检索结果-内蒙古大学图书馆

Research on feature point matching algorithm improvement using depth prediction

JOURNAL OF ENGINEERING-JOE 2019年第23期2019卷 8905-8909页

作者： Chen, Yongbin Wang, Guitang Wu, Liming Guangdong Univ Technol Guangzhou 510006 Peoples R China

Feature point matching plays an important role in feature-based image registration such as the scale-invariant feature transform algorithm. Feature-based image registration is widely used in visual simultaneous localisation and mapping, augmented reality, self-driving etc. The most meaningful study on feature matching is to improve the accuracy and efficiency and this study pays attention to improving the accuracy by removing the mismatching feature points. Since most of the existed feature-based image registration algorithms are not so strong and efficient enough in mismatch removing, in this study, the authors propose a novel mismatch removal algorithm by incorporating depth prediction into feature matching to improve the performance. In this approach, the depth maps are predicted in pixel-wise through the given red-green-blue images using a deep learning algorithm. Experimental results show that their method outperforms conventional ones in mismatch removing.

关键词： learning (artificial intelligence) image matching feature extraction transforms image registration image colour analysis red-green-blue images feature-based image registration algorithms visual simultaneous localisation feature point matching algorithm improvement deep learning algorithm depth prediction novel mismatch removal algorithm mismatch removing mismatching feature points feature matching

来源：评论

学校读者我要写书评

暂无评论

Prediction of Color Change in Heat-Treated Wood Based on Improved Zebra algorithm Optimized Deep Hybrid Kernel Extreme Learning Machine Model (IZOA-DHKELM)

引用

FORESTS 2025年第2期16卷

作者： Liang, Jingjie Wang, Wei Qu, Zening Cao, Ying Gong, Jingxiang Northeast Forestry Univ Coll Mech & Elect Engn Harbin 150040 Peoples R China

In this study, an Improved Zebra Optimization algorithm (ZOA) is proposed based on the search mechanism of the Sparrow Optimization algorithm (SSA), the perturbation mechanism of the Particle Swarm algorithm (PSO), and the adaptive function. Then, Improved Zebra Optimization algorithm (IZOA) was used to optimize the Deep Hybrid Kernel Extreme Learning Machine Model (DHKELM), and the IZOA-DHKELM was obtained. The model has been used to predict the color of heat-treated wood for different species, temperatures, times, media, and profile types. In this article, the original DHKELM and the ZOA-DHKELM were compared to verify the validity and accuracy of the model. The results indicated that the IZOA-DHKELM decreased the mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) by 56.2%, 67.4%, and 34.2%, respectively, while enhancing the coefficient of determination, R2, to 0.9952 compared to the ZOA-DHKELM. This demonstrated that the model was significantly optimized, with improved generalization ability and prediction accuracy. It can better meet the actual engineering needs.

关键词： heat-treated wood performance prediction algorithm improvement DHKELM wood color

来源：评论

学校读者我要写书评

暂无评论

Research on Two Refined algorithms for Creep Calculation for Reinforced Concrete Components

引用

BUILDINGS 2025年第3期15卷

作者： Wu, Pengfei Cui, Jianchao Dalian Univ Technol State Key Lab Coastal & Offshore Engn Dalian 116024 Peoples R China Shenyang City Univ Sch Intelligence & Engn Shenyang 110112 Peoples R China

Existing refined creep calculation methods primarily include the numerical recursive method. Previous algorithms merely provided a theoretical possibility for refined creep calculations. Their massive computational load, complex derivation processes, and limited applicability conditions made it difficult to apply them practically in engineering. Therefore, this study improves upon existing refined creep algorithms by proposing two new calculation methods: the trapezoidal method and the difference method. The study shows that when calculating creep under different conditions, the proposed methods only require adjustments to certain elements in the calculation model, without the need to re-derive the creep calculation formula;this thus provides a convenient solution for creep calculation under varying operating conditions. Compared to the traditional numerical recursive method, the proposed methods significantly reduce computational effort;compared to the midpoint integration method, the proposed methods offer broader applicability. Under different calculation conditions, both methods exhibit high computational accuracy.

关键词： creep refinement method algorithm improvement trapezoid method difference method T-shaped beam

来源：评论

学校读者我要写书评

暂无评论

A novel approach to analyzing the mechanical response of component failure in cable truss structures using an improved LSTM neural network

引用

ENGINEERING FAILURE ANALYSIS 2025年 174卷

作者： Liu, Zhansheng Shi, Guoliang Liu, Yue Beijing Univ Technol Key Lab Urban Secur & Disaster Engn Minist Educ 100 Pingleyuan Beijing 100124 Peoples R China Univ Sci & Technol Beijing Res Inst Urbanizat & Urban Safety Sch Future Cities Beijing 100083 Peoples R China

In the large cable structure, the cable as the main force component bears a large load. How to accurately analyze the influence of cable rupture on the structure and give reasonable maintenance measures has become the key to health monitoring of large cable structures. In this study, a cable truss structure (CTS) is taken as the research object, the model experiment is established, and the numerical analysis method of component failure mechanics is proposed. Firstly, the component failure and mechanical response acquisition mechanism are designed according to the CTS experimental model. The measured parameters are used as indicators to evaluate the simulation accuracy. In order to improve the accuracy of finite element simulation, a transient dynamic analysis method is proposed. Based on the simulation model and calculation method, the mechanical response analysis and parameter analysis of typical failure conditions are carried out. The most unfavorable failure mode is obtained, and the best maintenance measures for component failure are given. Considering the time correlation of component failure, a mechanical response prediction method based on convolutional neural network (CNN)- Bi long short-term memory (BiLSTM) optimized by improved particle swarm optimization (IPSO) is proposed. Combined with finite element simulation data samples and prediction methods, the mapping relationship between component failure and mechanical response is established. Finally, the continuous dynamic analysis of component failure is realized, and the most unfavorable failure path is obtained. The research results show that the accuracy of the established simulation model and calculation method is more than 95%. The improved deep learning prediction model significantly improves the prediction accuracy and efficiency, and the analysis error and time cost are reduced by 7.5% and 23.7%, respectively.

关键词： Cable truss structure Component failure Cable rupture analysis Mechanical response algorithm improvement

来源：评论

学校读者我要写书评

暂无评论

Research on the predictability of rock strength under freeze-thaw cycles - A hybrid model of SHAP-IPOA-XGBoost

引用

COLD REGIONS SCIENCE AND TECHNOLOGY 2025年 231卷

作者： Liu, Yuhang Xu, Xiangtian Wang, Jiwei Wang, Yongtao Fan, Caixia Inner Mongolia Univ Inst Transportat Hohhot 010070 Peoples R China

As environmental dynamics increasingly influence the stability of engineering materials, accurately predicting sandstone strength under freeze-thaw cycles has become essential. This study presents a new method, IPOAXGBoost, integrating an improved Pelican Optimization algorithm (IPOA) with Extreme Gradient Boosting (XGBoost) to accurately forecast sandstone strength in freeze-thaw environments. Principal component analysis (PCA) is employed for reducing data dimensionality, while IPOA optimizes the hyperparameters of the XGBoost model. Experimental findings show that the IPOA-XGBoost model outperforms traditional methods, delivering improved accuracy and robustness in both training and testing datasets. To address the "black box" challenge of machine learning models, SHAP (SHapley Additive exPlanations) values are applied to clarify the impact of individual features on prediction outcomes, validating SHAP's reliability as an interpretive tool. The findings highlight the importance of strain rate (SR), impact pressure (IP), and confining pressure (CP) as key variables affecting sandstone strength predictions. This methodology provides significant insights for predicting sandstone strength in applied engineering contexts.

关键词： Freeze-thaw cycles Sandstone strength IPOA-XGBoost Interpretability algorithm improvement

来源：评论

学校读者我要写书评

暂无评论

Research on Detection and Counting Method of Green Walnut Based on YOLOv8n-RBP

引用

IEEE ACCESS 2025年 13卷 39275-39288页

作者： Chen, Bangbang Tan, Keke Li, Kun Ma, Baojian Liu, Xiangdong Xinjiang Inst Technol Sch Mechatron Engn Aksu 843100 Peoples R China Xian Technol Univ Sch Mechatron Engn Xian 710021 Peoples R China

In natural environments, green walnuts often experience occlusion by branches and leaves, fruit overlap, and varying lighting conditions. To address the issues of low detection accuracy, missed detections, and false positives in the YOLO model, this study proposes an improved YOLOv8n-based detection and counting model for green walnuts, named YOLOv8n-RBP. First, a receptive field-concentrated attention module (RFCBAM) is integrated into the backbone network to enhance feature extraction capabilities. Second, a BiFPN-GLSA module is introduced to replace the Path Aggregation Network (PANet) in the neck, improving the fusion of feature layers from the backbone and Neck networks and enhancing the model's ability to capture both global and local spatial features. Lastly, to address the weak generalization and slow convergence issues of the CIoU loss function in detection tasks, the PIoUv2 loss function is employed to accelerate bounding box regression and improve detection performance. Experimental results demonstrate that the YOLOv8n-RBP model excels across multiple evaluation metrics. Specifically, the model achieves a mean average precision (mAP@0.5) of 82.2% and a recall rate of 72.4%, with a model size of only 4.65 MB, 2.2 million parameters, and 8.3 GFLOPs. Compared to the original YOLOv8n model, the recall rate and mAP@0.5 improve by 2.7% and 2.5%, respectively, while the number of parameters, FLOPs, and model size decrease by 26.7%, 0.6%, and 22.0%, respectively. Further deployment on the NVIDIA Jetson Xavier NX demonstrates the model's robust performance under natural conditions, indicating its suitability for orchard operations.

关键词： Feature extraction Accuracy Green products YOLO Training Real-time systems Neck Computational modeling Data models Data augmentation Natural environment green walnut detection algorithm improvement equipment deployment

来源：评论

学校读者我要写书评

暂无评论

Research on Improved Bridge Surface Disease Detection algorithm Based on YOLOv7-Tiny-DBB

引用

APPLIED SCIENCES-BASEL 2025年第7期15卷

作者： An, Haichao Fan, Ying Jiao, Zhuobin Liu, Meiqin Taiyuan Univ Sci & Technol Sch Vehicle & Transportat Engn Taiyuan 030024 Peoples R China

In response to the diverse target types, variable morphological characteristics, and the prevalence of small sample targets that are prone to missed detections in the bridge surface disease identification, this paper proposes an improved algorithm for detecting bridge surface diseases based on YOLOv7-Tiny-DBB. By introducing the DBB module to replace the ELAN-Tiny module in the backbone network, the capability of multi-scale feature extraction during the training phase is enhanced, the number of parameters during inference is reduced, and the inference speed has been accelerated. Additionally, by substituting the CIoU loss function with a boundary box regression loss function based on MPDIoU, the regression prediction capabilities are strengthened and both regression accuracy and speed are improved. Effective training and testing are conducted using a self-constructed augmented dataset. The results indicate that, compared to the YOLOv7-Tiny algorithm, the improved algorithm achieves an increase of 4.2% in precision, 6.5% in recall, 5.4% in F1 score, and 7.3% in mean Average Precision (mAP). Additionally, the detection speed improves by 13.1 FPS, successfully addressing the issue of missed detections for minor diseases. The ablation experiments, along with the performance comparison of different network models and visual effect assessments further corroborate the effectiveness of the proposed improvements, providing critical technical support for the deployment of real-time detection systems for bridge surface diseases on industrial edge devices.

关键词： bridge surface diseases algorithm improvement YOLOv7-Tiny-DBB DBB MPDIoU

来源：评论

学校读者我要写书评

暂无评论

Multi-Type Ship Target Detection in Complex Marine Background Based on YOLOv11

引用

PROCESSES 2025年第1期13卷

作者： Wang, Yao Zeng, Weigui Xu, Huiqi Jiang, Yi Liu, Minggang Xiao, Chuanliang Zhao, Ke Naval Aviat Univ Yantai 264001 Peoples R China Shandong Univ Technol Elect & Elect Engn Acad Zibo 255000 Peoples R China

Realizing accurate control of ship target information in complex marine environments is of great significance for maintaining marine environment security and safeguarding maritime sovereignty. With the rapid development of material technology and manufacturing industry, the types and styles of ships are increasing, and the distribution of multi-type ships on the sea is widespread. How to realize the accurate detection and identification of dynamic multi-type ship targets in the complex marine environment is an important and difficult problem that needs to be solved urgently in current marine environment detection. In this paper, an improved YOLOv11 ship target detection algorithm is proposed, which firstly utilizes the improved EfficientNetv2 network to replace the original backbone network of YOLOv11 to improve the learning ability of ship features under complex sea conditions;in order to solve the problem of interference by moving objects at sea when detecting dense ship targets and reduce the problems of missing detection and false alarms, the algorithm borrows from ConvNext block idea in the process of a neck feature pyramid network fusion;the algorithm introduces the WIoU loss function, which compensates for the effect of the small number of pixels of the small target in the process of regression loss computation, so as to improve the network's performance in detecting small targets. In order to test the network performance in actual application scenarios, the article builds a visible ship target dataset, including complex background, occlusion and overlap, small targets, and other factors. Through experimental verification, the detection accuracy of the improved algorithm is improved by 5.6% compared with the original algorithm, and compared with typical algorithms in terms of detection accuracy, speed, and number of parameters, ablation experiments are designed to comprehensively validate and analyze the algorithm's performance.

关键词： YOLOv11 multi-type ship target detection complex environment algorithm improvement

来源：评论

学校读者我要写书评

暂无评论

An improvement of the fast uncovering community algorithm

引用

Chinese Physics B 2013年第10期22卷 646-653页

作者：王莉王将沈华伟程学旗 College of Computer Science and Technology Taiyuan University of Technology Institute of Computing Technology Chinese Academy of Sciences

Community detection methods have been used in computer, sociology, physics, biology, and brain information science areas. Many methods are based on the optimization of modularity. The algorithm proposed by Blondel et al. （Blondel V D, Guillaume J L, Lambiotte R and Lefebvre E 2008 J. Star. Mech. 10 10008） is one of the most widely used methods because of its good performance, especially in the big data era. In this paper we make some improvements to this algorithm in correctness and performance. By tests we see that different node orders bring different performances and different community structures. We find some node swings in different communities that influence the performance. So we design some strategies on the sweeping order of node to reduce the computing cost made by repetition swing. We introduce a new concept of overlapping degree （OV） that shows the strength of connection between nodes. Three improvement strategies are proposed that are based on constant OV, adaptive OV, and adaptive weighted OV, respectively. Experiments on synthetic datasets and real datasets are made, showing that our improved strategies can improve the performance and correctness.

关键词： community division algorithm improvement performance

来源：评论

学校读者我要写书评

暂无评论

improvement on Navigation Behavior algorithm of Agent in Visual Simulation

Improvement on Navigation Behavior Algorithm of Agent in Vis...

引用

International Conference on Micro Nano Devices, Structure and Computing Systems

作者： Zhang Yong Li Cun-hua Yan Bing-yong Huaihai Inst Technol Sch Comp Engn Lianyungang Peoples R China China Univ Min & Technol Sch Management Xuzhou Peoples R China Hong Kong Appl Sci & Technol Res Inst Co Ltd IC Design Grp Hong Kong Peoples R China

ISBN: (纸本)9783037850091

In the visual simulation system, especially large visual game or military simulation training systems, the navigation behavior of agent controls movement of agent through a series of actions response to external environment. The combination of multiple navigation behaviors can create complex behaviors of agent. In the current commonly used behavior determination methods, the combination of different behaviors may cause unreasonable result in some circumstance. Based on navigation behavior, the paper brought out an improved algorithm for navigation behavior of agents, which used heuristic method to balance the local and global behavior priority level, so that the selection of navigation behavior is more reasonable.

关键词： visual simulation agent navigation behavior algorithm improvement

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：