A reliable obstacle detection system is crucial for autonomous surface vehicles (ASVs) to realize fully autonomous navigation with no need of human intervention. However, the current detection methods have particular drawbacks, such as poor detection for small objects, low estimation accuracy caused by water surface reflection, and a high rate of false-positive on water-sky interference. Therefore, we propose a new encoder–decoder structured deep semantic segmentation network, which is a water obstacle detection network based on image segmentation (WODIS), to solve the abovementioned problems. The first design feature of WODIS utilizes the use of an encoder network to extract high-level data based on different sampling rates. In order to improve obstacle detection at sea–sky line areas, an attention refine module (ARM) activated by both global average pooling and max pooling to capture high-level information has been designed and integrated into WODIS. In addition, a feature fusion module (FFM) is introduced to help concatenate the multidimensional high-level features in the decoder network. The WODIS is tested and cross-validated using four different types of maritime datasets with the results demonstrating that the mean intersection over union (mIoU) of WODIS can achieve superior segmentation effects for sea-level obstacles to values as high as 91.3%.

Unmanned aerial systems (UAS) provide two main functions with regards to bridge inspections: (1) high-quality digital imaging to detect element defects; (2) spatial point cloud data for the reconstruction of 3D asset models. With UAS being a relatively new inspection method, there is little in the way of existing framework for storing, processing and managing the resulting inspection data. This study has proposed a novel methodology for a digital information model covering data acquisition through to a 3D GIS visualisation environment, also capable of integrating within a bridge management system (BMS). Previous efforts focusing on visualisation functionality have focused on BIM and GIS as separate entities, which has a number of problems associated with it. This methodology has a core focus on the integration of BIM and GIS, providing an effective and efficient information model, which provides vital visual context to inspectors and users of the BMS. Three-dimensional GIS visualisation allows the user to navigate through a fully interactive environment, where element level inspection information can be obtained through point-and-click operations on the 3D structural model. Two visualisation environments were created: a web-based GIS application and a desktop solution. Both environments develop a fully interactive, user-friendly model which have fulfilled the aims of coordinating and streamlining the BMS process.

This study analyzes passenger incidents in metro stations and their relationship with safety in Valparaiso, Chile. The primary aim is to examine how factors such as station design, passenger flow, and weather conditions influence the frequency and types of incidents in various micromobility spaces within metro stations. A comprehensive data analysis was conducted using records from the Valparaiso Metro between 2022 and 2023. During this period, approximately 500 incidents were documented, providing a substantial dataset for identifying incident patterns and correlations with contributing factors. The analysis revealed that incidents are significantly influenced by peak-hour conditions and weekdays. The platform–train interface emerged as the most complex space for incident occurrences. Specifically, the study found that crowded conditions inside trains during morning and evening rush hours contribute substantially to incidents. In other station spaces, incidents were closely linked to the station type and the presence of stair access. Conversely, stations designed with more accessible features appeared to have fewer incidents. Future studies will expand on this framework by incorporating additional factors and analyzing new data to develop a more comprehensive understanding of incident dynamics.

The study focused on assessing passenger risks specifically at the platform-train interface (PTI). The primary aim of this investigation is to analyze how various factors, including station design, passenger flow, and weather conditions, impact the frequency and types of incidents occurring at this critical interaction point. To achieve this, the study utilized a comprehensive data analysis approach, examining records from the Valparaiso Metro for the period of 2022-2023. During this timeframe, a total of 361 incidents were documented, providing a substantial dataset for evaluating incident patterns and their correlations with different influencing factors. The analysis revealed that incidents are notably influenced by peak hour conditions and weekdays. Specifically, the study found that crowded conditions inside the train during peak hours, which typically occur in the morning and evening rush periods, contribute significantly to the occurrence of incidents. When examining incidents occurring on the platform, the study identified that these are closely related to the type of station and the presence of stairs for station access. Conversely, stations designed with more accessible features might experience fewer such incidents. Future studies will focus on incorporating additional factors and analysing new data to provide a more comprehensive understanding of incident dynamics.