Skip to main content

Advertisement

SpringerLink
Log in

Object detection using deep ensemble model for enhancing security towards sustainable agriculture

  • Original Research
  • Published:
International Journal of Information Technology Aims and scope Submit manuscript

Abstract

The protection of crops from intruders (objects) is a critical concern for sustainable agriculture and reducing crop loss. However, traditional methods relying on human intervention often lead to significant losses. To address this issue, we have developed the E-YOLOv3, a deep learning-based object detection model that detects objects within agricultural fields. Additionally, we created and compared four models based on YOLOv3 and Tiny-YOLOv3 to improve object detection accuracy in agriculture field. These models consist of multiple neural network layers that enhances the system's accuracy, using K-Means clustering algorithm and NMS algorithm. The results demonstrate that E-YOLOv3 outperforms the other models, achieving highest precision, recall, F1score, IoU, and mAP values of 97%, 96%, 96%, 80.81%, and 95.86%, respectively. Compared to previous models, the E-YOLOv3 shows an improvement of ~ 62.44% in accuracy with a minimal error rate of ~ 4%. Our proposed model is the most accurate among all state-of-the-art approaches and exhibits the highest detection probability when tested on various video datasets. Therefore, the E-YOLOv3 is an effective tool for farmers as it provides object detection without requiring human intervention, reducing crop losses, and increasing productivity.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Zhao Z-Q, Zheng P, Shou-tao Xu, Xindong Wu (2019) Object detection with deep learning: a review. IEEE Trans Neural Netw Learn Syst 30(11):3212–3232

    Article  Google Scholar 

  2. Ngo VM, Duong T-VT, Nguyen T-B-T, Dang CN, Conlan O. (2023) "A big data smart agricultural system: recommending optimum fertilizers for crops." Int J Inform Technol : 1–17.

  3. Radarapu R, Gopal ASS, Madhusudhan NH (2021) Video summarization and captioning using dynamic mode decomposition for surveillance. Int J Inform Technol 13(5):1927–1936

    Google Scholar 

  4. Elijah O, Rahman TA, Orikumhi I, Leow CY, Nour Hinda MHD (2018) An overview of internet of things (IoT) and data analytics in agriculture: benefits and challenges. IEEE Internet Things J 5(5):3758–3773

    Article  Google Scholar 

  5. Navulur S, Giri prasad MN (2017) Agricultural management through wireless sensors and internet of things.". Int J Electr Comput Eng 7(6):3492

    Google Scholar 

  6. Zhao L, Li S (2020) Object detection algorithm based on improved YOLOv3. Electronics 9(3):537

    Article  Google Scholar 

  7. Kumar S, Yadav D, Gupta H, Verma OP, Ansari IA, Ahn CW (2021) A novel yolov3 algorithm-based DL approach for waste segregation: towards smart waste management.". Electronics 10(1):14

    Article  Google Scholar 

  8. Gai W, Liu Y, Zhang J, Jing G (2021) An improved tiny YOLOv3 for real-time object detection. Syst Sci Control Eng 9(1):314–321

    Article  Google Scholar 

  9. He W, Huang Z, Wei Z, Li C, Guo B (2019) TF-YOLO: an improved incremental network for real-time object detection. Appl Sci 9(16):3225

    Article  Google Scholar 

  10. Balakrishna K, Fazil Mohammed M, Ullas CR, Hema CM, Sonakshi SK (2021) Application of IOT and machine learning in crop protection against animal intrusion. Global Transit Proc 2(2):169–174

    Article  Google Scholar 

  11. Thakur D, Kumar Y, Vijendra S (2020) Smart irrigation and intrusions detection in agricultural fields using IoT. Procedia Comput Sci 167:154–162

    Article  Google Scholar 

  12. Anandhalli, Mallikarjun, A. Tanuja, Vishwanath P. Baligar, and Pavana Baligar. "Indian pothole detection based on CNN and anchor-based deep learning method." International Journal of Information Technology (2022): 1–11.

  13. Bapat V, Kale P, Shinde V, Deshpande N, Shaligram A (2017) WSN application for crop protection to divert animal intrusions in the agricultural land. Comput Electron Agric 133:88–96

    Article  Google Scholar 

  14. Mahajan T, Mahajan J (2016) IOT based agriculture automation with intrusion detection. Int J Sci Tech Adv 2(4):269–274

    Google Scholar 

  15. Radhakrishnan, Saieshwar, and R. Ramanathan. "A support vector machine with Gabor features for animal intrusion detection in agriculture fields." Procedia computer science 143 (2018): 493–501..

  16. Andavarapu N, Vatsavayi VK (2017) Wild-animal recognition in agriculture farms using W-COHOG for agro-security. Int J Comput Intell Res 13(9):2247–2257

    Google Scholar 

  17. Trnovszky T, Kamencay P, Orjesek R, Benco M, Sykora P (2017) Animal recognition system based on convolutional neural network. Adv Electr Electron Eng 15(3):517–525

    Google Scholar 

  18. Wenling X, Jiang T, Shi J. (2017) Animal intrusion detection based on convolutional neural network. In: 2017 17th international symposium on communications and information technologies (ISCIT), pp. 1–5. IEEE,

  19. Upadrashta, Raviteja, Tarun Choubisa, V. S. Aswath, Praneeth A, Prabhu A, Raman S, Gracious T et al. (2015) "An animation-and-chirplet based approach to object classification using PIR sensing." In 2015 IEEE tenth international conference on intelligent sensors, sensor networks and information processing (ISSNIP), pp. 1–6. IEEE

  20. Sanku Kumar R, Roy A, Misra S, Raghuwanshi NS, and Mohammad S. Obaidat. "AID: a prototype for agricultural intrusion detection using wireless sensor network." In 2015 IEEE international conference on communications (icc), pp. 7059–7064. IEEE, 2015.

  21. Vishwas Raj J, Bagree R, Kumar A, and Ranjan P. (2008) wildCENSE: GPS based animal tracking system. In: 2008 International conference on intelligent sensors, sensor networks and information processing, pp. 617–622. IEEE

  22. Ansari MA, Singh DK (2021) Monitoring social distancing through human detection for preventing/reducing COVID spread. Int J Inform Technol 13(3):1255–1264

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. JIIT: Jaypee Institute of Information Technology, Noida, India

    Priya Singh & Rajalakshmi Krishnamurthi

Authors
  1. Priya Singh
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rajalakshmi Krishnamurthi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Priya Singh.

Ethics declarations

Conflict of interest

The author(s) declared no potential conflicts of interest for the research, authorship, and/or publication of this article.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Singh, P., Krishnamurthi, R. Object detection using deep ensemble model for enhancing security towards sustainable agriculture. Int. j. inf. tecnol. 15, 3113–3126 (2023). https://doi.org/10.1007/s41870-023-01341-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s41870-023-01341-4

Keywords

Search

Navigation