Mid Sweden University

miun.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Cost Optimization of Volumetric Surveillance for Sky Monitoring: Towards Flying Object Detection and Positioning
Mid Sweden University, Faculty of Science, Technology and Media, Department of Electronics Design.ORCID iD: 0000-0001-9319-1413
2022 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Unlike surface surveillance, volumetric monitoring deals with three-dimensional target space and moving objects within it. In sky monitoring, objects fly within outdoor and often remote volumes, such as wind farms and airport runways. Therefore, multiple cameras should be implemented to monitor these volumes and analyze flying activities.

Due to that, challenges in designing and deploying volumetric surveillance systems for these applications arise. These include configuring the multi-camera node placement, coverage, cost, and the system's ability to detect and position flying objects.

The research in this dissertation focuses on three aspects to optimize volumetric surveillance systems in sky monitoring applications. First, the node placement and coverage should be considered in accordance with the monitoring constraints. Also, the node architecture should be configured to minimize the design cost and maximize the coverage. Last, the system should detect small flying objects with good accuracy.

Placing the multi-camera nodes in a hexagonal pattern while allowing overlap between adjacent nodes optimizes the placement. The inclusion of monitoring constraints like monitoring altitude and detection pixel resolution influences the node design. Furthermore, presented results show that modeling the multi-camera nodes as a cylinder rather than a hemisphere minimizes the cost of each node. The design exploration in this thesis provides a method to minimize the node cost based on defined design constraints. It also maximizes the coverage in terms of the number of square meters per dollar. 

Surveillance systems for sky monitoring should be able to detect and position flying objects. Therefore, two new annotated datasets were introduced that can be used for developing in-flight birds detection methods. The datasets were collected by Mid Sweden University at two locations in Denmark. A YOLOv4-based model for birds detection in 4k grayscale videos captured in wind farms is developed. The model overcomes the problem of detecting small objects in dynamic background, and it improves detection accuracy through tiling and temporal information incorporation, compared to the standard YOLOv4 and background subtraction.

Place, publisher, year, edition, pages
Sundsvall: Mid Sweden University , 2022. , p. 54
Series
Mid Sweden University doctoral thesis, ISSN 1652-893X ; 358
Keywords [en]
Electronics, image processing, deep learning, YOLOv4, smart cameras
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
URN: urn:nbn:se:miun:diva-43945ISBN: 978-91-89341-36-4 (print)OAI: oai:DiVA.org:miun-43945DiVA, id: diva2:1619582
Public defence
2022-01-12, C312, Holmgatan 10, 851 70, Sundsvall, 09:00 (English)
Opponent
Supervisors
Available from: 2021-12-14 Created: 2021-12-13 Last updated: 2021-12-14Bibliographically approved
List of papers
1. Evaluating Coverage Effectiveness of Multi-Camera Domes Placement for Volumetric Surveillance
Open this publication in new window or tab >>Evaluating Coverage Effectiveness of Multi-Camera Domes Placement for Volumetric Surveillance
2017 (English)In: ICDSC 2017 Proceedings of the 11th International Conference on Distributed Smart Cameras, New York, NY, USA: Association for Computing Machinery (ACM), 2017, Vol. F132201, p. 49-54Conference paper, Published paper (Refereed)
Abstract [en]

Multi-camera dome is composed of a number of cameras arranged to monitor a half sphere of the sky. Designing a network of multi-camera domes can be used to monitor flying activities in open large area, such as birds' activities in wind parks. In this paper, we present a method for evaluating the coverage effectiveness of the multi-camera domes placement in such areas. We used GPS trajectories of free flying birds over an area of 9 km2 to analyze coverage effectiveness of randomly placed domes. The analysis is based on three criteria namely, detection, positioning and the maximum resolution captured. The developed method can be used to evaluate results of designing and optimizing dome placement algorithms for volumetric monitoring systems in order to achieve maximum coverage.

Place, publisher, year, edition, pages
New York, NY, USA: Association for Computing Machinery (ACM), 2017
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:miun:diva-32311 (URN)10.1145/3131885.3131916 (DOI)000716998900008 ()2-s2.0-85038865753 (Scopus ID)978-1-4503-5487-5 (ISBN)
Conference
The 11th International Conference on Distributed Smart Cameras (ICDSC), Stanford University, Stanford; United States; 5 September 2017 through 7 September 2017
Projects
SMART (Smarta system och tjänster för ett effektivt och innovativt samhälle)
Available from: 2017-12-07 Created: 2017-12-07 Last updated: 2022-06-02Bibliographically approved
2. Full Coverage Optimization for Multi Camera Dome Placement in Volumetric Monitoring
Open this publication in new window or tab >>Full Coverage Optimization for Multi Camera Dome Placement in Volumetric Monitoring
2018 (English)In: ACM International Conference Proceeding Series, New York, NY, USA: ACM Digital Library, 2018, article id Article No. 2Conference paper, Published paper (Refereed)
Abstract [en]

Volumetric monitoring can be challenging due to having a 3D target space and moving objects within it. Multi camera dome is proposed to provide a hemispherical coverage of the 3D space around it. This paper introduces a method that optimizes multi camera placement for full coverage in volumetric monitoring system. Camera dome placement is modeled in a volume by adapting the hexagonal packing of circles to provide full coverage at a given height, and 100% detection of flying objects within it. The coverage effectiveness of different placement configurations was assessed using an evaluation environment. The proposed placement is applicable in designing and deploying surveillance systems for remote outdoor areas, such as sky monitoring in wind farms and airport runways in order to record and analyze flying activities.

Place, publisher, year, edition, pages
New York, NY, USA: ACM Digital Library, 2018
Keywords
Volumetric surveillance, sky monitoring, camera dome, placement optimization.
National Category
Engineering and Technology
Identifiers
urn:nbn:se:miun:diva-34589 (URN)10.1145/3243394.3243690 (DOI)000455840700002 ()2-s2.0-85056662761 (Scopus ID)978-1-4503-6511-6 (ISBN)
Conference
12th International Conference on Distributed Smart Cameras, ICDSC 2018; Eindhoven; Netherlands; 3 September 2018 through 4 September 2018
Projects
SMART (Smarta system och tjänster för ett effektivt och innovativt samhälle)
Available from: 2018-10-02 Created: 2018-10-02 Last updated: 2021-12-13Bibliographically approved
3. Design Exploration of Multi-Camera Dome
Open this publication in new window or tab >>Design Exploration of Multi-Camera Dome
Show others...
2019 (English)In: ICDSC 2019 Proceedings of the 13th International Conference on Distributed Smart Cameras, New York, NY: ACM Digital Library, 2019, article id Article No. 7aConference paper, Published paper (Refereed)
Abstract [en]

Visual monitoring systems employ distributed smart cameras toeffectively cover a given area satisfying specific objectives. Thechoice of camera sensors and lenses and their deployment affectsdesign cost, accuracy of the monitoring system and the ability toposition objects within the monitored area. Design cost can bereduced by investigating deployment topology such as groupingcameras together to form a dome at a node and optimize it formonitoring constraints. The constraints may include coverage area,number of cameras that can be integrated in a node and pixelresolution at a given distance. This paper presents a method foroptimizing the design cost of multi-camera dome by analyzing tradeoffsbetween monitoring constraints. The proposed method can beused to reduce monitoring cost while fulfilling design objectives.Results show how to increase coverage area for a given cost byrelaxing requirements on design constraints. Multi-camera domescan be used in sky monitoring applications such as monitoring windparks and remote air-traffic control of airports where all-round fieldof view about a point is required to monitor.

Place, publisher, year, edition, pages
New York, NY: ACM Digital Library, 2019
Keywords
Distributed smart cameras, sky monitoring, volumetric surveillance.
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:miun:diva-36762 (URN)10.1145/3349801.3349808 (DOI)000519116500007 ()2-s2.0-85073333209 (Scopus ID)978-1-4503-7189-6 (ISBN)
Conference
13th InternationalConference on Distributed Smart Cameras (ICDSC 2019), Trento, Italy, 9-11 September, 2019
Projects
SMART
Available from: 2019-07-29 Created: 2019-07-29 Last updated: 2021-12-13Bibliographically approved
4. Cost Optimized Design of Multi-Camera Domefor Volumetric Surveillance
Open this publication in new window or tab >>Cost Optimized Design of Multi-Camera Domefor Volumetric Surveillance
Show others...
2021 (English)In: IEEE Sensors Journal, ISSN 1530-437X, E-ISSN 1558-1748, Vol. 21, no 3, p. 3730-3737Article in journal (Refereed) Published
Abstract [en]

A multi-camera dome consists of number ofcameras arranged in layers to monitor a hemisphere aroundits center. In volumetric surveillance,a 3D space is required tobemonitoredwhich can be achievedby implementing numberof multi-camera domes. A monitoring height is consideredas a constraint to ensure full coverage of the space belowit. Accordingly, the multi-camera dome can be redesignedinto a cylinder such that each of its multiple layers hasdifferent coverage radius. Minimum monitoring constraintsshould be met at all layers. This work is presenting a costoptimized design for the multi-camera dome that maximizesits coverage. The cost per node and number of squaremetersper dollar of multiple configurations are calculated using asearch space of cameras and considering a set of monitoring and coverage constraints. The proposed design is costoptimized per node and provides more coverage as compared to the hemispherical multi-camera dome.

Keywords
Camera node design, camera deployment, camera dome, cost optimization, multi-camera dome, volumetric surveillance, 3D monitoring, multiple-sensor systems
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:miun:diva-40339 (URN)10.1109/JSEN.2020.3025359 (DOI)000678186800029 ()2-s2.0-85099242881 (Scopus ID)
Available from: 2020-10-27 Created: 2020-10-27 Last updated: 2021-12-13Bibliographically approved
5. A temporal boosted yolo-based model for birds detection around wind farms
Open this publication in new window or tab >>A temporal boosted yolo-based model for birds detection around wind farms
2021 (English)In: Journal of Imaging, ISSN 2313-433X, Vol. 7, no 11, article id 227Article in journal (Refereed) Published
Abstract [en]

Object detection for sky surveillance is a challenging problem due to having small objects in a large volume and a constantly changing background which requires high resolution frames. For example, detecting flying birds in wind farms to prevent their collision with the wind turbines. This paper proposes a YOLOv4-based ensemble model for bird detection in grayscale videos captured around wind turbines in wind farms. In order to tackle this problem, we introduce two datasets—(1) Klim and (2) Skagen—collected at two locations in Denmark. We use Klim training set to train three increasingly capable YOLOv4 based models. Model 1 uses YOLOv4 trained on the Klim dataset, Model 2 introduces tiling to improve small bird detection, and the last model uses tiling and temporal stacking and achieves the best mAP values on both Klim and Skagen datasets. We used this model to set up an ensemble detector, which further improves mAP values on both datasets. The three models achieve testing mAP values of 82%, 88%, and 90% on the Klim dataset. mAP values for Model 1 and Model 3 on the Skagen dataset are 60% and 92%. Improving object detection accuracy could mitigate birds’ mortality rate by choosing the locations for such establishment and the turbines location. It can also be used to improve the collision avoidance systems used in wind energy facilities. 

Keywords
Background subtraction, Bird detection, Sky surveillance, Wind farms monitoring, YOLOv4
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:miun:diva-43641 (URN)10.3390/jimaging7110227 (DOI)2-s2.0-85118110304 (Scopus ID)
Available from: 2021-11-09 Created: 2021-11-09 Last updated: 2021-12-13

Open Access in DiVA

fulltext(31842 kB)560 downloads
File information
File name FULLTEXT01.pdfFile size 31842 kBChecksum SHA-512
413ad4b3fb5d8fd472daf8d374f4b22a9cc07d6487670c15c915b9fb7914bc9287cc7b1ac32f475c413a826f07d9a387cfad42206de184f2e55f7275ee25bfa6
Type fulltextMimetype application/pdf

Authority records

Alqaysi, Hiba

Search in DiVA

By author/editor
Alqaysi, Hiba
By organisation
Department of Electronics Design
Other Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 560 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 681 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf