基于改进在线多示例学习算法的机器人目标跟踪

提出基于改进的在线多示例学习算法（Improved multiple instance learning,IMIL）的移动机器人目标跟踪方法.该方法利用射频识别系统（Radio frequency identification,RFID）粗定位IMIL算法的搜索区域,然后应用IMIL算法实现目标跟踪.该方法保证了机器人跟踪系统的连续性,解决了目标突然转弯时的跟踪问题.IMIL算法采用从低维空间提取的压缩特征描述包中示例,以降低算法耗时.通过最大化弱分类器与极大似然概率的内积,选择判别能力强的弱分类器,避免了弱分类器选择过程中多次计算包概率和示例概率,进一步提高算法的实时处理能力.计算包概率时该...

Full description

Saved in:
Bibliographic Details
Published in自动化学报 Vol. 40; no. 12; pp. 2916 - 2925
Main Author 王丽佳 贾松敏 李秀智 王爽
Format Journal Article
LanguageChinese
Published 2014
Subjects
压缩特征
射频识别系统
改进的在线多示例学习
目标跟踪
Online AccessGet full text

Cover

More Information
Summary:提出基于改进的在线多示例学习算法（Improved multiple instance learning,IMIL）的移动机器人目标跟踪方法.该方法利用射频识别系统（Radio frequency identification,RFID）粗定位IMIL算法的搜索区域,然后应用IMIL算法实现目标跟踪.该方法保证了机器人跟踪系统的连续性,解决了目标突然转弯时的跟踪问题.IMIL算法采用从低维空间提取的压缩特征描述包中示例,以降低算法耗时.通过最大化弱分类器与极大似然概率的内积,选择判别能力强的弱分类器,避免了弱分类器选择过程中多次计算包概率和示例概率,进一步提高算法的实时处理能力.计算包概率时该算法平等对待各示例,保证概率高的示例对包概率的贡献度,克服跟踪漂移问题.跟踪过程中,结合当前跟踪结果与目标模板间的相似性分数在线实时调整分类器,提高了算法的自适应能力.最后将本文方法在视频和移动机器人上进行实验.实验结果表明,该方法在目标运动突变及外观改变时具有较强的鲁棒性和准确性,并满足系统的实时性要求.
Bibliography:Improved multiple instance learning （IMIL）, person following, radio frequency identification （RFID）, com-pressed features
11-2109/TP
WANG Li-Jia, JIA Song-Min, LI Xiu-Zhi, WANG Shuang
An improved multiple instance learning （IMIL） algorithm is proposed for person following with a mobile robot. In the tracking process, radio frequency identification （RFID） provides a searching area for the IMIL algorithm, which then successfully detects the person of interest. In IMIL, compressed features are extracted to describe instances of bags from the low dimensional space so as to reduce the time complexity in the operation. Then, the most discriminative weak classifiers are selected from the weak classifier pool by maximizing the inner product between the weak classifier and the log-likelihood function. The scheme avoids computing the bag probability and instance probability many times, which further reduces the computational time. To deal with the drift problem, the bag probability equally depends on each instance. Furthe
ISSN:0254-4156
1874-1029