HydroLens: Pioneering Underwater Surveillance with IoT-powered Object Detection and Tracking using the Hybrid ResNeXt DenseNet Model DOI

Sujilatha Tada,

Jeevanantham Vellaichamy

Journal of Machine and Computing, Год журнала: 2025, Номер unknown, С. 281 - 306

Опубликована: Янв. 3, 2025

Efficient object detection and tracking approaches are gaining popularity being actively used in the world of underwater surveillance. This study presents an innovative protocol that combines a Hybrid ResNeXt-DenseNet Model to boost visual perceptivity Internet Things (IoT)-based The model focuses on what is best ResNeXt DenseNet, yielding higher accuracy at lower computational cost than either. Its components are: IoT-enabled sensors for data capture, robust preprocessing pipeline designed imagery, tracking. architecture proposed order overcome issues related environments, such as low visibility, changeable illumination conditions, complex background. Python was implement experiments have been conducted popular benchmarks datasets, approach obtains recognition 98%. In this model, has notable ability accurately identify track objects interest real-time situations. Furthermore, inclusion IoT features ensures flows without interruption, allowing prompt response action. research leads towards better situational awareness marine environment protection systems by proliferating exploiting sophisticated deep learning methods root level.

Язык: Английский

UAVs for forestry: Metric-semantic mapping and diameter estimation with autonomous aerial robots DOI
Ankit Prabhu, Xu Liu, Igor Spasojevic

и другие.

Mechanical Systems and Signal Processing, Год журнала: 2024, Номер 208, С. 111050 - 111050

Опубликована: Янв. 3, 2024

Язык: Английский

Процитировано

8

Permeability-Adjustable Nanocrystalline Flake Ribbon in Customized High-Frequency Magnetic Components DOI
Zhichao Luo, Xinru Li, Chaoqiang Jiang

и другие.

IEEE Transactions on Power Electronics, Год журнала: 2023, Номер 39(3), С. 3477 - 3485

Опубликована: Дек. 18, 2023

Fe-based nanocrystalline ribbon is an alternative to the ferrite for high-frequency magnetic cores due its low hysteresis loss and high saturation. The drawback of conductivity. Crushing homogenous restructure a flake (NFR) can reduce conductivity while maintaining other superior properties noncrushed ribbon. So far, several previous works have proven that NFR replace in dual active bridge wireless power transfer system. However, seldom these mention detailed mechanism NFR. In this article, structure manufacturing process are introduced. effect relative permeability crushing pattern on has been quantitatively reported. A dual-permeability core formed by two types demonstrated inductor. Comparison made inductors using (N27, N87, DMR44) similar size. Experiment results show lower higher saturation than counterparts at frequencies from 100 300 kHz.

Язык: Английский

Процитировано

19

Coordinated control of path tracking and yaw stability for distributed drive electric vehicle based on AMPC and DYC DOI
Dongmei Wu, Yuying Guan, Xin Xia

и другие.

Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering, Год журнала: 2024, Номер unknown

Опубликована: Янв. 26, 2024

Maintaining both path-tracking accuracy and yaw stability of distributed drive electric vehicles (DDEVs) under various driving conditions presents a significant challenge in the field vehicle control. To address this limitation, coordinated control strategy that integrates adaptive model predictive (AMPC) direct moment (DYC) is proposed for DDEVs. The strategy, inspired by hierarchical framework, upper layer lower Based on linear time-varying (LTV MPC) algorithm, effects prediction horizon weight coefficients are compared analyzed first. According to aforementioned analysis, an AMPC controller with variable designed considering change speed layer. involves DYC based quadratic regulator (LQR) technique. Specifically, intervention rule determined threshold rate error phase diagram sideslip angle. Extensive simulation experiments conducted evaluate different conditions. results show that, low adhesion conditions, have been improved 21.58% 14.43%, respectively, AMPC. Similarly, high 44.30% 14.25%, coordination LTV MPC DYC. indicate effective across speeds. Furthermore, successfully enhances while maintaining good even extreme

Язык: Английский

Процитировано

7

Risk-aware lane-change trajectory planning with rollover prevention for autonomous light trucks on curved roads DOI
Hefeng Zhan, Gang Wang, Xin Shan

и другие.

Mechanical Systems and Signal Processing, Год журнала: 2024, Номер 211, С. 111126 - 111126

Опубликована: Фев. 6, 2024

Язык: Английский

Процитировано

7

GNSS/IMU/LiDAR fusion for vehicle localization in urban driving environments within a consensus framework DOI
Letian Gao, Xin Xia, Zhaoliang Zheng

и другие.

Mechanical Systems and Signal Processing, Год журнала: 2023, Номер 205, С. 110862 - 110862

Опубликована: Окт. 25, 2023

Язык: Английский

Процитировано

16

A Secured Vehicle Brain: DAO-Based Collaborative Perception and Decision-Making Systems for Intelligent Vehicles in CPSS DOI
Lili Fan, Changxian Zeng, Zonglin Meng

и другие.

IEEE Transactions on Intelligent Vehicles, Год журнала: 2023, Номер 9(1), С. 52 - 54

Опубликована: Дек. 12, 2023

This letter discusses the security considerations of cross-space collaborative perception based on Decentralized Autonomous Organizations (DAOs). It explores inter-space in three spaces, namely vehicles' configuration space, social society and cyberspace. A DAO-based system also enables data generation interaction among these spaces. The addresses privacy protection challenges cross-regional cooperation caused by privatization centralization protocols process. analyzes causes issues a system. By combining DAOs with system, safety, efficiency, sustainability intelligent vehicles can be improved, which is significant importance for autonomous management capability transportation systems.

Язык: Английский

Процитировано

15

FedBEVT: Federated Learning Bird's Eye View Perception Transformer in Road Traffic Systems DOI Creative Commons
Rui Song, Runsheng Xu, Andreas Festag

и другие.

IEEE Transactions on Intelligent Vehicles, Год журнала: 2023, Номер 9(1), С. 958 - 969

Опубликована: Авг. 31, 2023

Bird's eye view (BEV) perception is becoming increasingly important in the field of autonomous driving. It uses multi-view camera data to learn a transformer model that directly projects road environment onto BEV perspective. However, training often requires large amount data, and as for traffic are private, they typically not shared. Federated learning offers solution enables clients collaborate train models without exchanging but parameters. In this paper, we introduce FedBEVT, federated approach perception. order address two common heterogeneity issues FedBEVT: (i) diverse sensor poses, (ii) varying numbers systems, propose approaches - Learning with Camera-Attentive Personalization (FedCaP) Adaptive Multi-Camera Masking (AMCM), respectively. To evaluate our method real-world settings, create dataset consisting four typical use cases. Our findings suggest FedBEVT outperforms baseline all cases, demonstrating potential improving

Язык: Английский

Процитировано

14

Multi-objective dynamic coordinated Adaptive Cruise Control for intelligent electric vehicle with sensors fusion DOI
Dongmei Wu,

Baobao Qiao,

Changqing Du

и другие.

Mechanical Systems and Signal Processing, Год журнала: 2024, Номер 209, С. 111125 - 111125

Опубликована: Янв. 18, 2024

Язык: Английский

Процитировано

5

ViT-DD: Multi-Task Vision Transformer for Semi-Supervised Driver Distraction Detection DOI
Yunsheng Ma,

Ziran Wang

2022 IEEE Intelligent Vehicles Symposium (IV), Год журнала: 2024, Номер unknown, С. 417 - 423

Опубликована: Июнь 2, 2024

Язык: Английский

Процитировано

5

Assessment of the Effect of Different Loading Combinations Due to Truck Platooning and Autonomous Vehicles on the Performance of Asphalt Pavement DOI Open Access

Ghina H. Merhebi,

Rouba Joumblat, Adel Elkordi

и другие.

Sustainability, Год журнала: 2023, Номер 15(14), С. 10805 - 10805

Опубликована: Июль 10, 2023

Autonomous vehicles and truck platooning have become the future in transportation field. This new strategy has many benefits because it lowers fuel consumption CO2 emissions, improves safety, optimizes transport by using roads more effectively, reduces traffic congestion. In this research, effect of controlled positioning autonomous non-autonomous loadings on long-term performance pavement was estimated different variables such as climate, uniform wandering values distance between trucks, percentage trucks MEPDG/AASHTOWare Pavement ME Design software. achieved first computing strain stress loading combinations, resulting computation failures infrastructure thickness needed to support each combination. The second part research consisted designing a platoon that developed for series connected lateral position spacing them could be explicitly optimized minimize flexible damage. findings revealed small can beneficial life following well-studied skeleton open whole world design. revolutionary changing around improve infrastructure.

Язык: Английский

Процитировано

12