Home > Research > Publications & Outputs > ARTOT
View graph of relations

ARTOT: Autonomous Real-Time Object detection and Tracking by a moving camera

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

ARTOT: Autonomous Real-Time Object detection and Tracking by a moving camera. / Angelov, Plamen; Gude, Chirag; Sadeghi-Tehran, Pouria et al.
Intelligent Systems (IS), 2012 6th IEEE International Conference. IEEE, 2012. p. 446-452.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Angelov, P, Gude, C, Sadeghi-Tehran, P & Ivanov, T 2012, ARTOT: Autonomous Real-Time Object detection and Tracking by a moving camera. in Intelligent Systems (IS), 2012 6th IEEE International Conference. IEEE, pp. 446-452. https://doi.org/10.1109/IS.2012.6335175

APA

Angelov, P., Gude, C., Sadeghi-Tehran, P., & Ivanov, T. (2012). ARTOT: Autonomous Real-Time Object detection and Tracking by a moving camera. In Intelligent Systems (IS), 2012 6th IEEE International Conference (pp. 446-452). IEEE. https://doi.org/10.1109/IS.2012.6335175

Vancouver

Angelov P, Gude C, Sadeghi-Tehran P, Ivanov T. ARTOT: Autonomous Real-Time Object detection and Tracking by a moving camera. In Intelligent Systems (IS), 2012 6th IEEE International Conference. IEEE. 2012. p. 446-452 doi: 10.1109/IS.2012.6335175

Author

Angelov, Plamen ; Gude, Chirag ; Sadeghi-Tehran, Pouria et al. / ARTOT : Autonomous Real-Time Object detection and Tracking by a moving camera. Intelligent Systems (IS), 2012 6th IEEE International Conference. IEEE, 2012. pp. 446-452

Bibtex

@inproceedings{3cfc980e418747678a15d1669a5e86f8,
title = "ARTOT: Autonomous Real-Time Object detection and Tracking by a moving camera",
abstract = "A new approach to autonomously detect and track a moving object in a video captured by a moving camera (possibly mounted on a unmanned vehicle, UxV) is proposed in this paper. It is based on a combination of the recently introduced recursive density estimation (RDE) approach and the well-known scale invariant feature transformation (SIFT). The new approach involves building a model of the background using RDE in video sequences captured by a moving camera. RDE was robust in many videos with moving background in the absence of image registration (pixel position alignment). The output of RDE is a cluster of foreground pixels which can be associated with the object of interest. After the moving object is detected, the foreground pixels are enclosed in a rectangular region of interest (ROI). The approximate size and location of the rectangular region is then sent to the object tracking algorithm. The tracking algorithm uses the rectangular search area to detect and match SIFT keypoints across successive video frames. If and when the tracking fails, the RDE algorithm is started again to detect the moving object. The proposed algorithm does not require any human involvement and it operates in real-time. The tracking algorithm is also computationally efficient because only a small ROI is processed in each video frame. In the future we aim to substitute the SIFT approach with speeded-up robust features (SURF) for higher accuracy in tracking and for faster processing speed. Additionally, the case of multiple objects can be addressed using clustering in the spatial domain and is a subject of current research.",
keywords = "video analytics, RDE",
author = "Plamen Angelov and Chirag Gude and Pouria Sadeghi-Tehran and Tsvetan Ivanov",
note = "Selected as a best paper",
year = "2012",
month = sep,
doi = "10.1109/IS.2012.6335175",
language = "English",
isbn = "9781467322768",
pages = "446--452",
booktitle = "Intelligent Systems (IS), 2012 6th IEEE International Conference",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - ARTOT

T2 - Autonomous Real-Time Object detection and Tracking by a moving camera

AU - Angelov, Plamen

AU - Gude, Chirag

AU - Sadeghi-Tehran, Pouria

AU - Ivanov, Tsvetan

N1 - Selected as a best paper

PY - 2012/9

Y1 - 2012/9

N2 - A new approach to autonomously detect and track a moving object in a video captured by a moving camera (possibly mounted on a unmanned vehicle, UxV) is proposed in this paper. It is based on a combination of the recently introduced recursive density estimation (RDE) approach and the well-known scale invariant feature transformation (SIFT). The new approach involves building a model of the background using RDE in video sequences captured by a moving camera. RDE was robust in many videos with moving background in the absence of image registration (pixel position alignment). The output of RDE is a cluster of foreground pixels which can be associated with the object of interest. After the moving object is detected, the foreground pixels are enclosed in a rectangular region of interest (ROI). The approximate size and location of the rectangular region is then sent to the object tracking algorithm. The tracking algorithm uses the rectangular search area to detect and match SIFT keypoints across successive video frames. If and when the tracking fails, the RDE algorithm is started again to detect the moving object. The proposed algorithm does not require any human involvement and it operates in real-time. The tracking algorithm is also computationally efficient because only a small ROI is processed in each video frame. In the future we aim to substitute the SIFT approach with speeded-up robust features (SURF) for higher accuracy in tracking and for faster processing speed. Additionally, the case of multiple objects can be addressed using clustering in the spatial domain and is a subject of current research.

AB - A new approach to autonomously detect and track a moving object in a video captured by a moving camera (possibly mounted on a unmanned vehicle, UxV) is proposed in this paper. It is based on a combination of the recently introduced recursive density estimation (RDE) approach and the well-known scale invariant feature transformation (SIFT). The new approach involves building a model of the background using RDE in video sequences captured by a moving camera. RDE was robust in many videos with moving background in the absence of image registration (pixel position alignment). The output of RDE is a cluster of foreground pixels which can be associated with the object of interest. After the moving object is detected, the foreground pixels are enclosed in a rectangular region of interest (ROI). The approximate size and location of the rectangular region is then sent to the object tracking algorithm. The tracking algorithm uses the rectangular search area to detect and match SIFT keypoints across successive video frames. If and when the tracking fails, the RDE algorithm is started again to detect the moving object. The proposed algorithm does not require any human involvement and it operates in real-time. The tracking algorithm is also computationally efficient because only a small ROI is processed in each video frame. In the future we aim to substitute the SIFT approach with speeded-up robust features (SURF) for higher accuracy in tracking and for faster processing speed. Additionally, the case of multiple objects can be addressed using clustering in the spatial domain and is a subject of current research.

KW - video analytics

KW - RDE

U2 - 10.1109/IS.2012.6335175

DO - 10.1109/IS.2012.6335175

M3 - Conference contribution/Paper

SN - 9781467322768

SP - 446

EP - 452

BT - Intelligent Systems (IS), 2012 6th IEEE International Conference

PB - IEEE

ER -