Intelligent monitoring method for tamping times during dynamic compaction construction using machine vision and pattern recognition
Hongyang Zhang, Yinlong Jin, Quan Liu, Yueliang Zhao, Qiaoyu Gao
Abstract
Dynamic compaction method (DCM) is currently one of the most commonly used foundation reinforcement techniques. However, manual monitoring is still the mainstream way of DCM tamping counting with low efficiency and high cost. This paper focuses on the tamping times of DCM, and proposes a non-contact Intelligent Monitoring Method for Tamping Times (IM2T2) based on machine vision and pattern recognition technology. The hammer detection methods based on cooperative targets, YOLOv4 and YOLOv4-tiny are compared, and then the motion model based on the hammer position of construction image series is proposed and the vision-based full automatic measurement of tamping times is realized. Moreover, a field test was carried out to verify the applicability of above method. The results of the tamping times measurement indicate that the proposed method can measure the count of tamping under general working conditions with quite high accuracy.