Width Calculation of Tiny Bridge Cracks Based on Unmanned Aerial Vehicle Images

Introduction: Crack is the main bridge disease. The monitoring of the crack width is the key for determining whether the bridge needs to be maintained. The systematic and automatic detection of bridge cracks can be realized using the crack images, which are captured using unmanned aerial vehicles (UAV). Methods: Cracks in the image with a complex background and low contrast ratio are difficult to detect. In order to detect the tiny cracks, the image is preprocessed by homomorphic filtering to enhance the contrast ratio. It is a necessary step that makes the color clustering be used in the detection. An adaptive color clustering method is proposed to detect cracks without additional initialization. Morphological method is also used to obtain clean edges and skeletons. Results: The proposed method can accurately detect the crack areas with an actual width greater than 0.13 mm, and the absolute error is only 0.0013 mm. The relative error for all test images are smaller than 15.6%. Cracks over 0.2 mm need to be filled. Therefore, this error is completely acceptable in practice. Discussion: The proposed method is practical and reproducible for bridge disease automatic inspection based on UAV. In order to verify its advantage, the proposed method is compared with a state-of-the-art method, which is published on Sensors. The proposed method is proven to be better for images with water stains in its complex background. Conclusion: The proposed method can calculate the width of tiny cracks accurately, even if the width is below 0.2 mm.