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

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 pro...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hiba Alqaysi, Igor Fedorov, Faisal Z. Qureshi, Mattias O’Nils
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	bird detection wind farms monitoring sky surveillance background subtraction YOLOv4 Photography TR1-1050 Computer applications to medicine. Medical informatics R858-859.7 Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/9539677c7e0a466589e586a994ce1c84
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9539677c7e0a466589e586a994ce1c84
record_format	dspace
spelling	oai:doaj.org-article:9539677c7e0a466589e586a994ce1c842021-11-25T18:03:26ZA Temporal Boosted YOLO-Based Model for Birds Detection around Wind Farms10.3390/jimaging71102272313-433Xhttps://doaj.org/article/9539677c7e0a466589e586a994ce1c842021-10-01T00:00:00Zhttps://www.mdpi.com/2313-433X/7/11/227https://doaj.org/toc/2313-433XObject 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.Hiba AlqaysiIgor FedorovFaisal Z. QureshiMattias O’NilsMDPI AGarticlebird detectionwind farms monitoringsky surveillancebackground subtractionYOLOv4PhotographyTR1-1050Computer applications to medicine. Medical informaticsR858-859.7Electronic computers. Computer scienceQA75.5-76.95ENJournal of Imaging, Vol 7, Iss 227, p 227 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	bird detection wind farms monitoring sky surveillance background subtraction YOLOv4 Photography TR1-1050 Computer applications to medicine. Medical informatics R858-859.7 Electronic computers. Computer science QA75.5-76.95
spellingShingle	bird detection wind farms monitoring sky surveillance background subtraction YOLOv4 Photography TR1-1050 Computer applications to medicine. Medical informatics R858-859.7 Electronic computers. Computer science QA75.5-76.95 Hiba Alqaysi Igor Fedorov Faisal Z. Qureshi Mattias O’Nils A Temporal Boosted YOLO-Based Model for Birds Detection around Wind Farms
description	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.
format	article
author	Hiba Alqaysi Igor Fedorov Faisal Z. Qureshi Mattias O’Nils
author_facet	Hiba Alqaysi Igor Fedorov Faisal Z. Qureshi Mattias O’Nils
author_sort	Hiba Alqaysi
title	A Temporal Boosted YOLO-Based Model for Birds Detection around Wind Farms
title_short	A Temporal Boosted YOLO-Based Model for Birds Detection around Wind Farms
title_full	A Temporal Boosted YOLO-Based Model for Birds Detection around Wind Farms
title_fullStr	A Temporal Boosted YOLO-Based Model for Birds Detection around Wind Farms
title_full_unstemmed	A Temporal Boosted YOLO-Based Model for Birds Detection around Wind Farms
title_sort	temporal boosted yolo-based model for birds detection around wind farms
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/9539677c7e0a466589e586a994ce1c84
work_keys_str_mv	AT hibaalqaysi atemporalboostedyolobasedmodelforbirdsdetectionaroundwindfarms AT igorfedorov atemporalboostedyolobasedmodelforbirdsdetectionaroundwindfarms AT faisalzqureshi atemporalboostedyolobasedmodelforbirdsdetectionaroundwindfarms AT mattiasonils atemporalboostedyolobasedmodelforbirdsdetectionaroundwindfarms AT hibaalqaysi temporalboostedyolobasedmodelforbirdsdetectionaroundwindfarms AT igorfedorov temporalboostedyolobasedmodelforbirdsdetectionaroundwindfarms AT faisalzqureshi temporalboostedyolobasedmodelforbirdsdetectionaroundwindfarms AT mattiasonils temporalboostedyolobasedmodelforbirdsdetectionaroundwindfarms
_version_	1718411694717272064

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

Ejemplares similares