Taiwan, frequently affected by extreme weather causing phenomena such as earthquakes and typhoons, faces a high incidence of rockfall disasters due to its largely mountainous terrain. These disasters have led to numerous casualties, government compensation cases, and significant transportation safety impacts. According to the National Science and Technology Center for Disaster Reduction records from 2010 to 2022, 421 out of 866 soil and rock disasters occurred in eastern Taiwan, causing traffic disruptions due to rockfalls. Since traditional sensors of disaster detectors only record changes after a rockfall, there is no system in place to detect rockfalls as they occur. To combat this, a rockfall detection and tracking system using deep learning and image processing technology was developed. This system includes a real-time image tracking and recognition system that integrates YOLO and image processing technology. It was trained on a self-collected dataset of 2490 high-resolution RGB images. The system's performance was evaluated on 30 videos featuring various rockfall scenarios. It achieved a mean Average Precision (mAP50) of 0.845 and mAP50-95 of 0.41, with a processing time of 125 ms. Tested on advanced hardware, the system proves effective in quickly tracking and identifying hazardous rockfalls, offering a significant advancement in disaster management and prevention.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11050843 | PMC |
| http://dx.doi.org/10.3390/jimaging10040078 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Fixation-related potentials during a virtual navigation task: The influence of image statistics on early cortical processing.
Atten Percept Psychophys
January 2025
U.S. DEVCOM Army Research Laboratory, Humans in Complex Systems, Aberdeen Proving Ground, MD, USA.
Historically, electrophysiological correlates of scene processing have been studied with experiments using static stimuli presented for discrete timescales where participants maintain a fixed eye position. Gaps remain in generalizing these findings to real-world conditions where eye movements are made to select new visual information and where the environment remains stable but changes with our position and orientation in space, driving dynamic visual stimulation. Co-recording of eye movements and electroencephalography (EEG) is an approach to leverage fixations as time-locking events in the EEG recording under free-viewing conditions to create fixation-related potentials (FRPs), providing a neural snapshot in which to study visual processing under naturalistic conditions.
View Article and Find Full Text PDFDevelopment of a fixed-order [Formula: see text] controller for a robust P&O-MPPT strategy to control poly-crystalline solar PV energy systems.
Sci Rep
January 2025
Department of Electrical Engineering, College of Engineering, Taif University, Taif, 21944, Saudi Arabia.
This paper presents a novel approach to modeling and controlling a solar photovoltaic conversion system(SPCS) that operates under real-time weather conditions. The primary contribution is the introduction of an uncertain model, which has not been published before, simulating the SPCS's actual functioning. The proposed robust control strategy involves two stages: first, modifying the standard Perturb and Observe (P&O) algorithm to generate an optimal reference voltage using real-time measurements of temperature, solar irradiance, and wind speed.
View Article and Find Full Text PDFEvent-triggered adaptive compensation control for stochastic nonlinear systems with multiple failures: An improved switching threshold strategy.
ISA Trans
January 2025
School of Mathematics and Physics, Qingdao University of Science and Technology, Qingdao 266061, China; Qingdao Innovation Center of Artificial Intelligence Ocean Technology, Qingdao 266061, China; The Research Institute for Mathematics and Interdisciplinary Sciences, Qingdao University of Science and Technology, Qingdao 266061, China. Electronic address:
This paper considers the event-triggered adaptive fault-tolerant control (FTC) problem for a class of stochastic nonlinear systems suffering from finite number of actuator failures and abrupt system external failure. Unlike existing event-triggered mechanisms (ETMs), this paper proposes an improved switching threshold mechanism (STM) that effectively addresses the potential system security hazards caused by large signal impulses when both the magnitude size of the controller and its rate of change are too large, while also saving energy consumption. Especially, when the occurrence of both actuator failure and system external failure may lead to over-change rate of the controller, by using the multi-dimensional Taylor network (MTN) approximation technique, the adaptive fault-tolerant control scheme designed based on the improved STM not only has lower resource consumption, but also indirectly improves the control performance of the system by ensuring the system security operation.
View Article and Find Full Text PDFHyperplex PCR enables highly multiplexed analysis of point mutations in wastewater: Long-term SARS-CoV-2 variant surveillance in Sweden as a case study.
Water Res
January 2025
Department of Aquatic Sciences and Assessment, Swedish University of Agricultural Sciences, Box 7050, 75007, Uppsala, Sweden. Electronic address:
Wastewater-based surveillance (WBS) allows the analysis of pathogens, chemicals or other biomarkers in wastewater to derive unbiased epidemiological information at population scale. After re-gaining attention during the SARS-CoV-2 pandemic, the field holds promise as a surveillance and early warning system by tracking emerging pathogens with pandemic potential. Expanding the current toolbox of analytical techniques for wastewater analysis, we explored the use of Hyperplex PCR (hpPCR) to analyse SARS-CoV-2 mutations in wastewater samples collected weekly in up to 22 sites across Sweden between October 2022 and December 2023.
View Article and Find Full Text PDFTracking nonlinear conversion of light in van der Waals waveguides.
Nat Nanotechnol
January 2025
Center for Quantum Physics, Key Laboratory of Advanced Optoelectronic Quantum Architecture and Measurement (MOE), School of Physics, Beijing Institute of Technology, Beijing, China.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!