Automated detection and measurement of cracks from monochrome video clips captured by road network survey vehicle

The assessment of cracks is an essential part of a road management system for developing repair and maintenance strategies. Nowadays, road condition assessment is gradually being automated by using various imaging systems. However, the processing of the collected road visual data is still being done manually or semi-automatically in India. There are thousands of kilometres (50,000 km aprox.) of raw video data of Indian National Highways in Central Road Research Institute collected using road network survey vehicles under the Ministry of Road Transport & Highways (MORTH) sponsored research & development (R&D) Scheme (T-5) "Development of Geographic Information System (GIS) based National Highways Information System." Existing methods of data processing are very costly and time consuming. In this paper, a method for automated detection and measurement of cracks out of a large volume of monochrome video clips of Indian Highways is presented. In the proposed method, all the frames of a raw video clip are extracted and grouped automatically using an algorithm into two different categories, viz. clear frames, i.e., without distress, and suspicious frames which may have distress. Then, frames belonging to the suspicious category are subjected to various image processing techniques supported by user defined decision logic for the cracks detection and their measurement. This methodology has been implemented in a Windows XP environment with the help of Visual Studio 2008 and OpenCV, an open source computer vision library, and tested on five different road video clips. The results show that this method can detect and measure cracks automatically with accuracy up to 93%, while saving considerable time and manpower resources. The information extracted using the proposed method can be used for determining maintenance levels of Indian roads and taking further appropriate actions for repair and maintenance.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/1790571
• Supplemental Notes:
  • Abstract used with permission from the publisher.
• Authors:
  • Lokeshwor, Huidrom
  • Das, Lalit K
  • Sud, S K
• Publication Date: 2013-1

Language

• English

Media Info

• Media Type: Print
• Features: Figures; References; Tables;
• Pagination: pp 91-103
• Serial:
  • Indian Highways
  • Volume: 41
  • Issue Number: 1
  • Publisher: Indian Roads Congress
  • ISSN: 0376-7256

Subject/Index Terms

• TRT Terms: Data collection; Flaw detection; Image analysis; Image processing; Pavement cracking; Pavement management systems; Video cameras
• Uncontrolled Terms: Automated detection; Automated survey vehicles
• Geographic Terms: India
• Subject Areas: Highways; Maintenance and Preservation; Pavements; I60: Maintenance;

Filing Info

• Accession Number: 01472757
• Record Type: Publication
• Files: TRIS
• Created Date: Feb 19 2013 8:53AM