Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Automatic Top-View Transformation and Image Stitching of In-Vehicle Smartphone Camera for Road Crack Evaluation
Current technology for road crack evaluation uses precision profilers with line scan cameras and manual detection of road cracks from captured images. In Japan, the crack ratio is evaluated using a top-view photo by the coverage of the area of 0.5 m rectangular grid traversed by cracks usually over a 20 m span of road. Previous research using in-vehicle smartphone camera were conducted but the crack ratio cannot be calculated based on the definition. This paper proposes an automatic top-view transformation and image stitching algorithm for road crack evaluation by utilizing video captured of an in-vehicle smartphone camera. A vision-based approach for camera calibration is proposed since camera parameters cannot be easily obtained. Four conditions are used to perform the parameter calibration. (1) horizontal manhole axis, (2) parallel lane line, (3) circular manhole, (4) vertical lane line conditions. A frame with straight lane lines and a circular manhole is automatically selected by object detection. Top-view transformation is performed on these images and parameters are adjusted until both conditions are satisfied. The same parameters are then applied to the other frames assuming that the camera parameters (i.e., location, orientation, and settings remain the same). After the successful top-view transformation of frames, feature matching is conducted to pairs of successive frames to calculate the homography matrix between the two images. This is used for the image stitching of successive frames and obtain the translation offset between the images. Based on the calculated translation offset and the extracted frame distance interval the pixel-to-real-distance conversion factor is calculated. A fine resolution image of road top-view can be produced that can be used for the evaluation of road cracks.
Automatic Top-View Transformation and Image Stitching of In-Vehicle Smartphone Camera for Road Crack Evaluation
Current technology for road crack evaluation uses precision profilers with line scan cameras and manual detection of road cracks from captured images. In Japan, the crack ratio is evaluated using a top-view photo by the coverage of the area of 0.5 m rectangular grid traversed by cracks usually over a 20 m span of road. Previous research using in-vehicle smartphone camera were conducted but the crack ratio cannot be calculated based on the definition. This paper proposes an automatic top-view transformation and image stitching algorithm for road crack evaluation by utilizing video captured of an in-vehicle smartphone camera. A vision-based approach for camera calibration is proposed since camera parameters cannot be easily obtained. Four conditions are used to perform the parameter calibration. (1) horizontal manhole axis, (2) parallel lane line, (3) circular manhole, (4) vertical lane line conditions. A frame with straight lane lines and a circular manhole is automatically selected by object detection. Top-view transformation is performed on these images and parameters are adjusted until both conditions are satisfied. The same parameters are then applied to the other frames assuming that the camera parameters (i.e., location, orientation, and settings remain the same). After the successful top-view transformation of frames, feature matching is conducted to pairs of successive frames to calculate the homography matrix between the two images. This is used for the image stitching of successive frames and obtain the translation offset between the images. Based on the calculated translation offset and the extracted frame distance interval the pixel-to-real-distance conversion factor is calculated. A fine resolution image of road top-view can be produced that can be used for the evaluation of road cracks.
Automatic Top-View Transformation and Image Stitching of In-Vehicle Smartphone Camera for Road Crack Evaluation
Lecture Notes in Civil Engineering
Wu, Zhishen (Herausgeber:in) / Nagayama, Tomonori (Herausgeber:in) / Dang, Ji (Herausgeber:in) / Astroza, Rodrigo (Herausgeber:in) / Geda, Jose Maria G. (Autor:in) / Xue, Kai (Autor:in) / Nagayama, Tomonori (Autor:in)
Experimental Vibration Analysis for Civil Engineering Structures ; Kapitel: 47 ; 567-579
24.08.2022
13 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Crack Detection of Curved Surface Structure Based on Multi-Image Stitching Method
DOAJ | 2024
|Quantitative road crack evaluation by a U‐Net architecture using smartphone images and Lidar data
Wiley | 2024
|Automatic Crack Detection on Pressed Panels Using Camera Image Processing
British Library Conference Proceedings | 2016
|A Large-Crack Image-Stitching Method with Cracks as the Regions of Interest
DOAJ | 2024
|