Detail publikace

Depth-Based Filtration for Tracking Boost

CHRÁPEK, D. BERAN, V. ZEMČÍK, P.

Originální název

Depth-Based Filtration for Tracking Boost

Anglický název

Depth-Based Filtration for Tracking Boost

Jazyk

en

Originální abstrakt

This paper presents a novel depth information utilization method for performance boosting of tracking in traditional RGB trackers for arbitrary objects (objects not known in advance) by object segmentation/separation supported by depth information. The main focus is on real-time applications, such as robotics or surveillance, where exploitation of depth sensors, that are nowadays affordable, is not only possible but also feasible. The aim is to show that the depth information used for target segmentation significantly helps reducing incorrect model updates caused by occlusion or drifts and improves success rate and precision of traditional RGB tracker while keeping comparably efficient and thus possibly real-time. The paper also presents and discusses the achieved performance results.

Anglický abstrakt

This paper presents a novel depth information utilization method for performance boosting of tracking in traditional RGB trackers for arbitrary objects (objects not known in advance) by object segmentation/separation supported by depth information. The main focus is on real-time applications, such as robotics or surveillance, where exploitation of depth sensors, that are nowadays affordable, is not only possible but also feasible. The aim is to show that the depth information used for target segmentation significantly helps reducing incorrect model updates caused by occlusion or drifts and improves success rate and precision of traditional RGB tracker while keeping comparably efficient and thus possibly real-time. The paper also presents and discusses the achieved performance results.

Dokumenty

BibTex


@inproceedings{BUT119922,
  author="David {Chrápek} and Vítězslav {Beran} and Pavel {Zemčík}",
  title="Depth-Based Filtration for Tracking Boost",
  annote="This paper presents a novel depth information utilization method for performance
boosting of tracking in traditional RGB trackers for arbitrary objects (objects
not known in advance) by object segmentation/separation supported by depth
information. The main focus is on real-time applications, such as robotics or
surveillance, where exploitation of depth sensors, that are nowadays affordable,
is not only possible but also feasible. The aim is to show that the depth
information used for target segmentation significantly helps reducing incorrect
model updates caused by occlusion or drifts and improves success rate and
precision of traditional RGB tracker while keeping comparably efficient and thus
possibly real-time. The paper also presents and discusses the achieved
performance results.",
  address="Springer International Publishing",
  booktitle="Springer International Publishing",
  chapter="119922",
  doi="10.1007/978-3-319-25903-1_19",
  edition="Lecture Notes in Computer Science",
  howpublished="online",
  institution="Springer International Publishing",
  number="9386",
  year="2015",
  month="november",
  pages="217--228",
  publisher="Springer International Publishing",
  type="conference paper"
}