Shared-bed person segmentation based on motion estimation

Xuyuan Jin; Adrienne Heinrich; Caifeng Shan; Gerard De Haan

doi:10.1109/ICIP.2012.6466814

Shared-bed person segmentation based on motion estimation

Xuyuan Jin, Adrienne Heinrich, Caifeng Shan, Gerard De Haan

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Video-based sleep analysis is a topic with important applications, and shared-bed occurs frequently in the context of sleep. One difficulty for the shared-bed situation is to assign the movements to the correct person because they can occur in close proximity and even overlapping. To manage to achieve person segmentation in the shared-bed situation, in this paper we propose an approach to correctly segment the region of persons based on motion estimation. In our approach, considering the consistency of the motion vectors, specifically their length and angle, the adjacent blocks are clustered. The generated clusters are then assigned to a person according to temporal correlation. The occupied region of the person is updated each frame based on the assignment result of the clusters. The proposed approach tackles the segmentation issue when the two persons are close to each other or even overlap, and the accuracy of the segmentation is beyond 82% in the data set we acquired.

Original language	English
Title of host publication	2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	137-140
Number of pages	4
ISBN (Print)	9781467325332
DOIs	https://doi.org/10.1109/ICIP.2012.6466814
Publication status	Published - 1 Dec 2012
Event	19th IEEE International Conference on Image Processing (ICIP 2012) - Lake Buena Vista, FL, United States Duration: 30 Sept 2012 → 3 Oct 2012 Conference number: 19

Conference

Conference	19th IEEE International Conference on Image Processing (ICIP 2012)
Abbreviated title	ICIP 2012
Country/Territory	United States
City	Lake Buena Vista, FL
Period	30/09/12 → 3/10/12

Keywords

Motion Estimation
Video-based Segmentation

Access to Document

10.1109/ICIP.2012.6466814

Cite this

@inproceedings{70b097fba78f41e1a1ef728b13f04a7f,

title = "Shared-bed person segmentation based on motion estimation",

abstract = "Video-based sleep analysis is a topic with important applications, and shared-bed occurs frequently in the context of sleep. One difficulty for the shared-bed situation is to assign the movements to the correct person because they can occur in close proximity and even overlapping. To manage to achieve person segmentation in the shared-bed situation, in this paper we propose an approach to correctly segment the region of persons based on motion estimation. In our approach, considering the consistency of the motion vectors, specifically their length and angle, the adjacent blocks are clustered. The generated clusters are then assigned to a person according to temporal correlation. The occupied region of the person is updated each frame based on the assignment result of the clusters. The proposed approach tackles the segmentation issue when the two persons are close to each other or even overlap, and the accuracy of the segmentation is beyond 82% in the data set we acquired.",

keywords = "Motion Estimation, Video-based Segmentation",

author = "Xuyuan Jin and Adrienne Heinrich and Caifeng Shan and {De Haan}, Gerard",

year = "2012",

month = dec,

day = "1",

doi = "10.1109/ICIP.2012.6466814",

language = "English",

isbn = "9781467325332",

pages = "137--140",

booktitle = "2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "19th IEEE International Conference on Image Processing (ICIP 2012), ICIP 2012 ; Conference date: 30-09-2012 Through 03-10-2012",

}

Jin, X, Heinrich, A, Shan, C & De Haan, G 2012, Shared-bed person segmentation based on motion estimation. in 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings., 6466814, Institute of Electrical and Electronics Engineers, Piscataway, pp. 137-140, 19th IEEE International Conference on Image Processing (ICIP 2012), Lake Buena Vista, FL, Florida, United States, 30/09/12. https://doi.org/10.1109/ICIP.2012.6466814

Shared-bed person segmentation based on motion estimation. / Jin, Xuyuan; Heinrich, Adrienne; Shan, Caifeng et al.
2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings. Piscataway: Institute of Electrical and Electronics Engineers, 2012. p. 137-140 6466814.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Shared-bed person segmentation based on motion estimation

AU - Jin, Xuyuan

AU - Heinrich, Adrienne

AU - Shan, Caifeng

AU - De Haan, Gerard

N1 - Conference code: 19

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Video-based sleep analysis is a topic with important applications, and shared-bed occurs frequently in the context of sleep. One difficulty for the shared-bed situation is to assign the movements to the correct person because they can occur in close proximity and even overlapping. To manage to achieve person segmentation in the shared-bed situation, in this paper we propose an approach to correctly segment the region of persons based on motion estimation. In our approach, considering the consistency of the motion vectors, specifically their length and angle, the adjacent blocks are clustered. The generated clusters are then assigned to a person according to temporal correlation. The occupied region of the person is updated each frame based on the assignment result of the clusters. The proposed approach tackles the segmentation issue when the two persons are close to each other or even overlap, and the accuracy of the segmentation is beyond 82% in the data set we acquired.

AB - Video-based sleep analysis is a topic with important applications, and shared-bed occurs frequently in the context of sleep. One difficulty for the shared-bed situation is to assign the movements to the correct person because they can occur in close proximity and even overlapping. To manage to achieve person segmentation in the shared-bed situation, in this paper we propose an approach to correctly segment the region of persons based on motion estimation. In our approach, considering the consistency of the motion vectors, specifically their length and angle, the adjacent blocks are clustered. The generated clusters are then assigned to a person according to temporal correlation. The occupied region of the person is updated each frame based on the assignment result of the clusters. The proposed approach tackles the segmentation issue when the two persons are close to each other or even overlap, and the accuracy of the segmentation is beyond 82% in the data set we acquired.

KW - Motion Estimation

KW - Video-based Segmentation

UR - http://www.scopus.com/inward/record.url?scp=84875831634&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2012.6466814

DO - 10.1109/ICIP.2012.6466814

M3 - Conference contribution

AN - SCOPUS:84875831634

SN - 9781467325332

SP - 137

EP - 140

BT - 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 19th IEEE International Conference on Image Processing (ICIP 2012)

Y2 - 30 September 2012 through 3 October 2012

ER -

Shared-bed person segmentation based on motion estimation

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this