Continuous convolutional object tracking

Peer Springstübe; Stefan Heinrich; Stefan Wermter

Continuous convolutional object tracking

Peer Springstübe, Stefan Heinrich, Stefan Wermter

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

Tracking arbitrary objects is a challenging task in visual computing. A central problem is the need to adapt to the changing appearance of an object, particularly under strong transformation and occlusion. We propose a tracking framework that utilises the strengths of Convolutional Neural Networks (CNNs) to create a robust and adaptive model of the object from training data produced during tracking. An incremental update mechanism provides increased performance and reduces training during tracking, allowing its real-time use.

Original language	English
Title of host publication	Proceedings of the 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN2018)
Number of pages	6
Place of Publication	Bruges, Belgium
Publication date	1 Apr 2018
Pages	73-78
Publication status	Published - 1 Apr 2018
Externally published	Yes

Access to Document

Cite this

@inproceedings{c38e0b19173b41bab2358e201846a04c,

title = "Continuous convolutional object tracking",

abstract = "Tracking arbitrary objects is a challenging task in visual computing. A central problem is the need to adapt to the changing appearance of an object, particularly under strong transformation and occlusion. We propose a tracking framework that utilises the strengths of Convolutional Neural Networks (CNNs) to create a robust and adaptive model of the object from training data produced during tracking. An incremental update mechanism provides increased performance and reduces training during tracking, allowing its real-time use.",

author = "Peer Springst{\"u}be and Stefan Heinrich and Stefan Wermter",

year = "2018",

month = apr,

day = "1",

language = "English",

pages = "73--78",

booktitle = "Proceedings of the 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN2018)",

}

Continuous convolutional object tracking. / Springstübe, Peer; Heinrich, Stefan; Wermter, Stefan.
Proceedings of the 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN2018). Bruges, Belgium, 2018. p. 73-78.

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

TY - GEN

T1 - Continuous convolutional object tracking

AU - Springstübe, Peer

AU - Heinrich, Stefan

AU - Wermter, Stefan

PY - 2018/4/1

Y1 - 2018/4/1

N2 - Tracking arbitrary objects is a challenging task in visual computing. A central problem is the need to adapt to the changing appearance of an object, particularly under strong transformation and occlusion. We propose a tracking framework that utilises the strengths of Convolutional Neural Networks (CNNs) to create a robust and adaptive model of the object from training data produced during tracking. An incremental update mechanism provides increased performance and reduces training during tracking, allowing its real-time use.

AB - Tracking arbitrary objects is a challenging task in visual computing. A central problem is the need to adapt to the changing appearance of an object, particularly under strong transformation and occlusion. We propose a tracking framework that utilises the strengths of Convolutional Neural Networks (CNNs) to create a robust and adaptive model of the object from training data produced during tracking. An incremental update mechanism provides increased performance and reduces training during tracking, allowing its real-time use.

M3 - Article in proceedings

SP - 73

EP - 78

BT - Proceedings of the 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN2018)

CY - Bruges, Belgium

ER -

Continuous convolutional object tracking

Abstract

Access to Document

Fingerprint

Cite this