No abstract

This paper presents an image-based crack detection system, in which its architecture is modified to use deep convolutional neural networks in a feature extraction step and other classifiers in the classification step. In the classification step, classifiers including Support Vector machines (SVMs), Random Forest (RF) and Evolutionary Artificial Neural Network (EANN) are used as an alternative to a Softmax classifier and the performance of these classifiers are studied. The data set was created from various types of concrete structures using a standard digital camera and an unmanned aerial vehicle (UAV). The collected images are used in the crack detection system and in creating a 3D model of a sample concrete building using an image- based 3D photogrammetry technique. Then, the 3D model is used to create a mosaic image, in which the crack detection system was applied to create a global view of a crack density map. The map is then projected onto the 3D model to allow cracks to be located in the 3D world. A comparative study was conducted on the proposed crack detection system and the results prove that the combined architecture of CNN as a feature extractor and SVM as a classifier shows the best performance with the accuracy of 92.80. The results also show that the modified architecture by integrating CNN and other types of classifiers can improve a system performance, which is better than using the Softmax classifier.

No abstract

Visual inspection is a common technique to detect and examine the state of health of the structural system. Periodic inspection is carried out to determine if anomalies, such as cracks and surface paint, found in previous visits have changed in appearance over time. The image-based change detection techniques require accurate geometrical and photometrical corrections in pre-processing steps to minimize errors. Although several techniques have been proposed to remove geometrical errors, they still fail to align image correctly, which often results in inaccuracy in a change detection system. In this paper, a change detection system is proposed to tackle this problem. The system acquired images via an unmanned aerial vehicle. Then, the acquired images were manually processed to identify damages, such as cracks, which were used to guide a drone to obtain more images of damage areas for monitoring purpose. The images were then used to obtain a 3D surface model and camera calibration through Structure from Motion (SfM), which were used in the image synthesis technique to obtain an image with identical camera parameters as a queried image for accurate geometrical adjustment. The synthesized images were used to compare with the queried image to see if there were changes between them. In this research project, it was showed that the drone can be used to monitor problematic areas and the image synthetic technique via 3D modeling can be used in geometrical registration to improve a change detection system.

Heritage structures are important for tourism and for learning about nations' history. Historical sites around the world are in damaged conditions due to various factors from the environment, man-made activities or natural calamities. To ensure safety and avoid further deterioration, digital reconstruction of heritage sites can be used to create 3D virtual models of these structures for archiving and for inspection purpose. This paper presents a technique to reconstruct a high-quality image-based 3D model of a heritage structure. An exemplar-based inpainting algorithm was used for removing deformable obstacles such as trees in 2D images since such obstacles are unwanted in a final 3D model. They also create noise in the 3D modeling process, which makes the final 3D model less accurate. In this paper, an inpainting algorithm is applied to generate implied texture to fill holes that occurred from removing objects so that the generated 3D model does not contain any hole and becomes watertight. The modified exemplar-based inpainting algorithm was implemented on 2D images to remove unwanted objects, and then the image-based 3D modeling technique was applied to create a 3D model that did not contain any unwanted objects. The results show that the final 3D model is more accurate when applied the object removal process and the model provides better visualization for heritage structures.