The deterioration of underground storm drain infrastructure represents a significant challenge for urban asset management, with failures often remaining undetected until catastrophic events occur. This paper presents a novel inspection information management system that leverages 360-degree panoramic imaging and automated damage detection to enhance the efficiency and comprehensiveness of storm drain condition assessment. The proposed system employs commercially available 360-degree cameras mounted on robotic platforms to capture equirectangular panoramic images of drain interiors, which are then processed through a specialized framework. This framework converts equirectangular images to cubemap representations to address spherical distortion challenges, applies semantic segmentation for automated corrosion detection, and reconstructs processed cubemaps into panoramic visualizations with damage overlay information. The system integrates Structure from Motion (SfM) techniques to establish spatial relationships between multiple camera positions, enabling intuitive navigation through the storm drain network while maintaining viewing context. For damage detection, we implement a modified Segment Anything Model (SAM) with Low-Rank Adaptation (LoRA) fine-tuning, specifically optimized for corrosion identification in storm drain environments. Field implementation demonstrates the system’s effectiveness in detecting and visualizing corrosion damage while minimizing false positives through selective face processing. The developed system operates in both cloud-based and local environments, providing flexible deployment options while maintaining consistent functionality. By enabling comprehensive visual documentation, efficient navigation, automated damage detection, and systematic recording of inspection information, this system contributes to the development of digital twins for underground infrastructure management and supports more effective maintenance planning.

To discriminate between male-sterile and male-fertile Cryptomeria japonica (C. japonica) accurately, this study aimed to construct a discrimination model for identifying between male-fertility and male- sterility in C. japonica using fluorescence spectroscopy. The male strobili of the male-fertile and male- sterile C. japonica were divided into halves, and the internal fluorescence properties were measured by the excitation-emission matrix (EEM). Totally 10 data sets were derived from the EEM with different preprocessing methods, each of which was subjected to principal component analysis to construct a classification model based on the support vector machine (SVM). The data set with the highest F1 score (a harmonic mean of precision and recall) was the second derivative synchronous fluorescence spectra with Δλ = 80 nm and a window size of 11 nm, which shown a score of 98.5%. These spectra were deemed to be of high accuracy, as it was able to capture the fluorescence peaks that were specific to the male-fertile and male-sterile strobili. Additional data splitting analysis indicated that the kernel function k=1 in SVM was the optimum, resulting in a 100% precision to the test data. The results suggested the potential for utilizing fluorescence to distinguish between male-sterility and male-fertility in C. japonica.