Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
In order to meet the fast and accurate automatic detection requirements of equipment maintenance in railway tunnels in the era of high-speed railways, as well as adapting to the high dynamic, low-illumination imaging environment formed by strong light at the tunnel exit, we propose an automatic inspection solution based on panoramic imaging and object recognition with deep learning. We installed a hyperboloid catadioptric panoramic imaging system on an inspection vehicle to obtain a large field of view as well as to shield the high dynamic phenomena at the tunnel exit, and proposed a YOLOv5-CCFE object detection model based on railway equipment recognition. The experimental results show that the mAP@0.5 value of the YOLOv5-CCFE model reaches 98.6%, and mAP@0.5:0.95 reaches 68.9%. The FPS value is 158, which can meet the automatic inspection requirements of railway tunnel equipment along the line and has high practical application value.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10346268 | PMC |
| http://dx.doi.org/10.3390/s23135986 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Progress of a Novel Dentistry Teaching Model Based on the Combination of Virtual Reality and Artificial Intelligence Technologies in Optimizing Cognitive Load: A Systematic Review.
J Dent Educ
September 2025
Department of Oral and Maxillofacial Surgery, Stomatological Hospital, School of Stomatology, Southern Medical University, Guangzhou, P. R. China.
Background: Virtual reality (VR) and artificial intelligence (AI) technologies have advanced significantly over the past few decades, expanding into various fields, including dental education.
Purpose: To comprehensively review the application of VR and AI technologies in dentistry training, focusing on their impact on cognitive load management and skill enhancement. This study systematically summarizes the existing literature by means of a scoping review to explore the effects of the application of these technologies and to explore future directions.
Floral development and phenolic compounds production in Agastache rugosa through light regulation.
Planta
September 2025
Smart Farm Research Center, Korea Institute of Science and Technology (KIST), Gangneung, Gangwon, 25451, Republic of Korea.
The regulation of photoperiod and light intensity significantly affected Agastache rugosa by enhancing growth, modifying flowering dynamics, and promoting the accumulation of key phenolic compounds. Agastache rugosa is a medicinal and aromatic plant valued for its bioactive compounds, which contribute to its application in the flavoring, perfume, and food industries. However, variability in the composition of the bioactive compounds poses challenges for its commercial utilization.
View Article and Find Full Text PDFStereotactic Step-by-step Dissection of the Anterior Transpetrosal Approach: A Three-dimensional Photogrammetry-based Educational Tool for Neurosurgeons.
Neurol Med Chir (Tokyo)
September 2025
Department of Neurosurgery, Keio University School of Medicine.
Skull base surgery requires precise spatial recognition; however, existing educational tools remain limited. To address this issue, we developed a step-by-step stereotactic three-dimensional anatomical model of the anterior transpetrosal approach using digital photogrammetry. Cadaveric dissection was subsequently performed in 17 steps, of which 10 were reconstructed into three-dimensional models.
View Article and Find Full Text PDFDesign of a modified model predictive control and composite control strategy for hydraulic turbine regulation system.
ISA Trans
August 2025
Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education, Wuhan 430081, China; Institute of Robotics and Intelligent Systems, Wuhan University of Science and Technology, Wuhan 430081, China; School of Artifitial Intelligence and Automation, Wuhan U
As a critical component in hydropower systems, the Hydraulic Turbine Regulation System (HTRS) exhibits strong coupling characteristics that impose substantial challenges on control system design, necessitating the development of high-performance control strategies. To address the complex control requirements, this paper proposes an improved T-S fuzzy modeling method based on the Luenberger observer theory. It constructs a system model that combines high accuracy and simplicity.
View Article and Find Full Text PDFEnvironmental stressor-induced functional and expression dynamics of glutathione S-transferase genes in bees.
Pestic Biochem Physiol
November 2025
College of Life Sciences, Chongqing Normal University, Chongqing, China; Key Laboratory of Pollinator Resources Conservation and Utilization of the Upper Yangtze River, Ministry of Agriculture and Rural Affairs, Chongqing, China; Chongqing Key Laboratory of Vector Control and Utilization, Chongqing,
As key pollinators, bees are increasingly threatened by environmental stressors such as heavy metals, pesticides, and temperature fluctuations, which can cause oxidative stress and disrupt cellular homeostasis. Glutathione S-transferases (GSTs) play crucial roles in antioxidant defense and detoxification, yet systematic studies on bee GST families remain limited. Here, we conducted a genome-wide analysis of cytosolic GST genes in 13 bee species, identifying 146 genes in total.
View Article and Find Full Text PDF