期刊文献+

基于聚类算法的轨道交通履带式消防机器人的应用 被引量:1

Application of Crawler-type Firefighting Robot in Rail Transit Based on Clustering Algorithm
下载PDF
导出
摘要 对履带式消防机器人的构型进行分析,简化其构型设计为四轮机器人,并建立相应的坐标系。通过对其运动模型进行规律分析,得出单侧履带上所有点的运动速度规律,完成了功能模块的设计,再根据功能模块的设置完成对机器人的硬件结构设计。将履带式消防机器人所采集视频图像中每个像素点的色彩值作为特征向量,将所有采集到的视频图像构成一个样本集合,把图像分割任务转换为数据集合的聚类任务,运用K-means聚类算法进行图像区域分类,获取所需的分离图像。 This paper analyzes the configuration of a crawler-type firefighting robot,simplifies its configuration and design as a four wheeled robot,and establishes the corresponding coordinate system.By analyzing the laws of its motion model,the velocity patterns for all points on the single track are obtained.The design of the functional module is completed,and the hardware structure of the robot is designed according to the settings of the functional module.The color values of each pixel in the video image collected by the crawler-typefirefighting robot are used as feature vectors,and all collected video images are formed into a sample set.The image segmentation task is transformed into a clustering task of the data set,and the K-means clustering algorithm is used for image region classification to obtain the required separated images.
作者 张杨 刘国成 ZHANG Yang;LIU Guocheng(Guangzhou Railway Polytechnic,Guangzhou 510430,China)
出处 《现代信息科技》 2023年第20期62-65,74,共5页 Modern Information Technology
基金 广州市科技计划项目(202102080208)。
关键词 聚类算法 轨道交通 履带式机器人 消防巡检 clustering algorithm rail transit crawler-type robot fire patrol inspection
  • 相关文献

参考文献11

二级参考文献68

  • 1赵宏伟,陈霄,龙曼丽,袁世培.基于改进PLSA分类器的目标分类算法[J].吉林大学学报(工学版),2012,42(S1):231-235. 被引量:2
  • 2黄士科,陶琳,张天序.一种改进的基于光流的运动目标检测方法[J].华中科技大学学报(自然科学版),2005,33(5):39-41. 被引量:17
  • 3杜友田,陈峰,徐文立,李永彬.基于视觉的人的运动识别综述[J].电子学报,2007,35(1):84-90. 被引量:79
  • 4Friedman N, Russell S. hnage segmentation in video sequ- ences : a probabilistic approach [ C 1//Proceedings of the 13th conference on uncertainty in artificial intelligence. USA:Mor- gan Kaufmann, 1997 : 175-181.
  • 5Zhao Pengxiang, Zhao Yanyun, Cai Anni. Hierarchical code- book background model using haar- like features [ C ]//Proc of IEEE international conference on network infrastructure and digital content. [ s. 1. ] :IEEE,2012:438-442.
  • 6Reddy V,Sanderson C, Lovell B C. Improved foreground de- tection via block- based classifier cascade with probabilistic decision integration[ J ]. IEEE Trans on Circuits and Systems for Video Technology,2013,23( 1 ) :83-93.
  • 7Shi Xun,Tsotsos J K. Background subtraction via early recur-rence in dynamic scenes[ C]//Proc of 21st international con- ference on pattern recognition. [ s. 1. ] : [ s. n. ] ,2012:3172- 3175.
  • 8Lee D S. Effective Gaussian mixture learning for video back- ground subtraction[ J ]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005,27 ( 5 ) : 827- 832.
  • 9Zhang Z, Lipton A J, Venetianer P L, et al. Background model- ing with feature blocks[ P]. USA:US8150103,2012-04-03.
  • 10Elgammal A, Duraiswami R, Harwood D, et al. Background and foreground modeling using nonparametric kernel density estimation for visual surveillance [ J ]. Proceedings of IEEE, 2002,90(7) :1151-1163.

共引文献60

同被引文献5

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部