Automatic Detection of Bridge Deck Condition From Ground Penetrating Radar Images

Accurate assessment of the quality of concrete bridge decks and identification of corrosion induced delamination lead to economic management of bridge decks. It has been demonstrated that ground penetrating radar (GPR) can be successfully used for such purposes. The growing demand on GPR has brought into the challenge of developing automatic processes necessary to produce a final accurate interpretation. However, there have been few publications targeting at automatic detection of bridge deck delamination from GPR data. This paper proposes a novel method using partial differential equations to detect rebar (or steel-bar) mat signatures of concrete bridges from GPR data so that the delamination within the bridge deck can be effectively located. The proposed algorithm was tested on both synthetic and real GPR images and the experimental results have demonstrated its accuracy and reliability, even for diminished image contrast and low signal-to-noise ratio. Therefore, an accurate deterioration map of the bridge deck can be generated automatically. Note to Practitioners-This work was motivated by the problem of automatic detection of delamination inside a bridge deck. Nowadays, to generate the final bridge condition report from GPR data still relies on experienced civil engineers' excessive intervention and scan-by-scan processing. Therefore, the current method is both time and labor-consuming. Moreover, it has limited reproducibility and is subject to an operator's variability. This work presents a new approach to automatically generate the bridge deterioration report. It derives mathematical equations to fit the rebar shape in GPR images and applies the results to real data. The rebar inside the bridge deck can be detected accurately in spite of the low signal-to-noise ratio and low contrast. The final deterioration map is then generated based on the corroded rebar detection results automatically. This work is already tested and used in a real bridge in New Jersey, U.S.A.