TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Pothole Detection and Tracking in Car Video Sequence

Tutkimustuotosvertaisarvioitu

Standard

Pothole Detection and Tracking in Car Video Sequence. / Schiopu, Ionut; Saarinen, Jukka P.; Kettunen, Lauri; Tabus, Ioan.

International Conference on Telecommunications and Signal Processing (TSP). IEEE, 2016. s. 701-706.

Tutkimustuotosvertaisarvioitu

Harvard

Schiopu, I, Saarinen, JP, Kettunen, L & Tabus, I 2016, Pothole Detection and Tracking in Car Video Sequence. julkaisussa International Conference on Telecommunications and Signal Processing (TSP). IEEE, Sivut 701-706, Iso-Britannia, 1/01/15.

APA

Schiopu, I., Saarinen, J. P., Kettunen, L., & Tabus, I. (2016). Pothole Detection and Tracking in Car Video Sequence. teoksessa International Conference on Telecommunications and Signal Processing (TSP) (Sivut 701-706). IEEE.

Vancouver

Schiopu I, Saarinen JP, Kettunen L, Tabus I. Pothole Detection and Tracking in Car Video Sequence. julkaisussa International Conference on Telecommunications and Signal Processing (TSP). IEEE. 2016. s. 701-706

Author

Schiopu, Ionut ; Saarinen, Jukka P. ; Kettunen, Lauri ; Tabus, Ioan. / Pothole Detection and Tracking in Car Video Sequence. International Conference on Telecommunications and Signal Processing (TSP). IEEE, 2016. Sivut 701-706

Bibtex - Lataa

@inproceedings{1a5dabcb63534a658b46559dc048112a,
title = "Pothole Detection and Tracking in Car Video Sequence",
abstract = "In this paper, we propose a low complexity method for detection and tracking of potholes in video sequences taken by a camera placed inside a moving car.The region of interest for the detection of the potholes is selected as the image area where the road is observed with the highest resolution. A threshold-based algorithm generates a set of candidate regions. For each region the following features are extracted: its size, the regularity of the intensity surface, contrast with respect to background model, and the region's contour length and shape. The candidate regions are labeled as putative potholes by a decision tree according to these features, eliminating the false positives due to shadows of wayside objects.The putative potholes that are successfully tracked in consecutive frames are finally declared potholes.Experimental results with real video sequences show a good detection precision.",
keywords = "pothole detection, pothole tracking, region of interest, Euclidean distance mapping",
author = "Ionut Schiopu and Saarinen, {Jukka P.} and Lauri Kettunen and Ioan Tabus",
year = "2016",
month = "6",
language = "English",
isbn = "978-1-5090-1287-9",
pages = "701--706",
booktitle = "International Conference on Telecommunications and Signal Processing (TSP)",
publisher = "IEEE",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Pothole Detection and Tracking in Car Video Sequence

AU - Schiopu, Ionut

AU - Saarinen, Jukka P.

AU - Kettunen, Lauri

AU - Tabus, Ioan

PY - 2016/6

Y1 - 2016/6

N2 - In this paper, we propose a low complexity method for detection and tracking of potholes in video sequences taken by a camera placed inside a moving car.The region of interest for the detection of the potholes is selected as the image area where the road is observed with the highest resolution. A threshold-based algorithm generates a set of candidate regions. For each region the following features are extracted: its size, the regularity of the intensity surface, contrast with respect to background model, and the region's contour length and shape. The candidate regions are labeled as putative potholes by a decision tree according to these features, eliminating the false positives due to shadows of wayside objects.The putative potholes that are successfully tracked in consecutive frames are finally declared potholes.Experimental results with real video sequences show a good detection precision.

AB - In this paper, we propose a low complexity method for detection and tracking of potholes in video sequences taken by a camera placed inside a moving car.The region of interest for the detection of the potholes is selected as the image area where the road is observed with the highest resolution. A threshold-based algorithm generates a set of candidate regions. For each region the following features are extracted: its size, the regularity of the intensity surface, contrast with respect to background model, and the region's contour length and shape. The candidate regions are labeled as putative potholes by a decision tree according to these features, eliminating the false positives due to shadows of wayside objects.The putative potholes that are successfully tracked in consecutive frames are finally declared potholes.Experimental results with real video sequences show a good detection precision.

KW - pothole detection

KW - pothole tracking

KW - region of interest

KW - Euclidean distance mapping

UR - http://www.cs.tut.fi/~schiopu/Potholes/

M3 - Conference contribution

SN - 978-1-5090-1287-9

SP - 701

EP - 706

BT - International Conference on Telecommunications and Signal Processing (TSP)

PB - IEEE

ER -