检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:陈惠君[1]
机构地区:[1]郑州大学,河南郑州450000
出 处:《现代电子技术》2016年第24期109-112,115,共5页Modern Electronics Technique
基 金:国家自然科学基金(30353326)
摘 要:针对当前运动图像关键帧的快速跟踪系统存在误差大、实时性差的问题,提出一种基于自适应Harris角点检测和小波降噪滤波的运动图像关键帧快速跟踪系统设计方法。系统设计分为算法设计、系统的硬件设计和软件设计三大部分。对输入的原始图像进行图像降噪和角点检测处理,通过对运动参量的全局估计和误差补偿,实现对运动图像的关键帧快速跟踪识别。对系统的上电加载模块、图像的外部特征存储模块、系统逻辑控制模块和液晶显示接口电路等进行优化设计,在VHDL平台进行软件开发。仿真结果表明,该系统进行运动图像的关键帧快速跟踪和图像识别,能提高对运动图像目标的快速特征提取和细节捕捉分析能力,帧匹配度较高,可靠性、稳定性较好。Since the fast tracking system of current moving image keyframe has the problems of poor real-time performance and big error, an adaptive Harris corner point detection and wavelet denoising filtering based design method for fast tracking system of moving image keyframe is proposed. The system design is divided into the algorithm design, hardware design and software design. The input original image is processed with the image noise reduction and corner point detection. The moving image keyframe can be quickly tracked and recognized by means of the global estimation and error compensation of motion parameters. The optimization design of power-on load module of the system, external characteristics storage module of the image, system logic control module and LCD interface circuit are performed. Software development is carried out on VHDL. The simulation results show that the system can improve the fast feature extraction ability and detail capture analysis ability of the moving image target while performing the keyframe fast tracking and image recognition of the moving image, and has high frame matching degree and reliable stability.
分 类 号:TN953[电子电信—信号与信息处理] TP391[电子电信—信息与通信工程]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.15