NON-RIGID MULTI-BODY TRACKING in RGBD STREAMS

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

Research output: Contribution to journalConference article

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 (US)
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 - May 29 2019
Event4th ISPRS Geospatial Week 2019 - Enschede, Netherlands
Duration: Jun 10 2019Jun 14 2019

Fingerprint

Animals
Detectors
matrix
occlusion
Sensors
matrices
shelves
segmentation
animals
education
Experiments
sensor
animal
sensors
detectors
experiment
interactions
detector

All Science Journal Classification (ASJC) codes

  • Environmental Science (miscellaneous)
  • Instrumentation
  • Earth and Planetary Sciences (miscellaneous)

Cite this

Dai, K. X. ; Guo, H. ; Mordohai, Philippos ; Marinello, F. ; Pezzuolo, A. ; Feng, Q. L. ; Niu, Q. D. / NON-RIGID MULTI-BODY TRACKING in RGBD STREAMS. In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2019 ; Vol. 4, No. 2/W5. pp. 341-348.
@article{78a87cff561345b6aaad03c947862e9b,
title = "NON-RIGID MULTI-BODY TRACKING in RGBD STREAMS",
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.",
author = "Dai, {K. X.} and H. Guo and Philippos Mordohai and F. Marinello and A. Pezzuolo and Feng, {Q. L.} and Niu, {Q. D.}",
year = "2019",
month = "5",
day = "29",
doi = "https://doi.org/10.5194/isprs-annals-IV-2-W5-341-2019",
language = "English (US)",
volume = "4",
pages = "341--348",
journal = "ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences",
issn = "2194-9042",
number = "2/W5",

}

NON-RIGID MULTI-BODY TRACKING in RGBD STREAMS. / Dai, K. X.; Guo, H.; Mordohai, Philippos; Marinello, F.; Pezzuolo, A.; Feng, Q. L.; Niu, Q. D.

In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. 4, No. 2/W5, 29.05.2019, p. 341-348.

Research output: Contribution to journalConference article

TY - JOUR

T1 - NON-RIGID MULTI-BODY TRACKING in RGBD STREAMS

AU - Dai, K. X.

AU - Guo, H.

AU - Mordohai, Philippos

AU - Marinello, F.

AU - Pezzuolo, A.

AU - Feng, Q. L.

AU - Niu, Q. D.

PY - 2019/5/29

Y1 - 2019/5/29

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85067512770&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067512770&partnerID=8YFLogxK

U2 - https://doi.org/10.5194/isprs-annals-IV-2-W5-341-2019

DO - https://doi.org/10.5194/isprs-annals-IV-2-W5-341-2019

M3 - Conference article

VL - 4

SP - 341

EP - 348

JO - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

JF - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

SN - 2194-9042

IS - 2/W5

ER -