Improved Vision-Based Method for Detection of Unauthorized Intrusion by Construction Sites Workers (Record no. 814196)

MARC details
000 -LEADER
fixed length control field 02249aab a2200181 4500
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 231002b20232023|||mr|p| |||| 00| 0 eng d
100 ## - MAIN ENTRY--PERSONAL NAME
Personal name Wen, Hua-Ping, Zhang, Wen-Jie, Ge,Hui-Bin, Luo, Yaozhi, Todd, Michael D.
9 (RLIN) 878298
245 ## - TITLE STATEMENT
Title Improved Vision-Based Method for Detection of Unauthorized Intrusion by Construction Sites Workers
300 ## - PHYSICAL DESCRIPTION
Extent 1-12p.
520 ## - SUMMARY, ETC.
Summary, etc. The construction site environment is quite complex with many dangerous hazards (e.g., foundation pits, holes). To avoid injuries, workers must wear helmets that are color-coded for the specific type of work, which is helpful to identify whether workers are in permitted areas. Therefore, it is possible to identify unauthorized intrusion by classifying the safety helmets. This study proposes a vision-based method called Helmet–Yolov5 to automatically detect unauthorized intrusions by workers on construction sites. Multiple improvement measures are made to enhance the model performance. First, the attention mechanism is used to enhance the weights of object regions in the image, which makes the detection of small objects more effective. Second, atrous spatial pyramid pooling is adopted to preserve the detail information of the image. Third, the universal upsampling operator is introduced to fuse image features at different scales. To verify the effectiveness of the improved model, images collected from a real construction site are used to build a large-scale image dataset of safety helmets for model testing. It shows that the proposed Helmet-Yolov5 model is more accurate than the original Yolov5 model, also with high inference speed. Compared to other state-of-the-art models (e.g., Yolov4), the Helmet-Yolov5 model has considerable advantages in term of high detection accuracy and efficiency.
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element Technology Assimilation
9 (RLIN) 878299
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element Digital Technologies
9 (RLIN) 878300
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element Heavy Equipment
9 (RLIN) 878301
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element Measurement Invariance of Composite Models
9 (RLIN) 878302
773 0# - HOST ITEM ENTRY
Place, publisher, and date of publication Reston,Virginia, U.S.A : American Society of Civil Engineers/ American Concrete Institute
International Standard Serial Number 07339364
Title ASCE: Journal of Construction Engineering and Management
856 ## - ELECTRONIC LOCATION AND ACCESS
Uniform Resource Identifier <a href="https://ascelibrary.org/doi/10.1061/JCEMD4.COENG-13294">https://ascelibrary.org/doi/10.1061/JCEMD4.COENG-13294</a>
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Source of classification or shelving scheme Dewey Decimal Classification
Suppress in OPAC No
Koha item type Articles
Holdings
Not for loan Home library Serial Enumeration / chronology Total Checkouts Date last seen Koha item type
  Periodical Section Vol.149, No.7(July, 2023)   02/10/2023 Articles