| Title |
Building-up and Feasibility Study of Image Dataset of Field Construction Equipments for AI Training |
| Authors |
나종호(Na, Jong Ho) ; 신휴성(Shin, Hyu Soung) ; 이재강(Lee, Jae Kang) ; 윤일동(Yun, Il Dong) |
| DOI |
https://doi.org/10.12652/Ksce.2023.43.1.0099 |
| Keywords |
토목 현장 데이터; 건설 장비; 딥러닝; 영상처리 Civil-engineering dataset; Construction equipment; Deep learning; Image processing |
| Abstract |
Recently, the rate of death and safety accidents at construction sites is the highest among all kinds of industries. In order to applyartificial intelligence technology to construction sites, it is essential to secure a dataset which can be used as a basic training data. In thispaper, a number of image data were collected through actual construction site, for which major construction equipment objects mainlyoperated in civil engineering sites were defined. The optimal training dataset construction was completed by annotation process ofabout 90,000 image dataset. Reliability of the dataset was verified with the mAP of over 90 % in use of YOLO, a representative modelin the field of object detection. The construction equipment training dataset built in this study has been released which is currentlyavailable on the public data portal of the Ministry of Public Administration and Security. This dataset is expected to be freely used forany application of object detection technology on construction sites especially in the field of construction safety in the future. |