A5100639360- Robotic Path Planning Algorithms
- Advanced Image Processing Techniques
- Advanced Image Fusion Techniques
- Energy Efficient Wireless Sensor Networks
- Remote Sensing and Land Use
- Image Enhancement Techniques
- Photoacoustic and Ultrasonic Imaging
- Robotics and Sensor-Based Localization
- Image Retrieval and Classification Techniques
- Control and Dynamics of Mobile Robots
- Autoimmune and Inflammatory Disorders Research
- 3D Surveying and Cultural Heritage
- UAV Applications and Optimization
- Industrial Vision Systems and Defect Detection
- Advanced Image and Video Retrieval Techniques
- Guidance and Control Systems
- Real-Time Systems Scheduling
- Remote Sensing and LiDAR Applications
- Simulation Techniques and Applications
- Advanced Database Systems and Queries
- Scheduling and Optimization Algorithms
- IoT-based Smart Home Systems
- China's Ethnic Minorities and Relations
- Visual Attention and Saliency Detection
- Scientific Computing and Data Management
Dalian University of Technology
2024
Dalian Naval Academy
2023-2024
Zhejiang Police College
2024
Naval University of Engineering
2024
Northwestern Polytechnical University
2024
Xuzhou Medical College
2023
Xidian University
2022
Air Force Engineering University
2022
Northeastern University
2021
Northeastern University
2020-2021
Super-resolution neural networks have recently achieved great progress in restoring high-quality remote sensing images at low zoom-in magnitude. However, these often struggle with challenges like shape distortion and blurring effects due to the severe absence of structure texture details large-factor image super-resolution. Addressing challenges, we propose a novel Two-Stage Spatial-Frequency Joint Learning Network (TSFNet). TSFNet innovatively merges insights from both spatial frequency...
In this paper, a multilevel humanlike motion planning approach is proposed for indoor mobile robots. Compared with existing approaches, the novelty of paper twofold: 1) path framework and to ensure both foreseeability flexibility, wherein functions human brain, eyes, legs are corresponding global planning, sensor-level action-level respectively, 2) along planned path, new velocity-adjustable trajectory algorithm put forward which provably complete time optimal considering multiple...
The computing resources are supplied by cloud on basis of user requirements demand.Using virtualization and distributed computing, the resource allocation model is constructed to highlight services scalability.Nevertheless, a complex problem created user, manage demand in on-demand model.Hence, novel optimization approach developed called Grey Wolf Optimization Crow Search Algorithm (GWO-CSA) resolve model.On availability resources, tasks executed with aid concept, minimize response time.In...
Current low-light image enhancement techniques prioritize increasing luminance but fail to address issues including loss of intricate distortion colors and details. In order these that has been overlooked by all parties, this paper suggests a multi-module optimization network for enhancing images integrating deep learning with Retinex theory. First, we create decomposition separate the lighting components reflections from image. We incorporated an enhanced global spatial attention (GSA)...
Researchers working on image processing have had a hard time handling low-light images due to their low contrast, noise, and brightness. This paper presents an improved method that uses the Retinex theory enhance images, with network model mainly composed of Decom-Net Enhance-Net. Residual connectivity is fully utilized in both Enhance-Net reduce possible loss details. Additionally, introduces positional pixel attention mechanism directly incorporates global information image. Specifically,...
Formation obstacle avoidance is a critical aspect of cooperation among unmanned surface vehicles (USVs). In practical scenarios involving multiple USVs, managing during formation assembly and navigation essential to ensure the success cooperative tasks. This study devised obstacle-avoidance scheme utilizing dynamical systems (DS). The traditional interfered fluid system (IFDS) applied in two-dimensional planes was enhanced address local minima issues. Furthermore, robust virtual structure...
This paper proposes an improved artificial potential field method on route planing for UAV swarm to evade radar detection during flight and finally reach the target point. We solve problem of excessive gravitational force is solved by modifying function a segmental compared shortcomings traditional method. And unreachability concentrating relative distance between target. Finally, we local minima adjusting step size direction. The feasibility our in obstacle avoidance verified Matlab...
Abstract Objective The differential diagnosis between adult-onset Still’s disease (AOSD) and sepsis has always been a challenge. In this study, machine learning model for of AOSD was developed an online platform to facilitate the clinical application model. Methods All data were collected from 42 patients 50 admitted Affiliated Hospital Xuzhou Medical University December 2018 2021. addition, 5 10 diagnosed in our hospital after March 2022 external validation. models built using scikit-learn...
Texture feature description is a remarkable challenge in the fields of computer vision and pattern recognition. Since traditional texture method, local binary (LBP), unable to acquire more detailed direction information always sensitive noise, we propose novel method based on generalized Gabor (GGDP) weighted discrepancy measurement model (WDMM) overcome those defects. Firstly, patch-structure (PDP) proposed, which can extract rich be insensitive noise. Then, motivated by searching for that...
WSN plays an excellent role in offering a dynamic selection of CH.Nevertheless, the CH chosen is most important confronts because flawed CHselection which may cause unbalanced energy utilization.In this work, challenge addressed by developing hybrid optimization method for CH.The developed consists 3 phases that comprise setup, transmission, and measurement phase.Initially, energy, node's mobility, are initialized network.The setup phase processed selecting Cluster Head exploiting Optimized...
The three-dimensional (3D) models of buildings and plants from UAV images become increasingly popular for city construction. However, whether the previous 3D modeling precision large-scale can be further enhanced that is acceptable still remain to investigated. For these ends, this research studied a basketball hall row Euonymus japonicas based on DJI Inspire-1 system. data were processed with Pix4D calculate camera parameters, which then ContextCapture Photoscan generate models. displayed...
In this paper, in order to get a better understanding of the human visual preferences for AIGIs, large-scale IQA database AIGC is established, which named as AIGCIQA2023. We first generate over 2000 images based on 6 state-of-the-art text-to-image generation models using 100 prompts. Based these images, well-organized subjective experiment conducted assess each image from three perspectives including quality, authenticity and correspondence. Finally, database, we conduct benchmark evaluate...
In the WSNs environment, methodological development ensued in process of gathering and forwarding enormous data among nodes that is most important challenges as it related with high energy loss delay.This establishment a routing protocol for optimally chosen multipath to WSNs.Hence, this work presents an energy-effectual utilizing hybrid Wolf Pack approach Particle Swarm Optimization (WP-PSO) selects optimal hops succeeding routing.Initially, CHs are by exploiting LEACH which reduces traffic...
This paper presents a time-optimal motion planning approach for nonholonomic mobile robot working in typical warehouse-like environment, where barcodes are regularly attached on the ground global localization. In such an application, state lattice is inherently embedded barcode map with extra orientation dimension, and search based path scheme adapted. Different from existing approaches, new group of curvature continuous primitives corresponding primitive selection criterion introduced. The...