新書推薦：
《
大洗牌
》
售價：NT$
437.0
《
亚洲经济发展与模式分析
》
售價：NT$
498.0
《
零基础制作栩栩如生的立体纸艺花
》
售價：NT$
274.0
《
第三帝国图文史（修订版）：纳粹德国浮沉实录（彩色精装典藏版）
》
售價：NT$
941.0
《
四大会计师事务所：历史秘辛与未来挑战
》
售價：NT$
386.0
《
中国社会经济史
》
售價：NT$
498.0
《
犯罪心理X档案：法医精神科医生真实办案手记（第一季）法医精神科医师心理解剖手记
》
售價：NT$
269.0
《
台湾农业产业发展研究
》
售價：NT$
549.0
|
| 內容簡介： |
|
本书以序列图像中目标分析技术的基本过程为主线，系统地介绍了目标分析的基本理论，详细讲解了作者的研究成果。绪论重点对序列图像中目标分析技术的研究现状进行了分析。目检测部分，提出了一种基本的视频运动目标检测技术框架；在此基础上提出了两种改进的目标检测算法，可分别用于需要精确检测目标和阈值化后目标连通性较差的应用场合；针对帧间差分法的不足，提出了一种基于差分背景融合建模的目标检测算法。目标定位部分，提出了一种基于减法聚类算法的目标定位技术和一种椭圆域减法聚类目标定位方法；提出了减法聚类目标定位算法的七点优化技术；另外，提出了一种基于非参数核密度估计的目标定位技术，可根据应用灵活选择核函数估计样本点的密度值分布；针对减法聚类技术复杂度高的问题，提出了一种基于Nystr?m密度值逼近的减法聚类方法。目标运动估计部分，为了降低运动估计的计算复杂度，提出了一种基于运动场预测的六边形块运动估计算法和一种基于运动场预测的部分失真运动估计算法；另外，对UMHexagonS算法进行了改进。目标跟踪与识别部分，针对复杂背景下的目标跟踪，提出了一种基于图像感知哈希技术的目标跟踪算法；针对遮挡情况，提出了一种自适应步长选择的NCC图像匹配算法；最后，采用基于团块和轨迹分析的方法实现了区域入侵、人体跌倒、遗留物检测、人体徘徊四种异常行为的判定。
|
| 關於作者： |
|
李子印，2006年6月毕业于浙江大学，获工学博士学位。副教授，硕士生导师，新加坡南洋理工大学访问学者。浙江省"LED照明新技术”重点科技创新团队青年学科骨干。先后承担《图像传感与图像处理》、《视频分析与模式识别》、《多媒体技术》、《VB程序设计》、《图像处理技术》等本科课程和研究生课程《图像器件与图像处理》的教学任务，教学效果优异，深受学生喜爱。主持国家青年科学基金一项，国家质检总局质量技术监督科技项目一项，浙 江 省 仪 器 科 学 与 技 术 重 中 之 重 学科光电方向人才培育计划项目一项，企业横向项目多项；作为主要成员参加国家科技支撑计划子课题一项，浙江省重大科技专项两项，浙江省教育厅项目一项。目前有22 篇文章发表，有12 篇被EI 或SCI 收录。是国际期刊Journal of Visual Communication and Image Representation、IEEE Signal Processing Letters和多个国内一级期刊的审稿人。
|
| 目錄：
|
第1 章 绪论··········································································································· 1
1.1 研究背景及意义······························································································· 1
1.2 视频运动目标检测研究现状··········································································· 3
1.2.1 背景差法··································································································· 4
1.2.2 邻帧差法··································································································· 5
1.2.3 光流法······································································································· 5
1.3 视频运动目标定位研究现状··········································································· 6
1.4 视频运动估计研究现状··················································································· 7
1.5 视频运动目标跟踪研究现状··········································································· 8
1.6 本书的内容及章节安排················································································· 10
1.6.1 本书的内容····························································································· 10
1.6.2 本书的章节安排······················································································11
1.7 本章小结········································································································ 13
参考文献················································································································ 13
第2 章 基于积累差异背景建模的视频运动目标检测······························21
2.1 引言················································································································ 21
2.2 基于积累差异的背景建模············································································· 23
2.2.1 积累差异································································································· 23
2.2.2 积累差异背景建模················································································· 23
2.3 Otsu 自适应阈值化及目标轮廓提取····························································· 25
2.3.1 Otsu 阈值化算法···················································································· 25
2.3.2 改进的Otsu 阈值化算法········································································ 26
2.3.3 目标轮廓提取························································································· 27
2.4 两步区域生长目标连通区域标记································································· 27
2.5 目标质心关联································································································ 28
2.5.1 质心标记································································································· 28
2.5.2 质心关联································································································· 28
2.6 监控场合行人及运动车辆检测实验····························································· 29
2.6.1 积累差异背景建模及运动目标检测······················································ 29
2.6.2 运动目标轮廓提取及质心关联····························································· 31
2.7 夜间运动车辆检测实验················································································· 32
2.8 语义视频运动目标检测实验········································································· 36
2.8.1 颜色空间及肤色模型············································································· 36
2.8.2 实验效果及分析····················································································· 38
2.9 积累差异背景建模与GMM 背景建模的比较实验······································ 40
2.10 本章小结······································································································ 43
参考文献················································································································ 43
第3 章 基于差分背景融合建模的运动目标检测·······································46
3.1 引言················································································································ 46
3.2 算法基本思想································································································ 46
3.3 背景模型的建立··················································································3
|
| 內容試閱：
|
随着视频监控系统的广泛应用，监控规模和数据量迅速增长，普通监控系统的技术和人力成本的提高已经很难保证监控的及时性和有效性，智能视频监控系统已经成为大势所趋。但是，作为图像处理、模式识别和数据挖掘等学科的交叉融合，智能视频监控技术面临的实际应用场景复杂，应用需求多样化，技术实现难度大，目前仍处于探索发展阶段。
智能视频监控系统是能够自动对视频信号进行处理、分析和理解，通过对序列图像进行目标检测、定位、跟踪和识别，分析和判断目标的行为，能在异常情况时发出警报或提供有用信息的视频监控系统。智能视频监控系统的关键技术主要包括图像预处理、视频编解码、目标检测、目标定位、目标跟踪和模式识别等。
本书是作者在参考国内外大量学术论文和专著的基础上，结合作者多年的研究成果编写而成的。本书以序列图像中目标分析技术的基本过程为主线，系统地介绍了目标分析的基本理论，详细讲解了作者的研究成果。
本书适用于信号与信息处理、电子技术、计算机技术、网络和通信工程等相关专业高年级本科生和研究生的参考书籍，也可作为从事图像处理、机器视觉和模式识别等领域的研究和开发技术人员的参考书。
全书分为五大部分，第一部分为绪论，在第1 章对序列图像中目标分析技术的研究背景和意义进行了介绍，总结了国内外的相关研究现状。第二部分为运动目标的检测，其中第2 章提出了一种基于积累差异背景建模的视频运动目标检测方法，第3 章提出了一种差分背景融合建模的运动目标检测方法，第4 章提出了一种融合Knockout 抠图技术的视频运动目标检测方法，第5 章提出了一种基于网格区域划分的视频运动目标检测方法。第三部分为运动目标的定位，其中第6 章提出了一种基于减法聚类算法的视频运动目标定位技术，第7 章提出了一种视频目标定位的减法聚类改进算法，第8 章提出了一种非参数核密度估计视频目标空域定位算法，第9 章提出了一种基于Nystr?m 密度值逼近的减法聚类算法。第四部分为运动目标的运动估计，其中第10 章提出了一种基于运动场预测的六边形块运动估计算法，第11 章提出了一种基于运动信息自适应的快速运动估计算法，第12 章提出了一种快速高效的部分失真块运动估计搜索算法。第五部分为运动目标的跟踪与识别，其中第13 章提出了一种基于图像感知哈希技术的运动目标跟踪技术，第14 章提出了一种遮挡情况下的运动目标跟踪技术，第15 章介绍了智能视频监控系统中典型的异常行为分析技术，第16 章进行了总结与展望。
在本书编写过程中，得到了两位作者的单位中国计量大学和杭州电子科技大学的很多领导、同事的鼓励和帮助，在此一并表示衷心感谢。本书参考了国内外许多专家和研究人员的研究成果，引用了其中观点、数据与结论，在此表示诚挚的谢意。另外，还要特别感谢电子工业出版社责任编辑徐蔷薇对本书的顺利出版付出的努力与劳动。
由于作者水平有限，加之时间紧迫，书中不妥与疏漏之处在所难免，敬请各位专家、学者和读者批评指正。
李子印
2016 年5 月于中国计量大学
|
|
購物車/收銀台(
0
) | 在線留言板
| 付款方式
| 聯絡我們
| 運費計算
| 幫助中心 |
加入書簽
HOME
新書上架
