NON-RIGID MULTI-BODY TRACKING in RGBD STREAMS

K. X. Dai, H. Guo, P. Mordohai, F. Marinello, A. Pezzuolo, Q. L. Feng, Q. D. Niu

Research output: Contribution to journalConference articlepeer-review

Abstract

To efficiently collect training data for an off-the-shelf object detector, we consider the problem of segmenting and tracking non-rigid objects from RGBD sequences by introducing the spatio-temporal matrix with very few assumptions – no prior object model and no stationary sensor. Spatial temporal matrix is able to encode not only spatial associations between multiple objects, but also component-level spatio temporal associations that allow the correction of falsely segmented objects in the presence of various types of interaction among multiple objects. Extensive experiments over complex human/animal body motions with occlusions and body part motions demonstrate that our approach substantially improves tracking robustness and segmentation accuracy.

Original languageEnglish
Pages (from-to)341-348
Number of pages8
JournalISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Volume4
Issue number2/W5
DOIs
StatePublished - 29 May 2019
Event4th ISPRS Geospatial Week 2019 - Enschede, Netherlands
Duration: 10 Jun 201914 Jun 2019

Keywords

  • Multi-body tracking
  • Non-rigid
  • Point clouds
  • RGBD

Fingerprint

Dive into the research topics of 'NON-RIGID MULTI-BODY TRACKING in RGBD STREAMS'. Together they form a unique fingerprint.

Cite this