Vol. - No. | Vol.9 - No.4 |
---|---|
Date | Dec., 2020 |
Title | Equipment and Worker Recognition of Construction Site with Vision Feature Detection |
Author | Shaowen Qi1, Jiazeng Shan2, and Lei Xu3 |
Institutions |
1Department of Civil Engineering, Tongji University, China 2Department of Civil Engineering, Tongji University, China 3Shanghai Construction No.1 (Group) Co., Ltd. |
Abstract |
This article comes up with a new method which is based on the visual characteristic of the objects and machine learning technology to achieve semi-automated recognition of the personnel, machine & materials of the construction sites. Balancing the real-time performance and accuracy, using Faster RCNN (Faster Region-based Convolutional Neural Networks) with transfer learning method appears to be a rational choice. After fine-tuning an ImageNet pre-trained Faster RCNN and testing with it, the result shows that the precision ratio (mAP) has so far reached 67.62%, while the recall ratio (AR) has reached 56.23%. In other word, this recognizing method has achieved rational performance. Further inference with the video of the construction of Huoshenshan Hospital also indicates preliminary success. |
Keyword | Object detection, Construction Site management, Transfer learning, CNN |
PP. | PP.335~342 |
Paper File | View |