TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Deep learning–based automatic bird identification system for offshore wind farms

Tutkimustuotosvertaisarvioitu

Standard

Deep learning–based automatic bird identification system for offshore wind farms. / Niemi, Juha; Tanttu, Juha T.

julkaisussa: WIND ENERGY, Vuosikerta 23, Nro 6, 2020, s. 1394-1407.

Tutkimustuotosvertaisarvioitu

Harvard

APA

Vancouver

Author

Niemi, Juha ; Tanttu, Juha T. / Deep learning–based automatic bird identification system for offshore wind farms. Julkaisussa: WIND ENERGY. 2020 ; Vuosikerta 23, Nro 6. Sivut 1394-1407.

Bibtex - Lataa

@article{7b497b04207e4c16aa8a3e95136b4c8e,
title = "Deep learning–based automatic bird identification system for offshore wind farms",
abstract = "Practical deterrent methods are needed to prevent collisions between birds and wind turbine blades for offshore wind farms. It is improbable that a single deterrent method would work for all bird species in a given area. An automatic bird identification system is required in order to develop bird species-level deterrent methods. This system is the first and necessary part of the entirety that is eventually able to automatically monitor bird movements, identify bird species, and launch deterrent measures. A prototype system has been built on Finnish west coast.In the proposed system, a separate radar system detects birds and provides WGS84 coordinates to a steering system of a camera. The steering system consists of a motorized video head and our software to control it. The steering system tracks flying birds in order to capture series of images by a digital single-lens reflex camera. Classification is based on these images, and it is implemented by convolutional neural network trained with a deep learning algorithm. We applied to the images our data augmentation method, in which images are rotated and converted into different color temperatures. The results indicate that the proposed system has good performance to identify bird species in the test area. Aiming accuracy for the video head was 88.91 {\%}. Image classification performance as true positive rate was 0.8688.",
keywords = "machine learning, deep learning, convolutional neural networks, image classification, intelligent surveillance systems, wind farms",
author = "Juha Niemi and Tanttu, {Juha T.}",
year = "2020",
doi = "10.1002/we.2492",
language = "English",
volume = "23",
pages = "1394--1407",
journal = "WIND ENERGY",
issn = "1095-4244",
publisher = "Wiley",
number = "6",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - Deep learning–based automatic bird identification system for offshore wind farms

AU - Niemi, Juha

AU - Tanttu, Juha T.

PY - 2020

Y1 - 2020

N2 - Practical deterrent methods are needed to prevent collisions between birds and wind turbine blades for offshore wind farms. It is improbable that a single deterrent method would work for all bird species in a given area. An automatic bird identification system is required in order to develop bird species-level deterrent methods. This system is the first and necessary part of the entirety that is eventually able to automatically monitor bird movements, identify bird species, and launch deterrent measures. A prototype system has been built on Finnish west coast.In the proposed system, a separate radar system detects birds and provides WGS84 coordinates to a steering system of a camera. The steering system consists of a motorized video head and our software to control it. The steering system tracks flying birds in order to capture series of images by a digital single-lens reflex camera. Classification is based on these images, and it is implemented by convolutional neural network trained with a deep learning algorithm. We applied to the images our data augmentation method, in which images are rotated and converted into different color temperatures. The results indicate that the proposed system has good performance to identify bird species in the test area. Aiming accuracy for the video head was 88.91 %. Image classification performance as true positive rate was 0.8688.

AB - Practical deterrent methods are needed to prevent collisions between birds and wind turbine blades for offshore wind farms. It is improbable that a single deterrent method would work for all bird species in a given area. An automatic bird identification system is required in order to develop bird species-level deterrent methods. This system is the first and necessary part of the entirety that is eventually able to automatically monitor bird movements, identify bird species, and launch deterrent measures. A prototype system has been built on Finnish west coast.In the proposed system, a separate radar system detects birds and provides WGS84 coordinates to a steering system of a camera. The steering system consists of a motorized video head and our software to control it. The steering system tracks flying birds in order to capture series of images by a digital single-lens reflex camera. Classification is based on these images, and it is implemented by convolutional neural network trained with a deep learning algorithm. We applied to the images our data augmentation method, in which images are rotated and converted into different color temperatures. The results indicate that the proposed system has good performance to identify bird species in the test area. Aiming accuracy for the video head was 88.91 %. Image classification performance as true positive rate was 0.8688.

KW - machine learning

KW - deep learning

KW - convolutional neural networks

KW - image classification

KW - intelligent surveillance systems

KW - wind farms

U2 - 10.1002/we.2492

DO - 10.1002/we.2492

M3 - Article

VL - 23

SP - 1394

EP - 1407

JO - WIND ENERGY

JF - WIND ENERGY

SN - 1095-4244

IS - 6

ER -