Abstract
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.
Highlights
Wind power is rapidly emerging as a viable green energy alternative to fossil fuel.Wind farms installations that are needed to generate electricity from wind power can interfere with bird migrations—for example, birds can perish upon collision with wind turbines
This suggests that background subtraction based bird detection model is unable to deal with settings where birds are viewed against a dynamic background
This paper tackles the problem of bird detection in grayscale videos captured by cameras mounted around wind turbines
Summary
Wind power is rapidly emerging as a viable green energy alternative to fossil fuel.Wind farms installations that are needed to generate electricity from wind power can interfere with bird migrations—for example, birds can perish upon collision with wind turbines. Accurate bird detection has a big impact on the design of collision avoidance systems in wind farms These systems may include pulsing lights when birds are flying near the turbines [2], or lower frequencies of sound [3]. Bird counting can be improved based on the used detection method This process is important in order to predict birds migration changes [4]. Within this context, in this paper we develop a deep learning based approach for detecting birds flying around wind turbines. We conclude that background subtraction based bird detection method is unable to deal with changes in background. This method generates a lot of false positives. In reality there are only three birds present in the image and all of them were correctly detected using Model 3 as in Figure 7 (right)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
