| 本文已被：浏览 5540次 下载 6434次 |
码上扫一扫！ |
|
|
| 背景变化鲁棒的自适应视觉跟踪目标模型 |
|
王建宇1, 陈熙霖1,2, 高文1,2, 赵德斌1,2
|
|
1.哈尔滨工业大学,计算机科学与技术学院,黑龙江,哈尔滨,150001;2.中国科学院,计算技术研究所,北京,100080
|
|
| 摘要: |
| 提出了视觉跟踪任务中目标动态建模的一种方法.该方法首先针对跟踪序列中的当前帧图像观测进行Haar变换,从而得到图像的过完备特征描述;然后根据Fisher准则,评价每个Haar特征对目标和当前背景的区分能力,目标模型由那些区分能力最强的Haar特征构成.在跟踪过程中,采用卡尔曼滤波算法预测目标下一时刻的可能位置,从而根据目标的图像观测和目标下一时刻可能的位置附近的背景图像观测,对Haar特征的区分能力进行动态评价.通过保留区分能力强的特征,同时淘汰区分能力弱的特征,维护目标模型的强可区分性和低计算复杂性.该方法的主要策略是,在最大程度地保持可区分性的前提下,减少计算的复杂性.实验结果表明,在存在诸多不确定性因素的真实长序列视频上,该跟踪方法能够实时地完成复杂的目标跟踪任务. |
| 关键词: 视觉目标跟踪 在线特征选择 目标模型 Haar特征 卡尔曼滤波 |
| DOI： |
| 分类号: |
| 基金项目:Supported by the National Natural Science Foundation of China under Grant No.60332010 (国家自然科学基金); the "100 Talents Program" of the Chinese Academy of Sciences (中国科学院百人计划); the Shanghai Municipal Sciences and Technology Committee under Grand No.03DZ15013 (上海市科委项目); the ISVISION Technologies Co., Ltd. (上海银晨智能识别科技有限公司) |
|
| Adaptive Appearance Model Robust to Background Variations |
|
WANG Jian-Yu,CHEN Xi-Lin,GAO Wen,ZHAO De-Bin
|
| Abstract: |
| A novel method of dynamic object modeling for visual tracking is presented. The Haar transformation is first applied on the incoming image of the video to get features, which are over-complete description of the image. Then, the Fisher criteria are employed for ranking features based on their contributions to the discrimination between the tracked objects and the background. After that, the objects are modeled by the subset of top-ranked features. During tracking, a Kalman filter is used to predict the upcoming destinations of the tracked objects and the features are re-ranked by the discrimination between the objects and predicted locations. Thereafter, objects models will be updated and only discriminative features are kept in it. This proposed strategy aims to maximally maintain the basic discrimination and reduce computational cost simultaneously. To evaluate the performance of the proposed method, several experiments have been conducted on long video sequences. The experimental results show that the proposed method can handle various uncertain factors under the real world conditions and successfully track the objects in real-time. |
| Key words: visual object tracking online feature selection appearance model Haar feature Kalman filter |
