Detection of Roadway Sign Condition Changes Using Multi-scale Sign Image Matching (M-SIM)
Roadway signs are important for safety, and transportation agencies need to identify sign condition changes to perform timely maintenance, including replacement. Currently, sign condition changes are inspected manually in the field, which is time consuming, costly, and sometimes dangerous. This paper first proposes a novel algorithm to detect 3 condition changes: missing, tilted and blocked signs, using GPS data and video log images. The algorithm consists of 3 steps: 1) Multi-scale Sign Image Matching (M-SIM), 2) image feature analysis, and 3) sign condition change detection and classification. The algorithm was tested using images with simulated sign condition changes and actual video images taken in Fiscal Year 2003 and 2005 by the Louisiana Department of Transportation and Development. The tests demonstrate that the algorithm is effective to detect the 3 types of sign condition changes. Out of 34,000 actual video log images, the algorithm detected and classified 100% of the missing signs, 72.7% of the tilted signs, and 66.7% of the blocked signs, for an overall 74.3% detection rate. These results show that the algorithm is useful for developing an intelligent roadway sign condition change detection system.
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/issn/00991112
-
Authors:
- Tsai, Yichang
- Hu, Zhaozheng
- Alberti, Chris
- Publication Date: 2010-4
Language
- English
Media Info
- Media Type: Print
- Features: Figures; Photos; References; Tables;
- Pagination: pp 391-405
-
Serial:
- Photogrammetric Engineering and Remote Sensing
- Volume: 76
- Issue Number: 4
- Publisher: American Society for Photogrammetry and Remote Sensing
- ISSN: 0099-1112
Subject/Index Terms
- TRT Terms: Global Positioning System; Highway maintenance; Highway safety; Image analysis; Image processing; Maintenance practices; Structural health monitoring; Traffic control devices; Traffic signs; Transportation departments
- Identifier Terms: Louisiana Department of Transportation and Development
- Uncontrolled Terms: Condition monitoring
- Subject Areas: Highways; Maintenance and Preservation; Operations and Traffic Management; I61: Equipment and Maintenance Methods; I73: Traffic Control;
Filing Info
- Accession Number: 01156801
- Record Type: Publication
- Files: TRIS
- Created Date: May 24 2010 2:07PM