Automatic Identification of Idling Reasons in Excavation Operations Based on Excavator–Truck Relationships

Excavators and trucks are important equipment for earthwork operations, which make major contributions to construction productivity. To control the work efficiency and productivity of earthwork equipment, computer vision (CV) methods have been proposed to monitor equipment operations from site surveillance videos. Existing methods can recognize equipment activities to estimate the working and idling times. Idling time is an important factor that influences equipment productivity; however, the causes of equipment idling have not been considered in previous CV methods. Therefore, this research proposes a method to identify the main causes of excavator and truck idling by analyzing their interactive operations. First, the activities of the excavators and trucks are identified using convolutional neural networks. Then, work groups of excavators and trucks are clustered. Finally, the relationships between each excavator and the surrounding trucks are analyzed to identify the potential reason for idling. The proposed method was validated with videos from several construction sites, and the results were promising.

• Record URL:
  • https://doi.org/10.1061/(ASCE)CP.1943-5487.0000981
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/08873801
• Supplemental Notes:
  • © 2021 American Society of Civil Engineers.
• Authors:
  • Chen, Chen
  • Zhu, Zhenhua
  • Hammad, Amin
  • Akbarzadeh, Mohammad
• Publication Date: 2021-9

Language

• English

Media Info

• Media Type: Web
• Pagination: 04021015
• Serial:
  • Journal of Computing in Civil Engineering
  • Volume: 35
  • Issue Number: 5
  • Publisher: American Society of Civil Engineers
  • ISSN: 0887-3801

Subject/Index Terms

• TRT Terms: Engine idling; Excavating equipment; Excavation; Neural networks; Surveillance; Trucks
• Subject Areas: Data and Information Technology; Geotechnology; Highways; Vehicles and Equipment;

Filing Info

• Accession Number: 01789749
• Record Type: Publication
• Files: TRIS, ASCE
• Created Date: Nov 30 2021 10:23AM