Effective and Efficient Detection of Moving Targets from a UAV's Camera

Sara Minaeian, Jian Liu, Young-Jun Son

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Accurate and fast detection of the moving targets from a moving camera are an important yet challenging problem, especially when the computational resources are limited. In this paper, we propose an effective, efficient, and robust method to accurately detect and segment multiple independently moving foreground targets from a video sequence taken by a monocular moving camera [e.g., onboard an unmanned aerial vehicle (UAV)]. Our proposed method advances the existing methods in a number of ways, where: 1) camera motion is estimated through tracking background keypoints using pyramidal Lucas-Kanade at every detection interval, for efficiency; 2) foreground segmentation is applied by integrating a local motion history function with spatio-Temporal differencing over a sliding window for detecting multiple moving targets, while the perspective homography is used at image registration for effectiveness; and 3) the detection interval is adjusted dynamically based on a rule-of-Thumb technique and considering camera setup parameters for robustness. The proposed method has been tested on a variety of scenarios using a UAV camera, as well as publically available data sets. Based on the reported results and through comparison with the existing methods, the accuracy of the proposed method in detecting multiple moving targets as well as its capability for real-Time implementation has been successfully demonstrated. Our method is also robustly applicable to ground-level cameras for the ITS applications, as confirmed by the experimental results. More specifically, the proposed method shows promising performance compared with the literature in terms of quantitative metrics, while the run-Time measures are significantly improved for real-Time implementation.

Original languageEnglish (US)
Article number8248663
Pages (from-to)497-506
Number of pages10
JournalIEEE Transactions on Intelligent Transportation Systems
Volume19
Issue number2
DOIs
StatePublished - Feb 1 2018

Fingerprint

Unmanned aerial vehicles (UAV)
Cameras
Image registration

Keywords

  • Effectiveness
  • image motion analysis
  • object detection
  • robustness
  • unmanned aerial vehicles

ASJC Scopus subject areas

  • Automotive Engineering
  • Mechanical Engineering
  • Computer Science Applications

Cite this

Effective and Efficient Detection of Moving Targets from a UAV's Camera. / Minaeian, Sara; Liu, Jian; Son, Young-Jun.

In: IEEE Transactions on Intelligent Transportation Systems, Vol. 19, No. 2, 8248663, 01.02.2018, p. 497-506.

Research output: Contribution to journalArticle

@article{8322db42dace45d1824775bfa94122d4,
title = "Effective and Efficient Detection of Moving Targets from a UAV's Camera",
abstract = "Accurate and fast detection of the moving targets from a moving camera are an important yet challenging problem, especially when the computational resources are limited. In this paper, we propose an effective, efficient, and robust method to accurately detect and segment multiple independently moving foreground targets from a video sequence taken by a monocular moving camera [e.g., onboard an unmanned aerial vehicle (UAV)]. Our proposed method advances the existing methods in a number of ways, where: 1) camera motion is estimated through tracking background keypoints using pyramidal Lucas-Kanade at every detection interval, for efficiency; 2) foreground segmentation is applied by integrating a local motion history function with spatio-Temporal differencing over a sliding window for detecting multiple moving targets, while the perspective homography is used at image registration for effectiveness; and 3) the detection interval is adjusted dynamically based on a rule-of-Thumb technique and considering camera setup parameters for robustness. The proposed method has been tested on a variety of scenarios using a UAV camera, as well as publically available data sets. Based on the reported results and through comparison with the existing methods, the accuracy of the proposed method in detecting multiple moving targets as well as its capability for real-Time implementation has been successfully demonstrated. Our method is also robustly applicable to ground-level cameras for the ITS applications, as confirmed by the experimental results. More specifically, the proposed method shows promising performance compared with the literature in terms of quantitative metrics, while the run-Time measures are significantly improved for real-Time implementation.",
keywords = "Effectiveness, image motion analysis, object detection, robustness, unmanned aerial vehicles",
author = "Sara Minaeian and Jian Liu and Young-Jun Son",
year = "2018",
month = "2",
day = "1",
doi = "10.1109/TITS.2017.2782790",
language = "English (US)",
volume = "19",
pages = "497--506",
journal = "IEEE Transactions on Intelligent Transportation Systems",
issn = "1524-9050",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Effective and Efficient Detection of Moving Targets from a UAV's Camera

AU - Minaeian, Sara

AU - Liu, Jian

AU - Son, Young-Jun

PY - 2018/2/1

Y1 - 2018/2/1

N2 - Accurate and fast detection of the moving targets from a moving camera are an important yet challenging problem, especially when the computational resources are limited. In this paper, we propose an effective, efficient, and robust method to accurately detect and segment multiple independently moving foreground targets from a video sequence taken by a monocular moving camera [e.g., onboard an unmanned aerial vehicle (UAV)]. Our proposed method advances the existing methods in a number of ways, where: 1) camera motion is estimated through tracking background keypoints using pyramidal Lucas-Kanade at every detection interval, for efficiency; 2) foreground segmentation is applied by integrating a local motion history function with spatio-Temporal differencing over a sliding window for detecting multiple moving targets, while the perspective homography is used at image registration for effectiveness; and 3) the detection interval is adjusted dynamically based on a rule-of-Thumb technique and considering camera setup parameters for robustness. The proposed method has been tested on a variety of scenarios using a UAV camera, as well as publically available data sets. Based on the reported results and through comparison with the existing methods, the accuracy of the proposed method in detecting multiple moving targets as well as its capability for real-Time implementation has been successfully demonstrated. Our method is also robustly applicable to ground-level cameras for the ITS applications, as confirmed by the experimental results. More specifically, the proposed method shows promising performance compared with the literature in terms of quantitative metrics, while the run-Time measures are significantly improved for real-Time implementation.

AB - Accurate and fast detection of the moving targets from a moving camera are an important yet challenging problem, especially when the computational resources are limited. In this paper, we propose an effective, efficient, and robust method to accurately detect and segment multiple independently moving foreground targets from a video sequence taken by a monocular moving camera [e.g., onboard an unmanned aerial vehicle (UAV)]. Our proposed method advances the existing methods in a number of ways, where: 1) camera motion is estimated through tracking background keypoints using pyramidal Lucas-Kanade at every detection interval, for efficiency; 2) foreground segmentation is applied by integrating a local motion history function with spatio-Temporal differencing over a sliding window for detecting multiple moving targets, while the perspective homography is used at image registration for effectiveness; and 3) the detection interval is adjusted dynamically based on a rule-of-Thumb technique and considering camera setup parameters for robustness. The proposed method has been tested on a variety of scenarios using a UAV camera, as well as publically available data sets. Based on the reported results and through comparison with the existing methods, the accuracy of the proposed method in detecting multiple moving targets as well as its capability for real-Time implementation has been successfully demonstrated. Our method is also robustly applicable to ground-level cameras for the ITS applications, as confirmed by the experimental results. More specifically, the proposed method shows promising performance compared with the literature in terms of quantitative metrics, while the run-Time measures are significantly improved for real-Time implementation.

KW - Effectiveness

KW - image motion analysis

KW - object detection

KW - robustness

KW - unmanned aerial vehicles

UR - http://www.scopus.com/inward/record.url?scp=85041170518&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041170518&partnerID=8YFLogxK

U2 - 10.1109/TITS.2017.2782790

DO - 10.1109/TITS.2017.2782790

M3 - Article

AN - SCOPUS:85041170518

VL - 19

SP - 497

EP - 506

JO - IEEE Transactions on Intelligent Transportation Systems

JF - IEEE Transactions on Intelligent Transportation Systems

SN - 1524-9050

IS - 2

M1 - 8248663

ER -