基于SVM邻域学习的视频目标检测方法  被引量:3

Video target detection method based on SVM neighborhood learning

在线阅读下载全文

作  者:胡涛[1] 胡军[1] 郭杭[2] HU Tao;HU Jun;GUO Hang(School of Information Engineering,Nanchang University,Nanchang 330031,China;Institute of Space Science and Technology,Nanchang University,Nanchang 330031,China)

机构地区:[1]南昌大学信息工程学院,江西南昌330031 [2]南昌大学空间科学与技术研究院,江西南昌330031

出  处:《现代电子技术》2017年第14期95-98,共4页Modern Electronics Technique

基  金:国家自然科学基金项目(41374039)

摘  要:针对传统SVM普通学习模型无法适应视频中目标姿态变化、有遮挡或复杂背景的局限性,提出一种新的SVM邻域学习模型。邻域学习是基于视频相邻帧在时间和空间上的高度相关性,每个测试帧在其相邻帧上抽取训练数据进行SVM模型的学习与更新,随着视频的更新,SVM模型将不断更新来适应目标检测的各种变化。通过大量样本在各种复杂环境下实验,采用统计学分析结果,证明SVM邻域学习比传统SVM普通学习准确率更高、鲁棒性更好。Since the common learning model of traditional support vector machine(SVM)can′t adapt to the change targetposture in video,and is limited with occlusion or complex background,a new SVM neighborhood learning model is proposed.The neighborhood learning is based on the high correlation of video adjacent frame both in time and space.The training data ofeach testing frame is extracted from its adjacent frame to learn and update the SVM model.With the updating of the video,theSVM model is updated continually to adapt to the changes of target detection.A large number of samples were experimented incomplex environment.The statistics is used to analyze the results to verify that the SVM neighborhood learning has higher accuracy and better robustness than the traditional SVM common learning.

关 键 词:SVM模型 邻域学习 视频目标检测 统计学分析 

分 类 号:TN948.6-34[电子电信—信号与信息处理]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象