Skip to content
DraconiticResearch
Search Sources API
186,541 studies31 sourcesUpdated 4 min ago
Peer-reviewedCC BY 4.0PLOS One

Optimized bilateral segmentation deep learning network for wild animal detection

  • Srikanth Busa1
  • Johnwesily Chappidi2
  • Gunakala Archana3
  • Anitha Rani Palakayala4
  • Guggilam Venkata Vidya Lakshmi5
  • Khasim Syed
  • Shaik Salma Asiya Begum
5 affiliations
  1. 1School of Computer Science and Engineering, VIT- AP University, Guntur, Andhra Pradesh, India
  2. 2Department of CSE (AI&ML), Lakireddy Bali Reddy College of Engineering, Mylavaram, Andhra Pradesh, India
  3. 3Department of ACSE, Vignan’s Foundation for Science, Technology and Research, Guntur, Andhra Pradesh, India
  4. 4Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Guntur, Andhra Pradesh, India
  5. 5School of Computer Science and Engineering, SRM University, Guntur, Andhra Pradesh, India
Open at sourcePDFDOICite

Abstract

The use of Deep learning (DL) for recognition of wild animals has become an important development in wildlife monitoring. The advances will include the use of multimodal data for improved accuracy and development of lightweight models for use in edge devices. As a result, DL will help contribute to global conservation efforts as it tackles the issues. The key novelty of the proposed framework is the integration of bilateral segmentation with DL to enhance relevant animal feature extraction while reducing the influence of complex background information. The paper proposes the Optimized Bilateral Segmentation DL Network that uses Harris Hawks Optimization (HHO) to improve Convolutional Neural Network (CNN) parameters for wild animal identification. The first step in the process was collecting datasets from various online sources. The image quality was improved through image processing methods such as Adaptive Histogram Equalization (AHE) as well as median filtering. The classifier was trained and validated using pre-processed images. This classifier combines the Bilateral Segmentation Deep Learning Network (BSDLN) with the HHO algorithm. CNN is utilized for detection and the weight parameter is utilized by HHO. In order to enhance model convergence also with performance, HHO dynamically adjusts the learning rate during training within the BSDLN. This balances speed and accuracy by adapting to gradients and losses behavior. By adaptively adjusting the learning rate, HHO and BSDLN optimize the CNN learning process and enhance convergence and classification performance. The suggested approach is put into practice in Python, and statistical metrics are used to assess its effectiveness. The results are compared with other approaches to verify the strategy’s efficacy. With just 0.2% FPR and 0.3% FNR, the suggested BSDLN performed the best overall, achieving 99.4% precision, 99.8% accuracy, 99.6% recall, 99.5% F1-score, and 99.3% specificity. The experimental findings show that the combination of HHO and bilateral segmentation enhances the efficacy of wild animal detection, offering a strong foundation for automated wildlife monitoring.

Related

  1. CuFormer U-Net: a transformer-enhanced multi-task network for cucumber leaf disease detection and segmentation
    Batyrkhan Omarov, Sayat Ibrayev, Nurbibi Imanbayeva
    Frontiers in Plant SciencePeer-reviewedCC BY 4.0Full textPlant biologyCrossrefEurope PMC
  2. UAV-based disease detection in strawberry by multispectral image segmentation invoking deep learning.
    A F Cheshkova, V S Riksen, O V Elkin
    Vavilovskii zhurnal genetiki i selektsiiPeer-reviewedCC BYFull textPlant biologyEurope PMC
  3. Chili-Seg: a high-precision detection and instance segmentation model for chili flowers in complex environments
    Minqiu Kuang, Xiaojian Li, Zhizhen Hu +5
    Frontiers in plant sciencePeer-reviewedCC BYFull textPlant biologyEurope PMC
  4. Bilateral cortical network disruptions in the rat caudal forelimb area after unilateral stroke.
    Cheng'an Cao, Di Chen, Jin Gong +6
    Behavioral and brain functions : BBFPeer-reviewedCC BY-NC-NDFull textNeuroscienceEurope PMCPMC
  5. Physiology-Informed Blink Artefact Detection from Bilateral Frontal EEG Under Asymmetric Interference
    Weiqiang Zhang, Menglong Li, Yujie Zhang +5
    Bioengineering (Basel, Switzerland)Peer-reviewedCC BYFull textNeuroscienceEurope PMCDOAJ

Cite

BibTeXRIS
BibTeX
@article{busa2026optimized,
  title = {{Optimized bilateral segmentation deep learning network for wild animal detection}},
  author = {Srikanth Busa and Johnwesily Chappidi and Gunakala Archana and Anitha Rani Palakayala and Guggilam Venkata Vidya Lakshmi and Khasim Syed and Shaik Salma Asiya Begum},
  journal = {PLOS One},
  year = {2026},
  month = oct,
  doi = {10.1371/journal.pone.0360422},
  url = {https://doi.org/10.1371/journal.pone.0360422},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Optimized bilateral segmentation deep learning network for wild animal detection
AU  - Srikanth Busa
AU  - Johnwesily Chappidi
AU  - Gunakala Archana
AU  - Anitha Rani Palakayala
AU  - Guggilam Venkata Vidya Lakshmi
AU  - Khasim Syed
AU  - Shaik Salma Asiya Begum
PY  - 2026
DA  - 2026/10/15
JO  - PLOS One
DO  - 10.1371/journal.pone.0360422
UR  - https://doi.org/10.1371/journal.pone.0360422
AB  - The use of Deep learning (DL) for recognition of wild animals has become an important development in wildlife monitoring. The advances will include the use of multimodal data for improved accuracy and development of lightweight models for use in edge devices. As a result, DL will help contribute to global conservation efforts as it tackles the issues. The key novelty of the proposed framework is the integration of bilateral segmentation with DL to enhance relevant animal feature extraction while reducing the influence of complex background information. The paper proposes the Optimized Bilateral Segmentation DL Network that uses Harris Hawks Optimization (HHO) to improve Convolutional Neural Network (CNN) parameters for wild animal identification. The first step in the process was collecting datasets from various online sources. The image quality was improved through image processing methods such as Adaptive Histogram Equalization (AHE) as well as median filtering. The classifier was trained and validated using pre-processed images. This classifier combines the Bilateral Segmentation Deep Learning Network (BSDLN) with the HHO algorithm. CNN is utilized for detection and the weight parameter is utilized by HHO. In order to enhance model convergence also with performance, HHO dynamically adjusts the learning rate during training within the BSDLN. This balances speed and accuracy by adapting to gradients and losses behavior. By adaptively adjusting the learning rate, HHO and BSDLN optimize the CNN learning process and enhance convergence and classification performance. The suggested approach is put into practice in Python, and statistical metrics are used to assess its effectiveness. The results are compared with other approaches to verify the strategy’s efficacy. With just 0.2% FPR and 0.3% FNR, the suggested BSDLN performed the best overall, achieving 99.4% precision, 99.8% accuracy, 99.6% recall, 99.5% F1-score, and 99.3% specificity. The experimental findings show that the combination of HHO and bilateral segmentation enhances the efficacy of wild animal detection, offering a strong foundation for automated wildlife monitoring.
SN  - 1932-6203
ER  -