检索结果-内蒙古大学图书馆

第30届中国控制与决策会议

作者： Cui Shi-gang Li Heng Wu Xing-li Zhang Yong-li He Lin Tianjin University of Technology and Education Tianjin Key Laboratory of Information Sensing & Intelligent Control

The segmentation of lettuce is the key monitoring link in plant factory. First through the image information collector to collect a lettuce image, we analyzed the image of the morphological gradient image. Then the image of the lettuce was morphological and morphological, and the foreground image and background image of the image were marked. Finally lettuce and the background of the image based on the watershed algorithm for precise segmentation. The experimental results shown that the morphological recombination and watershed algorithm can accurately divide the images of the lettuce. This paper applies morphological recombination and watershed algorithm to plant factory, which provided reference basis for image processing in agricultural production and application.

关键词： Image Processing Image Segmentation watershed algorithm Morphological recombination

来源：评论

学校读者我要写书评

暂无评论

Medical image watermarking based on novel encoding for EHR and fusion based morphological watershed segmentation algorithm for medical images

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第9期83卷 25163-25190页

作者： Kavitha, K. J. Shan, Priestly B. GM Inst Technol Davangere Karnataka India Chandigarh Univ Mohali India

Advancement in the field of healthcare system, the identification of the infection with severity impact of a particular disease may be easily done with the help of scanned radiological images and thereby segmentation plays a major role in detection of presence of foreign objects or infected areas in certain parts of a human body and thereby helps in providing a clinical care to the patient with crucial state. So, precise segmentation is a key-step in the analysis of a disease at the time of radio therapy. Although many traditional segmentation techniques are available to separate region of interest from that of region of non-interest;no complete segmentation algorithm is available which is suitable for all kinds of medical images and moreover, an algorithm suitable for one kind of medical image may not be suitable for other type of medical image as each category of image differs in their characteristics;And hence, in the proposed paper, an improved segmentation algorithm based on dual tree complex wavelet transform (DTCWT) and fusion-morphological watershed algorithm for denoising is proposed for all kinds of scanned medical images and also proposes a medical image watermarking (MIW) based on encoding algorithm with hybrid embedding function for authentication in E-Health care systems. The MIW and segmentation algorithm is applied and evaluated to various modalities of medical images using various quality metrics and statistical parameters. The data integrity of the proposed system is evaluated for constructed MI and EHR and is validated by identifying tampered information in terms of decoding correct and wrong information using secret keys in the proposed system.

关键词： MIW Segmentation DTCWT Morphology watershed algorithm Fusion technique US MRI CT

来源：评论

学校读者我要写书评

暂无评论

Under Water Animals Detecting Robot Based on watershed algorithm

Under Water Animals Detecting Robot Based on Watershed Algor...

引用

2017 the 2nd International Conference on Mechatronics Engineering and Information Technology(ICMEIT 2017)

作者： Le Wang Senwei Wang Yansong Deng School of Southwest Minzu University

ISBN: (纸本)9781510840683

The underwater animals detecting robot collects images by using a camera,and the watershed algorithm can implement image *** robot can discern creature under the The hardware platform of under *** controller controls steering gear to make the robot move freely in the *** CV is an open source computer vision library and Raspberry Pi uses it to image segmentation on the basis of watershed algorithm under Linux *** algorithm is an image segmentation method based on topology theory,and was put forward to solve the problem of excessive *** to the results of the experiment,the practicability of the under water animals detecting robot has been ***,the robot get an expecting result.

关键词： watershed algorithm OpenCV Raspberry Pi The robot

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Applying watershed algorithm in Segmentation of CT Brain Images

Comprehensive Applying Watershed Algorithm in Segmentation o...

引用

2011 6th IEEE Joint International Information Technology and Artificial Intelligence Conference(ITAIC 2011)

作者： ZHU Bing-li Experimental Center Chongqing Three Gorges University,CTGU Wanzhou,Chongqing,China Xiong Jiang College of Mathematics and Computer Science Chongqing Three Gorges University,CTGU Wanzhou,Chongqing,China Tan Xiao-ling College of Physics and Electronic Engineering Chongqing Three Gorges University,CTGU Wanzhou,Chongqing,China

According to the multi-threshold values of CT brain images,applying watershed segmentation algorithm by comprehensive methods which take full advantage of de-noising,gradient reconstruction,watershed segmentation,binary result and so *** the binary skull image that is good at de-noising,detail accepting and over segmentation *** the program designed in MATLAB can process batches of CT brain images effectively,moreover,it can gain prophase data that is useful in anaphase image processing.

关键词： CT brain image image segmentation multi-threshold values watershed algorithm MATLAB

来源：评论

学校读者我要写书评

暂无评论

A Tongue-images Segmentation Method Based on Local Restoration and watershed algorithm

引用

Chinese Journal of Biomedical Engineering(English Edition) 2010年第1期19卷 1-7页

作者： ZHANG Ling QIN Jian Computer Faculty Guangdong University of Technology Guangzhou 510006 China TCM Department the First Affiliated Hospital SUN YA T-SEN University Guangzhou 510080 China

Objective: To propose a method to segment tongue- images efficiently, and extract tongue- body accurately and quickly. Methods: Firstly, a kind of color- images' pre- processing technique was used to solve tongue- surface reflection problem. Neighbouring and similar region's information was used to restore the region with tongue- surface reflection problem by replacement. Secondly, the restored image was transformed into a gray one, and then processed by mathematical morphological operation- dilation to get a closed- loop edge. The third technique used was watershed algorithm, which is an usual tool in image segmentation. 'watershed' function of matlab software was used to complete this algorithm. After that, region- combination technique was used. Through measuring neighbourship and similarity of regions, a non- objective and non- background region was merged into one of its neighbouring regions. This step was repeated until only two regions, objective and background regions, were left in the image. At last, corresponding to the merged image, tongue- body image was got from the original image. Results: 316 images were randomly taken from the image library for experiments, and 299 images were correctly segmented, so, the successful ratio is 94.62%. On the other hand, average time of running this method was about 50 s under whole sampling environment. Conclusion: The method presented in this paper can segment a tongue- body image from its original one effectively, and thus laying a good foundation for the following analysis work.

关键词： local restoration watershed algorithm tongue-body segmentation mathmatical morphology

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Morphology and watershed-algorithm-Based Method for Pitting Corrosion Evaluation

引用

BUILDINGS 2022年第11期12卷 1908页

作者： Li, Anbang Ma, Hongwang Xu, Shanhua Xian Univ Architecture & Technol Sch Civil Engn Xian 710055 Peoples R China State Key Lab Green Bldg Western China Xian 710055 Peoples R China Minist Educ Key Lab Struct Engn & Earthquake Resistance Xian 710055 Peoples R China

Pitting corrosion and stress concentration at rust pits are the principal reasons for severe degradation in fatigue performance of corroded steel structures. The accurate evaluation of rust pits on rough and uneven corrosion surfaces is the foundation of fatigue life estimation for corroded steel structures. In this paper, a new method for the identification, extraction, and evaluation of rust pits on the surface of corroded steel structures was proposed based on a three-dimensional morphology and watershed algorithm. An accelerated corrosion experiment was first executed to acquire corroded steel plates, and then surface profile measurements were conducted to obtain the three-dimensional morphology of the corroded steel surfaces. Furthermore, the surface topography data of the corroded steel surfaces were written into a gray matrix through coordinate transformation. Then, the gray matrix was successively filtered and gradient-mapped, and the watershed was calculated to obtain the pit mark matrix and pit depth matrix. A calculation method for the size and shape of rust pits was consequently developed, and a statistical analysis of the extraction results of the rust pits was also conducted. The results showed that rust pit density had a peak value at the corrosion duration of 3 months, and rust pit density showed a fluctuating process with corrosion duration that continued to increase until 15 months. The values of the depth diameter ratios of rust pits were concentrated in the range of 0.1-0.8. With corrosion duration increasing from 3 months to 4, 6, 8, 12, and 15 months, the distribution range of the depth diameter ratios of rust pits decreased at first and then increased, followed by decrease and, finally, increase. The width distribution of the rust pits was independent of the depth distribution of the rust pits. The values of the volume ratios were mostly distributed between pi/12 and pi/4, and the shapes of most rust pits were similar to half (ellipsoidal) sph

关键词： corrosion steel structure three-dimensional morphology watershed algorithm pitting corrosion rust pit identification

来源：评论

学校读者我要写书评

暂无评论

Applying Deep Learning and Heatmap Techniques for Sinusitis Diagnosis Using Enhanced 3-D Image Segmentation

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Huang, Pin-Siang Horng, Shi-Jinn Yang, Chia-Jung Chen, Hongmei Zhou, Wanlei Natl Taiwan Univ Sci & Technol Dept Comp Sci & Informat Engn Taipei 10607 Taiwan Asia Univ Dept Comp Sci & Informat Engn Taichung 41354 Taiwan China Med Univ China Med Univ Hosp Dept Med Res Taichung Taiwan Univ Technol Sydney Sch Comp Sci Ultimo NSW 2007 Australia Taitung MacKay Mem Hosp Dept Radiol Taitung 950 Taiwan Southwest Jiaotong Univ Sch Comp & Artificial Intelligence Chengdu 610032 Peoples R China City Univ Macau Fac Data Sci Macau Peoples R China

Sinusitis, characterized by inflammation of the sinus cavities, presents diagnostic challenges due to the subjective and time-consuming nature of manual computed tomography (CT) scan annotations. This study introduces a deep learning (DL) method combined with heatmap analysis to automate 3-D segmentation of sinusitis in CT images. The proposed approach reduces the dependency on fully segmented annotations, instead requiring only binary classification labels during training. A classification model identifies areas likely affected by inflammation, highlighted by gradient-weighted class activation mapping (Grad-CAM) to produce heatmaps, which are refined using a watershed algorithm for precise segmentation. This approach reduces annotation preparation time from 30 min to under 1 min while achieving a Dice similarity coefficient (DSC) of 90.04%. Built on the EfficientNet-B2 architecture, the model outperforms state-of-the-art methods like U-Net, U-Net++, and statistical-based approaches. Additionally, a novel instrumentation system integrated with CT scanners calculates inflammation areas in real time, streamlining diagnostic workflows. This method accelerates the process while improving the consistency and reliability of sinusitis diagnosis, potentially transforming clinical practices with advanced image processing techniques.

关键词： Image segmentation Computed tomography Deep learning watersheds Three-dimensional displays Accuracy Medical diagnostic imaging Convolutional neural networks Annotations Training 3-D segmentation computed tomography (CT) scan deep learning (DL) diagnostic automation Dice similarity coefficient (DSC) gradient-weighted class activation mapping (GRAD-CAM) image annotation medical image processing sinusitis watershed algorithm

来源：评论

学校读者我要写书评

暂无评论

Factors influencing spatiotemporal cooling potential of blue-green infrastructure across diverse local climate zones-Case study of Wroclaw, Poland

引用

BUILDING AND ENVIRONMENT 2025年 267卷

作者： Budzik, Grzegorz Krajewski, Piotr Soszynska, Agnieszka Lebiedzinska, Monika Kowalczyk, Tomasz Wroclaw Univ Environm & Life Sci Dept Environm Protect & Dev Grunwaldzki Sq 24 PL-50363 Wroclaw Poland Wroclaw Univ Environm & Life Sci Inst Spatial Management Grunwaldzka Str 55 PL-50375 Wroclaw Poland Univ Leicester Natl Ctr Earth Observat Sch Phys & Astron 92 Corp Rd Leicester LE4 5SP England

The development of blue-green infrastructure (BGI) is essential for mitigating urban heat islands;however, it encounters operational challenges that demand effective, locally-adapted strategies. Existing literature does not completely assess the factors influencing the cooling mechanisms of blue, green, and integrated BGI types across various local climate zones (LCZs). This study evaluates the most influential characteristics shaping the cooling potential of BGI according to different LCZs, considering BGI characteristics (type, geometry, spatial density, vegetation features) and basic weather conditions. We focused on all BGI components in Wroclaw, Poland using the PlanetScope time-series from April to October (2020-2023). The thermal characteristics were analyzed using Landsat 8/9 time-series land surface temperatures. The variations in urban morphology were assessed using the World Urban Database and Access Portal Tools LCZ Generator. BGI cooling characteristics such as high-intensity cooling distance and intensity, cooling area, and the cooling efficiency were calculated using a custom Python script based on the ArcPy library and a watershed algorithm. The results indicate significant variations in the impact of the studied characteristics on cooling effectiveness, depending on the LCZ and BGI types. The most pronounced cooling was observed in highly urbanized LCZs. Larger and more densely vegetated BGI objects with complex shapes exhibited stronger cooling effects. The presence of water within the BGI significantly enhanced cooling potential. Despite the impact of basic weather conditions, the hierarchy of the influence of BGI characteristics remained consistent. This holistic approach may enhance our understanding of cooling mechanisms in various types of urban development.

关键词： Blue-green infrastructure Urban cool island Local climate zones Remote sensing watershed algorithm

来源：评论

学校读者我要写书评

暂无评论

Investigation of wave spectral climate at key location of the Northern South China sea using a novel modeling framework

引用

OCEAN ENGINEERING 2025年 327卷

作者： Ma, Yuxiang Li, Junzheng Ai, Congfang Zheng, Wentao Sun, Lei Xie, Botao Dalian Univ Technol State Key Lab Coastal & Offshore Engn Dalian 116023 Liaoning Peoples R China China Ship Sci Res Ctr Wuxi 214082 Jiangsu Peoples R China Dalian Univ Technol Sch Naval Architecture & Ocean Engn Dalian 116023 Liaoning Peoples R China CNOOC Res Inst Co Ltd Beijing 100028 Peoples R China

Wave spectral climate explains the complexity of local marine environments. The dynamic variations of dominating wave components hamper wave spectral climate analysis, necessitating a precise modeling of climatic wave spectra. In this study, wave spectral datasets are constructed using WavewatchIII for the key location of the Northern South China Sea (NSCS-K). By the improved watershed algorithm, the datasets were classified into five distinct spectral classes, namely wind systems (ClassI), swell systems (ClassII), wind and swell systems (ClassIII), two swell systems (ClassIV), and complex multipeak systems (ClassV). The transformational patterns of wave systems in NSCS-K are revealed using a Markov chain approach. The main spectral class data are modeled by spectrum models. It is found that ClassI (64.80 %) and ClassIII (20.37 %) are the dominant ones in NSCS-K. In addition to the intra-spectral transformations that exceed 85 % in each class, the transformation from ClassI to ClassIII and ClassII to ClassIV deserves to be noticed, with a proportion of 6.66 % and 9.65 %, respectively. The JONSWAP spectrum model provides the most optimal applicability for ClassI, with gamma typically between 1.8 and 2.2. For ClassIII, the Ochi-Hubble spectrum model achieves an accurate representation with lambda 1 mostly in 2.0-2.5 and lambda 2 mostly in 1.5-2.0.

关键词： Key location of the northern south China sea (NSCS-K) Wave spectral climate watershed algorithm Wave spectrum model

来源：评论

学校读者我要写书评

暂无评论

Identifying localized heat zones in urban heat islands from a hill and saddle perspective

引用

SUSTAINABLE CITIES AND SOCIETY 2025年 118卷

作者： Yu, Wenbo Yang, Jun Ren, Jiayi Zhang, Zhenchao Sun, Dongqi Xue, Bing Sun, Wei Xiao, Xiangming Xia, Jianhong(Cecilia) Li, Xueming Northeastern Univ Sch Humanities & Law Shenyang 110169 Peoples R China Northeastern Univ JangHo Architecture Coll Shenyang 110169 Peoples R China Liaoning Normal Univ Human Settlements Res Ctr Dalian 116029 Peoples R China Dalian Maritime Univ Coll Transportat Engn Dalian 116029 Peoples R China Chinese Acad Sci Inst Geog Sci & Nat Resources Res Key Lab Reg Sustainable Dev Modeling Beijing Peoples R China Chinese Acad Sci Inst Appl Ecol Shenyang 110016 Peoples R China Chinese Acad Sci Nanjing Inst Geog & Limnol Nanjing 210008 Peoples R China Univ Oklahoma Ctr Earth Observat & Modeling Dept Microbiol & Plant Biol Norman OK 73019 USA Curtin Univ Sch Earth & Planetary Sci EPS Perth Australia

Urban heat islands are highly heterogeneous with localized heat zones (LHZs) forming hill-like patterns representing temperature peaks;however, the generation and segmentation of these LHZs remain unclear. This study focused on Jinan, Shandong Province, China, and used a watershed algorithm to segment the urban heat island into LHZs, with inner parts and segmentation lines considered as "hills" and "saddles," respectively. The influences of urban parameters on the "hill" temperature and "hill-saddle" temperature differences were elucidated. Results showed that (1) temperatures in the LHZ hills were notably higher than those in LHZ saddles;(2) population density (PD) had the highest ability to influence the temperatures in the LHZ hills, exerting a warming effect of similar to 0.7 degrees C for PD > 10,000 persons/km(2);and (3) urban parameters could drive temperature differences in two main ways. PD and building height followed monotonous upward paths, promoting the hill parameters and making them significantly higher than the saddle parameters, thereby increasing the temperature differences, whereas NDVI and building density followed "V" shaped paths, which could be expanded by unilaterally increasing the hill and saddle parameters, thereby increasing the temperature differences.

关键词： Urban heat island watershed algorithm Structural segmentation Driving mechanism Jinan city

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：