Next Article in Journal
On a Variational and Convex Model of the Blake–Zisserman Type for Segmentation of Low-Contrast and Piecewise Smooth Images
Previous Article in Journal
Fast Fiber Orientation Estimation in Diffusion MRI from kq-Space Sampling and Anatomical Priors
Article

A Temporal Boosted YOLO-Based Model for Birds Detection around Wind Farms

by 1,*,†, 2,†, 3,† and 1,†
1
Department of Electronics Design, Mid Sweden University, Holmgatan 10, 85170 Sundsvall, Sweden
2
Department of Science and Technology, Linköping University, 58183 Linköping, Sweden
3
Faculty of Science, University of Ontario Institute of Technology, Oshawa, ON L1G 0C5, Canada
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Academic Editors: Petra Gomez-Krämer, Joseph Chazalon and Muhammad Muzzamil Luqman
J. Imaging 2021, 7(11), 227; https://doi.org/10.3390/jimaging7110227
Received: 29 August 2021 / Revised: 7 October 2021 / Accepted: 22 October 2021 / Published: 27 October 2021
(This article belongs to the Special Issue Mobile Camera-Based Image and Video Processing)
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. View Full-Text
Keywords: bird detection; wind farms monitoring; sky surveillance; background subtraction; YOLOv4 bird detection; wind farms monitoring; sky surveillance; background subtraction; YOLOv4
Show Figures

Figure 1

MDPI and ACS Style

Alqaysi, H.; Fedorov, I.; Qureshi, F.Z.; O’Nils, M. A Temporal Boosted YOLO-Based Model for Birds Detection around Wind Farms. J. Imaging 2021, 7, 227. https://doi.org/10.3390/jimaging7110227

AMA Style

Alqaysi H, Fedorov I, Qureshi FZ, O’Nils M. A Temporal Boosted YOLO-Based Model for Birds Detection around Wind Farms. Journal of Imaging. 2021; 7(11):227. https://doi.org/10.3390/jimaging7110227

Chicago/Turabian Style

Alqaysi, Hiba, Igor Fedorov, Faisal Z. Qureshi, and Mattias O’Nils. 2021. "A Temporal Boosted YOLO-Based Model for Birds Detection around Wind Farms" Journal of Imaging 7, no. 11: 227. https://doi.org/10.3390/jimaging7110227

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop