| The research in the thesis investigates the use of minimal path techniques to track and detect cracks, modeled as curves, in critical infrastructure like pavements and bridges. We developed a novel minimal path algorithm to detect curves with complex topology that may have both closed cycles and open sections using an arbitrary point on the curve as the sole input. Specifically, we apply the novel algorithm to three problems: semi-automatic crack detection, detection of continuous cracks for crack sealing applications and detection of crack growth in structures like bridges.;First, we provide the background of the problem of crack detection and critically assess the strengths and limitations of six current algorithms. Detection of cracks in these structures is very challenging because of multiple textures, shadows, variable lighting, irregular background and high noise present in the images, and this motivated our research into minimal path techniques. Next, a background of the minimal path techniques theory is provided. The current state of the art minimal path techniques only work with prior knowledge of either both terminal points or one terminal point plus total length of the curve. For curves with multiple branches, all terminal points need to be known. Therefore, we developed a new algorithm that detects curves and relaxes the necessary user input to one arbitrary point on the curve. The document presents the systematic development of this algorithm in three stages. First, an algorithm that can detect open curves with branches was formulated. Then this algorithm was modified to detect curves that also have closed cycles. Finally, a robust curve detection algorithm was devised that can increase the accuracy of curve detection. The robust algorithm tackles two problems: spurious detection of curve portions and inability to detect complex topological curves that have sharp corners at branches. The algorithm was applied to crack images and the results of crack detection were validated against the ground truth. A new quantification measure called the buffered Hausdorff distance measure was developed for the experimental validation. In addition, the algorithm was also used to detect features like catheter tube and optical nerves in medical images. We finally conclude by giving some future research directions. In particular, the algorithm can be extended to detect higher dimensional curves and the computational speed of the algorithm can be improved by optimizing the use of redundant information. |
