检索结果-南通市图书馆

Efficient Image Stitching in the Presence of Dynamic Objects and Structure Misalignment

在线全文

学校读者我要写书评

暂无评论

Journal of Signal and Information Processing 2011年第3期2卷 205-210页

作者： Chao Tao Hanqiu Sun changcai yang Jinwen Tian 不详

This paper presents a new method for simultaneously eliminating visual artifacts caused by moving objects and structure misalignment in image stitching. Given that the input images are roughly aligned, our approach is implemented in two stages. In the first stage, we discover motions between input images, and then extract their corresponding regions through a multi-seed based region growing algorithm. In the second stage, with prior information provided by the extracted regions, we perform a graph cut optimization in gradient-domain to determine which pixels to use from each image to achieve seamless stitching. Our method is simple to implement and effective. The experimental results illustrate that the proposed approach can produce comparable or superior results in comparison with state-of-the-art methods.

关键词： Image Stitching Motion Estimate Region Growing Graph Cut

Classification of Rice Yield Using UAV-Based Hyperspectral Imagery and Lodging Feature

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Plant Phenomics 2021年第1期3卷 115-128页

作者： Jian Wang Bizhi Wu Markus VKohnen Daqi Lin changcai yang Xiaowei Wang Ailing Qiang Wei Liu Jianbin Kang Hua Li Jing Shen Tianhao Yao Jun Su Bangyu Li Lianfeng Gu Institute of Crop Sciences Ningxia Academy of Agriculture and Forestry ScienceYinchuanNingxia 750105China Basic Forestry and Proteomics Research Center College of ForestryFujian Agriculture and Forestry UniversityFuzhou 350002China State Key Laboratory of Marine Environmental Science Xiamen UniversityChina Digital Fujian Institute of Big Data for Agriculture and Forestry Key Laboratory of Smart Agriculture and ForestryFujian Agriculture and Forestry UniversityFuzhou 350002China Seed Workstations of the Ningxia Hui Autonomous Region YinchuanNingxia 750004China Aerospace Information Research Center Institute of AutomationChinese Academic ScienceBeijing 100190China

High-yield rice cultivation is an effective way to address the increasing food demand *** classification of high-yield rice is a key step of ***,manual measurements within breeding programs are time consuming and have high cost and low throughput,which limit the application in large-scale field *** this study,we developed an accurate large-scale approach and presented the potential usage of hyperspectral data for rice yield measurement using the XGBoost algorithm to speed up the rice breeding process for many *** total,13 japonica rice lines in regional trials in northern China were divided into different categories according to the manual measurement of *** an Unmanned Aerial Vehicle(UAV)platform equipped with a hyperspectral camera to capture images over multiple time series,a rice yield classification model based on the XGBoost algorithm was *** comparison experiments were carried out through the intraline test and the interline test considering lodging characteristics at the midmature stage or *** result revealed that the degree of lodging in the midmature stage was an important feature affecting the classification accuracy of ***,we developed a low-cost,high-throughput phenotyping and nondestructive method by combining UAV-based hyperspectral measurements and machine learning for estimation of rice yield to improve rice breeding efficiency.

关键词： breeding equipped consuming

Panicle-Cloud:An Open and Al-Powered Cloud Computing Platform for Quantifying Rice Panicles from Drone-Collected Imagery to Enable the Classification of Yield Production in Rice

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Plant Phenomics 2023年第4期5卷 905-916页

作者： Zixuan Teng Jiawei Chen Jian Wang Shuixiu Wu Riqing Chen Yaohai Lin Liyan Shen Robert Jackson Ji Zhou changcai yang Digital Fujian Research Institute of Big Data for Agriculture and Forestry College of Computer and Information SciencesFujian Agriculture and Forestry UniversityFuzhou 350002China State Key Laboratory of Crop Genetics&Germplasm Enhancement academy for Advanced Interdisciplinary StudiesNanjing Agricultural UniversityNanjing 210095China Ningxia Academy of Agriculture and Forestry Sciences Yinchuan 750002China College of Mechanical and Electrical Engineering Fujian Agriculture and Forestry UniversityFuzhou 350002China Cambridge Crop Research National Institute of Agricultural Botany(NIAB)Cambridge CB3 OLEUK Key Laboratory of Smart Agriculture and Forestry(Fujian Agriculture and Forestry University) Fujian Province UniversityFuzhou 350002China Center for Agroforestry Mega Data Science School of Future TechnologyFujian Agriculture and Forestry UniversityFuzhou 350002China

Rice(Oryza sativa)is an essential stable food for many rice consumption nations in the world and,thus,the importance to improve its yield production under global climate *** evaluate different rice varieties'yield performance,key yield-related traits such as panicle number per unit area(PNpM^(2))are key indicators,which have attracted much attention by many plant research ***,it is still challenging to conduct large-scale screening of rice panicles to quantify the PNpM^(2)trait due to complex field conditions,a large variation of rice cultivars,and their panicle morphological ***,we present Panicle-Cloud,an open and artificial intelligence(AI)-powered cloud computing platform that is capable of quantifying rice panicles from drone-collected *** facilitate the development of Al-powered detection models,we first established an open diverse rice panicle detection dataset that was annotated by a group of rice specialists;then,we integrated several state-of-the-art deep learning models(including a preferred model called Panicle-AI)into the Panicle-Cloud platform,so that nonexpert users could select a pretrained model to detect rice panicles from their own aerial *** trialed the Al models with images collected at different attitudes and growth stages,through which the right timing and preferred image resolutions for phenotyping rice panicles in the field were ***,we applied the platform in a 2-season rice breeding trial to valid its biological relevance and classified yield production using the platform-derived PNpM^(2)trait from hundreds of rice *** correlation analysis between computational analysis and manual scoring,we found that the platform could quantify the PNpM^(2)trait reliably,based on which yield production was classified with high ***,we trust that our work demonstrates a valuable advance in phenotyping the PNpM^(2)trait in rice,which provides a useful toolkit to enable rice br

关键词： breeding cultivar hundreds

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

库岸复杂滑坡体形成机制的数值分析

自然灾害学报 2015年第2期24卷 74-80页

作者：肖拥军邓敏杨昌才湖南科技大学土木工程学院湖南湘潭411201

三峡库区黄土坡滑坡已历经了几十年的勘察,但对其复杂滑体结构的成因机制仍有待研究。论文从分析黄土坡滑坡体I号崩滑体的原岩结构特征及岩体风化泥化过程入手,通过数值模拟研究了斜坡发育过程中滑坡的演化机制。模拟结果表明,斜坡表层... 详细信息

三峡库区黄土坡滑坡已历经了几十年的勘察,但对其复杂滑体结构的成因机制仍有待研究。论文从分析黄土坡滑坡体I号崩滑体的原岩结构特征及岩体风化泥化过程入手,通过数值模拟研究了斜坡发育过程中滑坡的演化机制。模拟结果表明,斜坡表层拉应力的分布及深部夹层剪应力的集中有利于岩体的风化泥化。数值分析结果较好地解析了黄土坡滑坡复杂滑体结构的形成机制,指出前缘断层发育与斜坡岩体深部夹层泥化是其形成演化的关键因数。数值分析也表明三峡水库蓄水对滑坡整体稳定性的影响较大,模拟结果还表明,潜在滑带由深部泥化夹层控制。

关键词：黄土坡滑坡滑体结构演化机制数值模拟

Simultaneous determination of five plant hormones in cotton leaves using QuEChERS combined with HPLC‒MS/MS

在线全文

学校读者我要写书评

暂无评论

Journal of Cotton Research 2024年第2期7卷 163-176页

作者： WANG Wenhao SONG Xianpeng WANG Dan MA Yajie SHAN Yongpan REN Xiangliang HU Hongyan WU changcai yang Jun MA Yan National Key Laboratory of Cotton Biobreeding and Integrated Utilization Institute of Cotton ResearchChinese Academy of Agricultural SciencesAnyangHenan 455000China College of Agriculture Hebei Agricultural UniversityBaodingHebei 071000China Zhengzhou Research Base National Key Laboratory of Cotton Biobreeding and Integrated UtilizationZhengzhou UniversityZhengzhouHenan 450001China Western Agricultural Research Center Chinese Academy of Agricultural SciencesChangjiXinjiang 831100China

Background Plant hormones profoundly influence cotton growth,development,and responses to various ***,there is a pressing need for an efficient assay to quantify these hormones in *** this groundbreaking study,we have established QuEChERS-HPLC‒MS/MS method,for the simultaneous detection of multiple plant hormones in cotton leaves,allowing the analysis and quantification of five key plant *** Sample extraction and purification employed 0.1%acetic acid in methanol and C18 for optimal recovery of plant *** method applied to cotton demonstrated excellent linearity across a concentration range of 0.05–1 mg・L−1,with linear regression coefficients exceeding *** limits of quantification(LOQs)were 20μg・kg−1 for GA3 and 5μg・kg−1 for the other four plant *** rates for the five plant hormones matrix spiked at levels of 5,10,100,and 1000μg・kg−1 were in the range of 79.07%to 98.97%,with intraday relative standard deviations(RSDs)ranging from 2.11%to 8.47%.The method was successfully employed to analyze and quantify the five analytes in cotton leaves treated with plant growth *** The study demonstrates that the method is well-suited for the determination of five plant hormones in *** exhibits excellent selectivity and sensitivity in detecting field samples,thus serving as a robust tool for indepth research into cotton physiology.

关键词： Cotton Plant hormones QuEChERS HPLC‒MS/MS

在线全文

学校读者我要写书评

暂无评论

天基光学成像系统空间目标成像模拟技术

红外与激光工程 2012年第9期41卷 2410-2414页

作者：杨长才田金文叶瑾尚轲田昕华中科技大学图像识别与人工智能研究所多光谱信息处理技术国家级重点实验室湖北武汉430074 华中科技大学武昌分校艺术设计学院湖北武汉430074

提出了一种天基光学成像系统对空间目标和背景成像的模拟方法。首先利用3DMAX软件创建精确的空间目标三维模型;然后根据目标的结构特性建立了目标的光照模型,利用光线跟踪算法计算目标卫星各小面元传递到CCD镜头处的能量值。在此基础上... 详细信息

提出了一种天基光学成像系统对空间目标和背景成像的模拟方法。首先利用3DMAX软件创建精确的空间目标三维模型;然后根据目标的结构特性建立了目标的光照模型,利用光线跟踪算法计算目标卫星各小面元传递到CCD镜头处的能量值。在此基础上,结合空间环境、空间目标运动特性和成像模型构建了空间目标和背景特性仿真演示系统。仿真结果表明:该方法可有效地模拟天基光学成像系统对空间目标和背景成像。

关键词：空间目标三维建模光照模型光学成像仿真天基光学成像系统

在线全文

学校读者我要写书评

暂无评论

自然场景图像中的重叠蜜柚识别及试验

农业工程学报 2021年第24期37卷 158-167页

作者：林耀海吕钟亮杨长才林培杰陈芳育洪嘉伟福建农林大学计算机与信息学院福州350002 福州大学物理与信息工程学院福州350116 福建农林大学农学院福州350002

重叠蜜柚目标的准确分离和蜜柚果梗的定位是实现采摘自动化必须解决的两个关键问题。现有的苹果、柑橘等重叠果实分离方法不适用于重叠蜜柚,且无果梗定位功能。针对以上问题,该研究提出了一种结合渐进式中心定位的重叠蜜柚分离方法和果... 详细信息

重叠蜜柚目标的准确分离和蜜柚果梗的定位是实现采摘自动化必须解决的两个关键问题。现有的苹果、柑橘等重叠果实分离方法不适用于重叠蜜柚,且无果梗定位功能。针对以上问题,该研究提出了一种结合渐进式中心定位的重叠蜜柚分离方法和果梗定位方法。首先利用主成分分析方法提取蜜柚区域、滤除背景并对图像中的重叠蜜柚进行初步分离;接着,对重叠蜜柚区域采用渐进式中心定位方法得到各个蜜柚的中心;然后,利用区域边缘点到其相应的不同中心点的距离大小的变化规律实现重叠蜜柚的分离;最后,利用前述的中心点结合蜜柚的形状特征,定位出遮挡程度较小的蜜柚果梗。在50张自然场景下的图像上进行试验,结果表明在有阴影、小目标、遮挡和重叠等复杂环境下,该方法的平均识别率为94.02%。同时,对于果梗未被遮挡且离摄像头较近的蜜柚,也给出了准确的果梗区域。在利用蜜柚模型搭建的识别自动化试验平台上进行试验,结果表明采摘机器人能够有效识别并分离重叠蜜柚、定位果梗。该研究可为蜜柚采摘机器人准确识别重叠果实提供参考。

关键词：图像处理识别机器视觉重叠蜜柚主成分分析渐进式中心定位分离果梗

在线全文

学校读者我要写书评

暂无评论

基于支持度变换的水平集人脸轮廓提取方法

三峡大学学报（自然科学版） 2008年第5期30卷 64-67页

作者：杨长才郑胜叶瑾三峡大学电气信息学院智能视觉与图像信息研究所湖北宜昌443002 华中科技大学电子与信息工程系武汉430074

提出了一种新的人脸轮廓提取方法,该方法将水平集与支持度相结合.首先将人脸图像进行支持度变换得到支持度图像,在此基础上,用支持度图像计算几何活动轮廓模型的边缘指示函数,在演化过程中先选取参数较小的边缘指示函数,使得边缘指示函... 详细信息

提出了一种新的人脸轮廓提取方法,该方法将水平集与支持度相结合.首先将人脸图像进行支持度变换得到支持度图像,在此基础上,用支持度图像计算几何活动轮廓模型的边缘指示函数,在演化过程中先选取参数较小的边缘指示函数,使得边缘指示函数对眉毛不敏感,演化曲线过眉毛后选取参数较大的边缘指示函数,使得演化正确收敛于人脸轮廓.实验结果表明该方法的人脸轮廓提取效果较好,收敛速度快.

关键词：水平集人脸轮廓提取边缘指示函数支持度变换

基于联合深度网络和形态结构约束的三维医学图像分割方法

在线全文

学校读者我要写书评

暂无评论

中国生物医学工程学报 2023年第1期42卷 30-40页

作者：李军叶欣怡杨长才陈秋凤薛岚燕魏丽芳福建农林大学计算机与信息学院福州350002

医学图像自动分割具有广泛和重要临床应用价值,特别是病灶、脏器的自动分割。基于传统图像处理方法的医学图像分割仅能利用浅层结构模型的浅层特征来识别感兴趣区域,并且需要大量人工干预。而基于机器学习的分割方法在模型建模时存在局... 详细信息

医学图像自动分割具有广泛和重要临床应用价值,特别是病灶、脏器的自动分割。基于传统图像处理方法的医学图像分割仅能利用浅层结构模型的浅层特征来识别感兴趣区域,并且需要大量人工干预。而基于机器学习的分割方法在模型建模时存在局限性且缺乏可解释性。本研究提出一种基于Transformer和卷积神经网络结合形态结构约束的三维医学图像分割方法。编码器中利用卷积神经网络和Transformer构建U型网络结构提取多重特征;解码器中采用上采样并通过跳跃连接将不同层次的特征拼接在一起;加入形态结构约束模块,通过提取病灶和脏器等分割目标的形状信息,以增强模型可解释性,并采用最大池化和平均池化操作,对经过卷积神经网络得到的结果进一步提取有代表性的特征,作为形态结构模块的输入,最终提高分割结果的准确性。在公开数据集Synapse和ACDC上利用评价指标Dice相似系数(DSC)和Hausdorff距离(HD)验证所提出算法的有效性。其中,在Synapse数据集上,18例数据作为训练集,12例数据作为测试集;在ACDC数据集上,70例数据作为训练集,10例数据作为验证集,20例数据作为测试集。实验结果表明,在Synapse上使用不同的优化器的Dice相似系数(DSC)和HD均值可以达到76.67%和25.18 mm(SGD优化器)及82.80%和21.07 mm(Adam优化器);在ACDC上不同的优化器的DSC可以达到90.65%(SGD优化器)及91.75%(Adam优化器),与其他方法相比具有一定的优势。所提出的方法对三维医学图像分割中的错分割问题有所改善,并提高了图像分割任务的性能。

关键词：三维医学图像图像分割 Transformer 卷积神经网络形态结构约束