Skip to main content

Detection and Classification of Bird Pest Using Spectrogram, Physical Imagery, and Convolutional Neural Network

  • Conference paper
  • First Online:
Data Engineering and Intelligent Computing

Part of the book series: Lecture Notes in Networks and Systems ((LNNS,volume 446))

  • 263 Accesses

Abstract

In this paper, we present a method for detecting and recognizing certain birds that are damaging to agriculture among a large number of bird species using physical and acoustic spectrogram imagery and optimized convolutional neural network classifiers. Two CNN models are designed to automatically and hierarchically learn spatially image features using 5 convolution layers of different filters followed by max polling 3 and fully connected 10 NN layers, respectively. CNNs model are then individually trained on physical and spectrogram images to identify five classes of pest birds using back-propagation algorithm. Several experiments are performed to tune many hyperparameters of the CNN models to optimize training and testing accuracy. The classification performance of CNN models is evaluated on different datasets for each case. The CNN classifier using physical bird image has better recognition accuracy (93%) as compared to the CNN model using bird acoustic spectrogram image (90%). The test results have proven that the models are good enough to classify bird pest and can, therefore, be deployed in an automatic system to recognize bird pest in an agriculture field to initiate preventive measures or record alert events to safeguard crops or plant from bird pest attack.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 189.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 249.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Ashokrao Kale M, Dudhe N, Kasambe R, Bhattacharya P, Department of Sustainable Development, Environmental Science and Engineering, KTH Royal Institute of Technology, Teknikringen 76, 100 44 Stockholm, Sweden, Environment Service Scheme (ESS), Centre for Environment Education (CEE), Pune 411007, India, IBA-IBCN, Bombay Natural History Society, Mumbai 400023, India, “Crop Depredation by Birds in Deccan Plateau, India”

    Google Scholar 

  2. Bird Audio Detection—DCASE 2018 Franz Berger, William Freillinger, Paul Primus, and Wolfgang Reisinger Special Topics—Machine Learning and Audio: a challenge Johannes Kepler University, Linz, Austria

    Google Scholar 

  3. Janˇcovic P, Senior Member, IEEE, and Münevver Köküer, Member, IEEE (2019) Bird species recognition using unsupervised modeling of individual vocalization elements. IEEE/ACM Transactions on Audio, Speech, and Language Processing 27(5), May

    Google Scholar 

  4. Emre Cakir Tampere University of Technology, Finland, Sharath Adavanne Tampere University of Technology, Finland, Giambattista Parascandolo Tampere University of Technology, Finland, Konstantinos Drossos Tampere University of Technology, Finland, Tuomas Virtanen Tampere University of Technology, Finland, “Convolutional Recurrent Neural Networks for Bird Audio Detection”, 2017 25th European Signal Processing Conference (EUSIPCO)

    Google Scholar 

  5. Xie J, Hu K, Zhu M, Yu J, Zhu Q (2019) Jiangsu Key Laboratory of Advanced Food Manufacturing Equipment and Technology, Jiangnan University, Wuxi 214122, China, Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi 214122, China, School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China, Department of Economics, University of Ottawa, Ottawa, ON K1N 6N5, Canada, School of Mechanical Engineering, Jiangnan University, Wuxi 214122, China, “Investigation of Different CNN-Based Models for Improved Bird Sound Classification”, November

    Google Scholar 

  6. Rezazadeh Sereshkeh A, Trott R, Bricout A, Chau T (2017) Senior Member, IEEE EEG classification of covert speech using regularized neural networks. IEEE/ACM Transactions on Audio, Speech, and Language Processing, Vol. 25(12)

    Google Scholar 

  7. Stowell D, Wood M, Pamuła H, Stylianou Y Glotin H (2018) Machine Listening Lab, Centre for Digital Music, Queen Mary University of London, “Automatic acoustic detection of birds through deep learning: the first Bird Audio Detection challenge”, https://arXiv:1807.05812v1[cs.SD]

    Google Scholar 

  8. Pahuja R, Kumar A, DR B R Ambedkar National Institute of technology, Jalandhar (Punjab), India, Sound spectrogram based automatic bird species recognition using MLP classifier.

    Google Scholar 

  9. Narasimhan R, Xiaoli Z. Fern, Raviv Raich School of EECS, Oregon State University, Corvallis, OR 97331–5501, USA, “Simultaneous Segmentation and Classification of Bird Song Using CNN

    Google Scholar 

  10. Adavanne S, Drossos K, Emre C (2017) Tuomas Virtanen Department of Signal Processing, Tampere University of Technology, Finland, “Stacked Convolutional and Recurrent Neural Networks for Bird Audio Detection”. 2017 25th European Signal Processing Conference (EUSIPCO)

    Google Scholar 

  11. Kong Q, Xu Y, Mark D (2017) Plumbley Center for Vision, Speech and Signal Processing (CVSSP) University of Surrey. Joint Detection and Classification Convolutional Neural Network on Weakly Labelled Bird Audio Detection. 25th European Signal Processing Conference (EUSIPCO)

    Google Scholar 

  12. Stowell D, Benetos E, Member, IEEE, Gill LF (2017) On-bird sound recordings: Automatic acoustic recognition of activities and contexts. IEEE/ACM Transactions on Audio, Speech, and Language Processing 25(6)

    Google Scholar 

  13. Ke-Lin D, Swamy MNS, Neural networks and statistical learning

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Aniket Roy .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Roy, A., Pahuja, R. (2022). Detection and Classification of Bird Pest Using Spectrogram, Physical Imagery, and Convolutional Neural Network. In: Bhateja, V., Khin Wee, L., Lin, J.CW., Satapathy, S.C., Rajesh, T.M. (eds) Data Engineering and Intelligent Computing. Lecture Notes in Networks and Systems, vol 446. Springer, Singapore. https://doi.org/10.1007/978-981-19-1559-8_6

Download citation

Publish with us

Policies and ethics