Application of Deep-Learning Methods to Bird Detection Using Unmanned Aerial Vehicle Imagery
Wild birds are monitored with the important objectives of identifying their habitats and estimating the size of their populations. Especially in the case of migratory bird, they are significantly recorded during specific periods of time to forecast any possible spread of animal disease such as avian...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/7/1651 |
| _version_ | 1811278120655781888 |
|---|---|
| author | Suk-Ju Hong Yunhyeok Han Sang-Yeon Kim Ah-Yeong Lee Ghiseok Kim |
| author_facet | Suk-Ju Hong Yunhyeok Han Sang-Yeon Kim Ah-Yeong Lee Ghiseok Kim |
| author_sort | Suk-Ju Hong |
| collection | DOAJ |
| description | Wild birds are monitored with the important objectives of identifying their habitats and estimating the size of their populations. Especially in the case of migratory bird, they are significantly recorded during specific periods of time to forecast any possible spread of animal disease such as avian influenza. This study led to the construction of deep-learning-based object-detection models with the aid of aerial photographs collected by an unmanned aerial vehicle (UAV). The dataset containing the aerial photographs includes diverse images of birds in various bird habitats and in the vicinity of lakes and on farmland. In addition, aerial images of bird decoys are captured to achieve various bird patterns and more accurate bird information. Bird detection models such as Faster Region-based Convolutional Neural Network (R-CNN), Region-based Fully Convolutional Network (R-FCN), Single Shot MultiBox Detector (SSD), Retinanet, and You Only Look Once (YOLO) were created and the performance of all models was estimated by comparing their computing speed and average precision. The test results show Faster R-CNN to be the most accurate and YOLO to be the fastest among the models. The combined results demonstrate that the use of deep-learning-based detection methods in combination with UAV aerial imagery is fairly suitable for bird detection in various environments. |
| first_indexed | 2024-04-13T00:28:58Z |
| format | Article |
| id | doaj.art-8ad24dea5f414de0996b3076310267b7 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T00:28:58Z |
| publishDate | 2019-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-8ad24dea5f414de0996b3076310267b72022-12-22T03:10:31ZengMDPI AGSensors1424-82202019-04-01197165110.3390/s19071651s19071651Application of Deep-Learning Methods to Bird Detection Using Unmanned Aerial Vehicle ImagerySuk-Ju Hong0Yunhyeok Han1Sang-Yeon Kim2Ah-Yeong Lee3Ghiseok Kim4Department of Biosystems and Biomaterials Science and Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, KoreaDepartment of Biosystems and Biomaterials Science and Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, KoreaDepartment of Biosystems and Biomaterials Science and Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, KoreaDepartment of Biosystems and Biomaterials Science and Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, KoreaDepartment of Biosystems and Biomaterials Science and Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, KoreaWild birds are monitored with the important objectives of identifying their habitats and estimating the size of their populations. Especially in the case of migratory bird, they are significantly recorded during specific periods of time to forecast any possible spread of animal disease such as avian influenza. This study led to the construction of deep-learning-based object-detection models with the aid of aerial photographs collected by an unmanned aerial vehicle (UAV). The dataset containing the aerial photographs includes diverse images of birds in various bird habitats and in the vicinity of lakes and on farmland. In addition, aerial images of bird decoys are captured to achieve various bird patterns and more accurate bird information. Bird detection models such as Faster Region-based Convolutional Neural Network (R-CNN), Region-based Fully Convolutional Network (R-FCN), Single Shot MultiBox Detector (SSD), Retinanet, and You Only Look Once (YOLO) were created and the performance of all models was estimated by comparing their computing speed and average precision. The test results show Faster R-CNN to be the most accurate and YOLO to be the fastest among the models. The combined results demonstrate that the use of deep-learning-based detection methods in combination with UAV aerial imagery is fairly suitable for bird detection in various environments.https://www.mdpi.com/1424-8220/19/7/1651deep learningconvolutional neural networksunmanned aerial vehiclebird detection |
| spellingShingle | Suk-Ju Hong Yunhyeok Han Sang-Yeon Kim Ah-Yeong Lee Ghiseok Kim Application of Deep-Learning Methods to Bird Detection Using Unmanned Aerial Vehicle Imagery Sensors deep learning convolutional neural networks unmanned aerial vehicle bird detection |
| title | Application of Deep-Learning Methods to Bird Detection Using Unmanned Aerial Vehicle Imagery |
| title_full | Application of Deep-Learning Methods to Bird Detection Using Unmanned Aerial Vehicle Imagery |
| title_fullStr | Application of Deep-Learning Methods to Bird Detection Using Unmanned Aerial Vehicle Imagery |
| title_full_unstemmed | Application of Deep-Learning Methods to Bird Detection Using Unmanned Aerial Vehicle Imagery |
| title_short | Application of Deep-Learning Methods to Bird Detection Using Unmanned Aerial Vehicle Imagery |
| title_sort | application of deep learning methods to bird detection using unmanned aerial vehicle imagery |
| topic | deep learning convolutional neural networks unmanned aerial vehicle bird detection |
| url | https://www.mdpi.com/1424-8220/19/7/1651 |
| work_keys_str_mv | AT sukjuhong applicationofdeeplearningmethodstobirddetectionusingunmannedaerialvehicleimagery AT yunhyeokhan applicationofdeeplearningmethodstobirddetectionusingunmannedaerialvehicleimagery AT sangyeonkim applicationofdeeplearningmethodstobirddetectionusingunmannedaerialvehicleimagery AT ahyeonglee applicationofdeeplearningmethodstobirddetectionusingunmannedaerialvehicleimagery AT ghiseokkim applicationofdeeplearningmethodstobirddetectionusingunmannedaerialvehicleimagery |