3D Displacement Monitoring System Using Computer Vision Technology for Drainage Well''s Deformation

• Main Authors: Han-Lun Chen, 陳漢倫
• Other Authors: 蘇苗彬
• Format: Others
• Language: zh-TW
• Published: 2017
• Online Access: http://ndltd.ncl.edu.tw/handle/26613807029840137444

碩士 === 國立中興大學 === 土木工程學系所 === 105 === Lishan is one important observation area to prevent the occurrences of landslides in Taiwan. In order to expel deeper underground water inside the area, various drainage well''s were established in Lishan. Drainage well''s is often set up in landslide area to reduce underground water accumulation more efficiently, so as to enhance the stability of slope land. On the other hand, the occurrence of earth slide may also cause the deformation of drainage well''s. Hence, the observation on the shape of drainage well''s is also an effective measure to determine whether there are earth slides in the area. This study installed four Raspberry Pi around one of the drainage well''s, drainage well''s No.W6, in Lisan and utilized OpenCV to interpret the signals inside the drainage well''s. There were four levels in this drainage well''s. The four Raspberry Pi were assigned with different serial number, Pw6-B1, Pw6-B2, Pw6-P3, and Pw6-B4, and were sent to different level to monitor the signals at each level respectively. Through both lab testing and on-site testing, the study observed the signals for a long period and obtained stable statistics, which was further discussed after conducting data analysis. From observing the changes in full-time trend and daily average trend, the study was able to determine the changes of this drainage well''s. The drainage well''s displacement observation system by computer vision in the future may become an early warning reference for landslides in Lishan area.