Human detection based on a sequence of thermal images using deep learning

X. Wang; S. Hosseinyalamdary

doi:10.5194/isprs-archives-XLII-2-W13-127-2019

Human detection based on a sequence of thermal images using deep learning

X. Wang^*, S. Hosseinyalamdary

^*Corresponding author for this work

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

10 Citations (Scopus)

57 Downloads (Pure)

Abstract

Human detection has been playing an increasingly important role in many fields in recent years. Human detection is a still challenging task because, for the group of people, each individual has his unique appearance and, body shape. Compared with the traditional method, the deep learning neural network has the advantages of shorter computing time, higher accuracy and easier operation. Therefore, deep learning method has been widely used in object detection. The current state of art in human detection is RetinaNet. Among all the deep learning approaches, RetinaNet gives the highest accuracy of human detection (Lin, Goyal, Girshick, He, & Piotr Dollar, 2018).The temporal component of video provides additional and significant clues as compared to the static image. In this paper, the temporal relationship of the images is utilized to improve the accuracy of human detection. Compared to using only an image, the accuracy of human detection is 21.4% higher when a sequence of images is applied. .

Original language	English
Title of host publication	The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Editors	G. Vosselman, S.J. Oude Elberink, M.Y. Yang
Publisher	International Society for Photogrammetry and Remote Sensing (ISPRS)
Pages	127-132
Number of pages	6
Volume	42
Edition	2/W13
DOIs	https://doi.org/10.5194/isprs-archives-XLII-2-W13-127-2019
Publication status	Published - 4 Jun 2019
Event	4th ISPRS Geospatial Week 2019 - University of Twente, Enschede, Netherlands Duration: 10 Jun 2019 → 14 Jun 2019 Conference number: 4 https://www.gsw2019.org/

Publication series

Name	International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
Publisher	Copernicus
ISSN (Print)	1682-1750

Conference

Conference	4th ISPRS Geospatial Week 2019
Country/Territory	Netherlands
City	Enschede
Period	10/06/19 → 14/06/19
Internet address	https://www.gsw2019.org/

Keywords

Deep learning
Human detection
Temporal consistency
Thermal images
ITC-GOLD

Access to Document

10.5194/isprs-archives-XLII-2-W13-127-2019Licence: CC BY

ArticleFinal published version, 1.51 MBLicence: CC BY

Cite this

Wang, X., & Hosseinyalamdary, S. (2019). Human detection based on a sequence of thermal images using deep learning. In G. Vosselman, S. J. Oude Elberink, & M. Y. Yang (Eds.), The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences (2/W13 ed., Vol. 42, pp. 127-132). (International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives). International Society for Photogrammetry and Remote Sensing (ISPRS). https://doi.org/10.5194/isprs-archives-XLII-2-W13-127-2019

Wang, X. ; Hosseinyalamdary, S. / Human detection based on a sequence of thermal images using deep learning. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. editor / G. Vosselman ; S.J. Oude Elberink ; M.Y. Yang. Vol. 42 2/W13. ed. International Society for Photogrammetry and Remote Sensing (ISPRS), 2019. pp. 127-132 (International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives).

@inproceedings{f9e9665abaa04ef5a24915ff9e7cfbc8,

title = "Human detection based on a sequence of thermal images using deep learning",

abstract = "Human detection has been playing an increasingly important role in many fields in recent years. Human detection is a still challenging task because, for the group of people, each individual has his unique appearance and, body shape. Compared with the traditional method, the deep learning neural network has the advantages of shorter computing time, higher accuracy and easier operation. Therefore, deep learning method has been widely used in object detection. The current state of art in human detection is RetinaNet. Among all the deep learning approaches, RetinaNet gives the highest accuracy of human detection (Lin, Goyal, Girshick, He, & Piotr Dollar, 2018).The temporal component of video provides additional and significant clues as compared to the static image. In this paper, the temporal relationship of the images is utilized to improve the accuracy of human detection. Compared to using only an image, the accuracy of human detection is 21.4% higher when a sequence of images is applied. .",

keywords = "Deep learning, Human detection, Temporal consistency, Thermal images, ITC-GOLD",

author = "X. Wang and S. Hosseinyalamdary",

note = "Publisher Copyright: {\textcopyright} Authors 2019.; 4th ISPRS Geospatial Week 2019 ; Conference date: 10-06-2019 Through 14-06-2019",

year = "2019",

month = jun,

day = "4",

doi = "10.5194/isprs-archives-XLII-2-W13-127-2019",

language = "English",

volume = "42",

series = "International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives",

publisher = "International Society for Photogrammetry and Remote Sensing (ISPRS)",

pages = "127--132",

editor = "G. Vosselman and {Oude Elberink}, S.J. and Yang, {M.Y. }",

booktitle = "The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences",

edition = "2/W13",

url = "https://www.gsw2019.org/",

}

Wang, X & Hosseinyalamdary, S 2019, Human detection based on a sequence of thermal images using deep learning. in G Vosselman, SJ Oude Elberink & MY Yang (eds), The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2/W13 edn, vol. 42, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, International Society for Photogrammetry and Remote Sensing (ISPRS), pp. 127-132, 4th ISPRS Geospatial Week 2019, Enschede, Netherlands, 10/06/19. https://doi.org/10.5194/isprs-archives-XLII-2-W13-127-2019

Human detection based on a sequence of thermal images using deep learning. / Wang, X.; Hosseinyalamdary, S.
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. ed. / G. Vosselman; S.J. Oude Elberink; M.Y. Yang. Vol. 42 2/W13. ed. International Society for Photogrammetry and Remote Sensing (ISPRS), 2019. p. 127-132 (International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives).

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

TY - GEN

T1 - Human detection based on a sequence of thermal images using deep learning

AU - Wang, X.

AU - Hosseinyalamdary, S.

N1 - Conference code: 4

PY - 2019/6/4

Y1 - 2019/6/4

N2 - Human detection has been playing an increasingly important role in many fields in recent years. Human detection is a still challenging task because, for the group of people, each individual has his unique appearance and, body shape. Compared with the traditional method, the deep learning neural network has the advantages of shorter computing time, higher accuracy and easier operation. Therefore, deep learning method has been widely used in object detection. The current state of art in human detection is RetinaNet. Among all the deep learning approaches, RetinaNet gives the highest accuracy of human detection (Lin, Goyal, Girshick, He, & Piotr Dollar, 2018).The temporal component of video provides additional and significant clues as compared to the static image. In this paper, the temporal relationship of the images is utilized to improve the accuracy of human detection. Compared to using only an image, the accuracy of human detection is 21.4% higher when a sequence of images is applied. .

AB - Human detection has been playing an increasingly important role in many fields in recent years. Human detection is a still challenging task because, for the group of people, each individual has his unique appearance and, body shape. Compared with the traditional method, the deep learning neural network has the advantages of shorter computing time, higher accuracy and easier operation. Therefore, deep learning method has been widely used in object detection. The current state of art in human detection is RetinaNet. Among all the deep learning approaches, RetinaNet gives the highest accuracy of human detection (Lin, Goyal, Girshick, He, & Piotr Dollar, 2018).The temporal component of video provides additional and significant clues as compared to the static image. In this paper, the temporal relationship of the images is utilized to improve the accuracy of human detection. Compared to using only an image, the accuracy of human detection is 21.4% higher when a sequence of images is applied. .

KW - Deep learning

KW - Human detection

KW - Temporal consistency

KW - Thermal images

KW - ITC-GOLD

U2 - 10.5194/isprs-archives-XLII-2-W13-127-2019

DO - 10.5194/isprs-archives-XLII-2-W13-127-2019

M3 - Conference contribution

AN - SCOPUS:85067447885

VL - 42

T3 - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

SP - 127

EP - 132

BT - The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

A2 - Vosselman, G.

A2 - Oude Elberink, S.J.

A2 - Yang, M.Y.

PB - International Society for Photogrammetry and Remote Sensing (ISPRS)

T2 - 4th ISPRS Geospatial Week 2019

Y2 - 10 June 2019 through 14 June 2019

ER -

Wang X, Hosseinyalamdary S. Human detection based on a sequence of thermal images using deep learning. In Vosselman G, Oude Elberink SJ, Yang MY, editors, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2/W13 ed. Vol. 42. International Society for Photogrammetry and Remote Sensing (ISPRS). 2019. p. 127-132. (International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives). doi: 10.5194/isprs-archives-XLII-2-W13-127-2019

Human detection based on a sequence of thermal images using deep learning

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this