, using HSB representation model could get the colour value on each item, and compared to existed area calculated method, the error rate is close to 7%. Because of felicities detection belongs to large area measurement, it means to the influence of calculated error is very low by expert's estimate.

1. Biswas, S.,Nath, S.,Dey, S.(2022).Tangent-cut optimizer on gradient descent: an approach towards Hybrid Heuristics.Artif Intell Rev,55,1121-1147.
2. Flah, Majdi,Suleiman, Ahmed R.,Nehdi, Moncef L.(2020).Classification and quantification of cracks in concrete structures using deep learning image-based techniques.Cement and Concrete Composites,114,103781.
3. Liu, Zhenqing,Cao, Yiwen,Wang, Yize,Wang, Wei(2019).Computer vision-based concrete crack detection using U-net fully convolutional networks.Automation in Construction,104,129-139.
4. Mashford, John,Rahilly, Mike,Davis, Paul,Burn, Stewart(2010).A morphological approach to pipe image interpretation based on segmentation by support vector machine.Automation in Construction,19(7),875-883.
5. Tziavoua, O.,Pytharoulia, S.,Souterb, J.(2017).Unmanned Aerial Vehicle (UAV) based mapping in engineering geological surveys Considerations for optimum results.Engineering Geology,232,12-21.
6. Yeh-James，2017，資料分析-機器學習-第 5-1 講卷積神經網絡介紹https://medium.com/jameslearningnote/
7. 李宸綾(2022)。花蓮縣，國立東華大學資訊工程學系。
8. 范萬淵(2021)。明新科技大學。
9. 張智岳(2020)。台中市，國立中興大學土木工程學系所。
10. 莊凱翔(2012)。台中市，國立中興大學水土保持學系所。
11. 陳奎言(2016)。雲林縣，國立雲林科技大學工程科技研究所。
12. 陳舜詮(2022)。彰化縣，國立彰化師範大學機電工程學系。
13. 黃美甄,張國楨(2014)。無人飛行載具數值地形模型精度評估及應用。中國土木水利工程學會，41(4)
14. 楊鎮銘，（2022），AI 共學社群/電腦視覺與深度學習馬拉松/D2：Color presentation 介紹。https://reurl.cc/ROYdrZ
15. 蔡博翰(2021)。雲林縣，國立雲林科技大學營建工程系。