Visual enhancement-based bridge detection algorithm and technique
In order to identify small vibrations of the bridge structure,a target center detection algorithm based on orientation code matching(OCM)method is proposed.The algorithm first uses the OCM method to achieve pixel-level matching,and then uses the target center detection algorithm for accurate tracking in the best matching area.Through laboratory experiments,the OCM-based target center detection algorithm is com-pared with the phase-based optical flow method and the OCM sub-pixel implementation algorithm,and the ap-plicability of the three algorithms in different vibration amplitudes and practical engineering applications is ex-plored,which provides a technical scheme comparison basis for real bridge detection.The results show that the proposed algorithm can accurately identify the structural vibration displacement and frequency under various vi-bration amplitudes,and the feasibility of target sticking should be considered in the application of real bridge.The phase-based optical flow method can accurately identify the vibration displacement and frequency of the structure under small vibration cases with amplitude index less than 2 mm or 1.7 pixels.The resolution accura-cy of the OCM sub-pixel implementation algorithm depends on the number of interpolation points,and has a similar effect to the proposed algorithm under large amplitude vibration cases.
国家科技期刊平台
NSTL
万方数据
