Established Detection Algorithms Research Articles

Rail surface defect inspection via a self-reference template and similarity evaluation

Although railway transportation has rapidly evolved in recent times, the existing manual maintenance of rail infrastructure presents several challenges, such as labor intensity and tediousness. Computer vision, as one of the automatic inspection methods, shows promising prospects for railway detection tasks. In this study, we proposed a novel rail surface defect detection method based on a self-reference template and similarity evaluation. Firstly, a self-reference template was generated by extracting the domain information together with the longitudinal direction of the rail image. We further defined an image structural similarity index, and subsequently compared all the transversal rows with the background template. A coarse-to-fine segmentation method was further proposed to locate the defect. In the first step of the segmentation procedure, rows with large differences were selected using the Otsu algorithm adaptively. The exact position of the defect was then determined by utilizing both gradient magnitude and grayscale information. Our method was evaluated on a public rail surface defects dataset, which included two types of data. The experiment results showed that our method detected type-I and type-II defects with 89.04% and 89.61% recall, and 98.46% and 97.87% precision, respectively. This shows that our method achieved higher accuracy than the established detection algorithms.

Evaluation of morphology discrimination for ventricular tachycardia diagnosis in implantable cardioverter-defibrillators

To reduce inappropriate therapy from implantable cardioverter-defibrillators (ICDs), electrogram morphology discrimination has been developed to improve arrhythmia discrimination without compromising device safety. The purpose of this study was to determine the accuracy of the morphology discrimination algorithm for detecting ventricular tachycardia (VT). Stored electrograms of 795 tachyarrhythmias from 106 patients with a St. Jude Medical ICD (51 single-chamber and 55 dual-chamber) were analyzed by the investigators. The data were analyzed for morphology discrimination alone, sudden onset and stability, and morphology discrimination in combination with sudden onset and stability. Data were corrected for multiple episodes within a patient with the generalized estimating equation method. Using the nominal template match of 60%, morphology discrimination alone provided sensitivity and specificity of 78% and 95% for single-chamber ICDs and 63% and 92% for dual-chamber ICDs, respectively. Based on the receiver operator characteristic curve, the optimal-match percent threshold was 80% to 85% but at the expense of specificity. Morphology discrimination combined with sudden onset and stability increased sensitivity to 98% with specificity of 86% in single-chamber devices. In dual-chamber devices, the loss in sensitivity is compensated by rate branch analysis, yielding a sensitivity of 98%. Arrhythmia discrimination based on electrogram morphology has the potential to reject atrial tachyarrhythmias. However, there is a risk for underdetection of ventricular tachyarrhythmias if arrhythmia discrimination is primarily based on morphology. To guarantee patient safety in single-chamber devices, the morphology discrimination algorithm must be programmed in combination with established detection algorithms. In dual-chamber devices, loss of sensitivity is compensated by the V > A rate branch.