无目标计算机视觉技术在斜拉索振动测试中的应用研究

Application of non-target computer-vision-based technique in stay-cable vibration measurement

以单台普通消费级相机为测试手段,提出了基于无目标计算机视觉技术的斜拉索振动测试新方法,旨在通过分析斜拉索节段的振动视频来测试其振动特性。基于计算机视觉理论,形成该方法的主要关键点包括:相机参数标定、光流分析和拉索位移的重构。通过刚性塑料管模拟拉索振动实验和某人行桥拉索振动测试,验证了该方法的准确性和适用性。实验结果表明:基于计算机视觉的斜拉索振动测试方法具备了工程振动测试的准确性,且与传统拉索振动测试方法相比,该方法拥有无目标非接触式测量、现场操作便捷、成本低等诸多优点。

A novel non-target computer-vision based technique for stay-cable vibration measurement using an off- the shelf camera was developed, the stay-cable dynamic characteristics were measured by analyzing cable vibration video clip. Based on the computer vision theorem, the key points of the technique included camera parameters calibration, optical flow analysis and cable displacement reconstruction. To validate the accuracy and reliability of the proposed technique, vibration simulation test of a rigid plastic pipe and vibration measurement test of a stay-cable on a pedestrian bridge were performed. The results showed that the proposed approach possesses the correctness of vibration measurement, it has advantages of non-target non-contact measurement, more flexibility, and low cost compared with traditional sensors.