基于卷积神经网络的无人机遥感影像水鸟自动识别
作者:
作者单位:

1.北京林业大学生态与自然保护学院 北京 100083;2.国家林业和草原局华东调查规划院 杭州 310019

作者简介:

林海,男,硕士研究生;研究方向:自然保护区学;E-mail:sclh45@bjfu.edu.cn。

基金项目:

国家自然科学基金项目(No. 32171545);


Waterbirds Auto-Detection in Unmanned Aerial Vehicle Remote Sensing Image Base on Convolutional Neural Network
Author:
Affiliation:

1.School of Ecology and Nature Conservation, Beijing Forestry University, Beijing 100083; 2.East China Forest Inventory and Planning Institute, Hangzhou 310019, China

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [24]
  • |
  • 相似文献
  • | | |
  • 文章评论
    摘要:

    水鸟监测是了解水鸟种群和分布动态、开展水鸟和湿地保护的基础,但该活动耗时耗力。近年来,随着无人机遥感技术的发展,使用小型无人机获得高分辨率的水鸟遥感影像已经成为可能;与此同时,卷积神经网络提供了一种快速识别无人机遥感图像中的鸟类的方法。我们尝试结合两种技术,使用卷积神经网络Mask R-CNN与YOLOv3识别湖南西洞庭湖国家级自然保护区无人机遥感影像中的大型水鸟,取得了良好的效果:模型检测拍摄到的鸭属鸟类,包括绿翅鸭(Anas crecca)和罗纹鸭(A. falcata)的结果平均精度达到0.93,精度达到90.83%,召回率达到93%;检测小天鹅(Cygnus columbianus)的结果平均精度达到0.91,精度达到84.38%,召回率达到84.00%。结果表明,将无人机遥感技术与卷积神经网络结合,可以快速统计水鸟数量,在种群监测工作中具有应用潜力。

    Abstract:

    [Objectives] Waterbird monitoring plays a crucial role in understanding population dynamics and guiding conservation efforts, but it has traditionally been a time-consuming process. In this study, our objective is to integrate unmanned aerial vehicle (UAV) remote sensing with convolutional neural networks (CNN) to achieve rapid and accurate estimation of waterbird populations. [Methods] We employed the DJI Mavic 2 Zoom UAV to capture high-resolution remote sensing images in the West Dongting Lake National Nature Reserve in Hunan. The UAV was flown at an altitude of 75 m, with its camera positioned in a vertically downward-facing orientation. We obtained images with a ground resolution of 1.2 cm/pixel, Table 1 displays the waterbirds captured in the images. We selected 503 images to construct a dataset, including two categories:Anas crecca/A. falcata and Cygnus columbianus, with 3 778 and 395 samples respectively. The dataset has several training sets of different sizes (Table 2) and a validation set of 3 032 samples. For each training set, we independently developed Mask R-CNN and YOLOv3 models, evaluating their performance using the validation set. Evaluation metrics include average precision, recall, precision, and F1-score. [Results] When identifying A. crecca/A. falcata, Mask R-CNN model achieved a recall rate of 93.00% and a precision of 90.83% (Table 4, Fig. 4), while the YOLOv3 model achieved a recall rate of 93.00% and a precision of 88.79% (Table 5, Fig. 5). After reaching 178 ind for A. crecca/A. falcata in the training set, further augmentation did not result in a significant improvement in the performance of both models. When identifying C. columbianus, the performance of both models improved with an increase in the size of the training set. The Mask R-CNN model achieved a recall rate of 84.00% and a precision of 84.38% (Table 6, Fig. 6), while the YOLOv3 model achieved a recall rate of 90.00% and a precision of 81.69% (Table 7, Fig. 7). The Mask R-CNN model detected images at a speed of approximately 12 images/s, while the YOLOv3 model detected images at a speed of 20﹣30 images/s. [Conclusion] Our study proposes a potential solution for efficient and accurate waterbird population monitoring in natural habitats. Our models demonstrated high accuracy in identifying A. crecca/A. falcata, the recognition accuracy difference between Mask R-CNN and YOLO was minimal. Remarkably, by integrating UAV remote sensing with CNN, our approach demonstrates the potential for training highly efficient and accurate waterbird identification models with minimal annotated data—perhaps requiring fewer than 250 ind per waterbird species, as suggested by our results.

    参考文献
    Chen K, Wang J Q, Pang J M, et al. 2019. MMDetection:open MMLab detection toolbox and benchmark. [EB/OL]. [2023-05- 05]. http://arxiv.org/abs/1906.07155.
    Díaz-Delgado R, Ma?ez M, Martínez A, et al. 2017. Using UAVs to map aquatic bird colonies // Díaz-Delgado R, Lucas R, Hurford C. The Roles of Remote Sensing in Nature Conservation. Cham:Springer, 277–291.
    Gu J X, Wang Z H, Kuen J, et al. 2018. Recent advances in convolutional neural networks. Pattern Recognition, 77(C):354–377.
    He K M, Gkioxari G, Dollár P, et al. 2017. Mask R-CNN // Institute of Electrical and Electronics Engineers. 2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy. IEEE, 2980–2988.
    Hou J, He Y X, Yang H B, et al. 2020. Identification of animal individuals using deep learning:a case study of giant panda. Biological Conservation, 242:108414.
    Kahl S, Wilhelm-Stein T, Hussein H, et al. 2017. Large-scale bird sound classification using convolutional neural networks. CLEF (working notes), 1866.
    Kassim Y M, Byrne M E, Burch C, et al. 2020. Small object bird detection in infrared drone videos using Mask R-CNN deep learning. Electronic Imaging, 32(8):85-1–85-8.
    Kellenberger B, Marcos D, Lobry S, et al. 2019. Half a percent of labels is enough:efficient animal detection in UAV imagery using deep CNNs and active learning. IEEE Transactions on Geoscience and Remote Sensing, 57(12):9524–9533.
    Kellenberger B, Volpi M, Tuia D. 2017. Fast animal detection in UAV images using convolutional neural networks // Institute of Electrical and Electronics Engineers. 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). Fort Worth, TX, USA. IEEE, 866–869.
    Korczak-Abshire M, Zmarz A, Rodzewicz M, et al. 2019. Study of fauna population changes on Penguin Island and Turret Point Oasis (King George Island, Antarctica) using an unmanned aerial vehicle. Polar Biology, 42(1):217–224.
    Krizhevsky A, Sutskever I, Hinton G E. 2012. ImageNet classification with deep convolutional neural networks // Proceedings of the 25th International Conference on Neural Information Processing Systems:Volume 1. Red Hook, NY, USA:Curran Associates, 1097–1105.
    Li H, Dong Y Q, Liu Y X, et al. 2022. Design and implementation of UAVs for bird’s nest inspection on transmission lines based on deep learning. Drones, 6(9):252.
    Redmon J, Farhadi A. 2018. YOLOv3:an incremental improvement. [EB/OL]. [2023-05-05]. http://arxiv.org/abs/1804.02767.pdf.
    Shafer M W, Vega G, Rothfus K, et al. 2019. UAV wildlife radiotelemetry:system and methods of localization. Methods in Ecology and Evolution, 10(10):1783–1795.
    Shao W, Kawakami R, Yoshihashi R, et al. 2020. Cattle detection and counting in UAV images based on convolutional neural networks. International Journal of Remote Sensing, 41(1):31–52.
    Xu B B, Wang W S, Falzon G, et al. 2020. Livestock classification and counting in quadcopter aerial images using Mask R-CNN. International Journal of Remote Sensing, 41(21):8121–8142.
    蔡前舟. 2022. 基于卷积神经网络的野生动物种类识别中长尾问题研究. 南充:西华师范大学硕士学位论文.
    陈刚琦. 2020. 基于卷积神经网络的高原鼠兔图像检测与分割方法研究. 兰州:兰州理工大学硕士学位论文.
    高大中, 林海, 林乐乐, 等. 2021. 利用小型无人机监测西洞庭湖水鸟的可行性探讨. 动物学杂志, 56(1):100–110.
    胡旭. 2019. 基于注意力机制的金丝猴面部识别研究与实现. 西安:西安电子科技大学硕士学位论文.
    雷倩, 李金亚, 马克明. 2018. 遥感技术在鸟类生态学研究中的应用. 生物多样性, 26(8):862–877.
    李杰, 刘强. 2019. 无人机水禽监测模式的设立原则探讨. 热带地理, 39(4):546–552.
    史春妹, 谢佳君, 顾佳音, 等. 2021. 基于目标检测的东北虎个体自动识别. 生态学报, 41(12):4685–4693.
    张毓, 高雅月, 常峰源, 等. 2021. 小样本条件下基于数据扩充和ResNeSt的雪豹识别. 北京林业大学学报, 43(10):89–99.
    相似文献
    引证文献
引用本文

林海,高大中,张童,崔国发.2024.基于卷积神经网络的无人机遥感影像水鸟自动识别.动物学杂志,59(3):450-459.

复制
文章指标
  • 点击次数:1032
  • 下载次数: 1039
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2023-06-14
  • 在线发布日期: 2024-06-17