Robot Visual Tracking via Incremental Self-Updating of Appearance Model

Robot Visual Tracking via Incremental Self-Updating of Appearance Model
复制标题

通过外观模型增量自我更新的机器人视觉跟踪

DOI:
10.5772/56759
复制
发表时间:
2013-09
影响因子:
2.3
通讯作者:
Jiang, Zhiguo
Jiang, Zhiguo
中科院分区:
计算机科学4区
文献类型:
--
作者:
Zhao, Danpei;Lu, Ming;Zhang, Xuguang;Jiang, Zhiguo

文献摘要

参考文献

被引文献

相似文献

针对机器人平台,提出了一种增量自更新视觉跟踪方法。我们的跟踪器将跟踪问题视为二元分类:目标和背景。在这项工作中使用灰度、HOG和LBP特征来表示目标,并将其集成到粒子滤波框架中。为了在长时间序列中跟踪目标,跟踪器必须更新其模型以跟踪最近的目标。针对传统方法存在的计算浪费和缺乏模型更新策略的问题,设计了一种智能有效的在线自更新策略,选择最优更新时机。外观模型的更新策略可以基于当前框架与先前更新框架之间的判别能力的变化来实现。通过自适应调整更新步长,可以在保持模型稳定性的同时,避免不必要更新造成的严重计算时间浪费。此外,当目标被暂时遮挡时,外观模型可以避免严重的漂移问题。实验结果表明,该跟踪器能够在姿态、尺度、光照和遮挡等多种复杂环境变化的视频序列中实现鲁棒、高效的跟踪性能。
This paper proposes a target tracking method called Incremental Self-Updating Visual Tracking for robot platforms. Our tracker treats the tracking problem as a binary classification: the target and the background. The greyscale, HOG and LBP features are used in this work to represent the target and are integrated into a particle filter framework. To track the target over long time sequences, the tracker has to update its model to follow the most recent target. In order to deal with the problems of calculation waste and lack of model-updating strategy with the traditional methods, an intelligent and effective online self-updating strategy is devised to choose the optimal update opportunity. The strategy of updating the appearance model can be achieved based on the change in the discriminative capability between the current frame and the previous updated frame. By adjusting the update step adaptively, severe waste of calculation time for needless updates can be avoided while keeping the stability of the model. Moreover, the appearance model can be kept away from serious drift problems when the target undergoes temporary occlusion. The experimental results show that the proposed tracker can achieve robust and efficient performance in several benchmark-challenging video sequences with various complex environment changes in posture, scale, illumination and occlusion.
DOI: 10.1117/12.918705
发表时间: 2012-05
影响因子: 8.3
作者:
A. Lacaze;K. Murphy;Mark Del Giorno;Katrina Corley
通讯作者: A. Lacaze;K. Murphy;Mark Del Giorno;Katrina Corley
DOI: --
发表时间: --
期刊: --
影响因子: --
作者:
X. Jin;Jing-jing Du;Bao Jia
通讯作者: X. Jin;Jing-jing Du;Bao Jia
DOI: 10.1109/icassp.2007.366062
发表时间: 2007-04
期刊: 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07
影响因子: --
作者:
Tiesheng Wang;I. Gu;P. Shi
通讯作者: Tiesheng Wang;I. Gu;P. Shi
DOI: 10.1109/tsmcc.2012.2198055
发表时间: 2012-11
期刊: IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)
影响因子: --
作者:
Theodoros Theodoridis;Huosheng Hu
通讯作者: Theodoros Theodoridis;Huosheng Hu
DOI: 10.1117/12.895965
发表时间: 2011-09
期刊: --
影响因子: --
作者:
Qing Wang;Feng Chen;Wenli Xu;Ming-Hsuan Yang
通讯作者: Qing Wang;Feng Chen;Wenli Xu;Ming-Hsuan Yang