Phase unwrapping of vibration signals from pixels to improve structural damage detection

• Millions of vibration signals are obtained from video pixels via PME for damage detection. • The phase-wrapping issue in PME signals is addressed by the proposed Unwrapformer. • Structural damage detection accuracy is considerably improved by the unwrapped signals. In recent years, deep neural networks have been used increasingly to process vibration signals for detecting structural damage. However, the effectiveness of deep neural networks relies on having many vibration signals, which are di