Skip to main content
SpringerLink
Log in

Evolutionary algorithm for optimized CNN architecture search applied to real-time boat detection in aerial images

  • Research
  • Published:
Journal of Real-Time Image Processing Aims and scope Submit manuscript

Abstract

When processing the detection of boats in aerial images by neural networks, we have always been concerned about the execution time of these networks in the equipment on board the Unmanned Aerial Vehicle (UAV). Throughout its mission, the UAV will capture images that must be processed in real time. For this purpose, a network optimized for execution time is essential. This article proposes an enhanced Network Architecture Search (NAS) method for searching for time-optimized detection networks, for a given dataset, using an evolutionary algorithm. The search uses mutations as a mechanism of evolution that affect the structure of the network and the hyper-parameters of its layers. Its original fitness function allows the choice of architectures that are not very greedy in terms of operations, specifically favouring small networks whose advantages are to be fast and quick to train, thus accelerating the search algorithm. Using this method, we were able to obtain detection networks with an improved mean Average Precision (mAP) compared to the initial network (parent) but with much fewer FLoating-point OPerations (Flops): 68% of operations reduction. This induces considerable gain in terms of execution time with 50 Frames Processed per Second (FPS) in an embedded environment on a drone.

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
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Data availability

The dataset that support the findings of this study are available from the corresponding author on reasonable request. Other data are available within the paper and its supplementary information file.

Code Availability

The source code of the evolutionary algorithm subject of this work are not publicly available due to the partial license detention by AtlanSpace but are available from the corresponding author on reasonable request and with permission of AtlanSpace.

Notes

  1. Framework source code: https://github.com/AlexeyAB/darknet.

References

  1. Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning Transferable Architectures for Scalable Image Recognition. arXiv (2017). https://doi.org/10.48550/ARXIV.1707.07012

  2. Tan, M., Le, Q.: EfficientNet: Rethinking model scaling for convolutional neural networks. Proc. Int. Conf. Mach. Learn. Proc. Mach. Learn. Res. 97, 6105–6114 (2019)

    Google Scholar 

  3. Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. Proc. AAAI Conf. Artif. Intell. and Innov. Appl. of Artif. Intell. Conf. and AAAI Symp. Educ. Adv. Artif. Intell. AAAI’19/IAAI’19/EAAI’19, (2019). https://doi.org/10.1609/aaai.v33i01.33014780

  4. Elsken, T., Metzen, J.H., Hutter, F.: Neural architecture search: A survey. J. Mach. Learn. Res. 20(55), 1–21 (2019)

    MathSciNet  MATH  Google Scholar 

  5. Stanley, K.O., Clune, J., Lehman, J., Miikkulainen, R.: Designing neural networks through neuroevolution. Nat. Mach. Intell. 1(1), 24–35 (2019). https://doi.org/10.1038/s42256-018-0006-z

    Article  Google Scholar 

  6. Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002). https://doi.org/10.1162/106365602320169811

    Article  Google Scholar 

  7. Blalock, D., Ortiz, J.J.G., Frankle, J., Guttag, J.: What is the State of Neural Network Pruning? arXiv (2020). https://doi.org/10.48550/ARXIV.2003.03033

  8. Li, X., Wang, Z., Geng, S., Wang, L., Zhang, H., Liu, L., Li, D.: Yolov3-Pruning(transfer): real-time object detection algorithm based on transfer learning. J. Real-Time Image Proc. 19(4), 839–852 (2022). https://doi.org/10.1007/s11554-022-01227-x

    Article  Google Scholar 

  9. Redmon, J., Farhadi, A.: YOLOv3: An incremental improvement. arXiv (2018). https://doi.org/10.48550/ARXIV.1804.02767

  10. Hinton, G., Vinyals, O., Dean, J.: Distilling the Knowledge in a Neural Network. arXiv (2015). https://doi.org/10.48550/ARXIV.1503.02531

  11. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv (2017). https://doi.org/10.48550/ARXIV.1704.04861

  12. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C.: Mobilenetv2: Inverted residuals and linear bottlenecks. arXiv (2018). https://doi.org/10.48550/ARXIV.1801.04381

  13. Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices. arXiv (2017). https://doi.org/10.48550/ARXIV.1707.01083

  14. Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., Le, Q.V.: Mnasnet: Platform-aware neural architecture search for mobile. arXiv (2018). https://doi.org/10.48550/ARXIV.1807.11626

  15. Jin, C., Phothilimthana, P.M., Roy, S.: Neural architecture search using property guided synthesis. Proc. ACM Program. lang. 6(OOPSLA2), 1150–1179 (2022). https://doi.org/10.1145/3563329

    Article  Google Scholar 

  16. Liu, H., Simonyan, K., Yang, Y.: DARTS: Differentiable architecture search. In: Int. Conf. Learn. Represent. (2019)

  17. Tsukada, R., Zou, L., Iba, H.: Evolving Deep Neural Networks for X-ray Based Detection of Dangerous Objects, pp. 325–355. Springer, Singapore (2020)

    Google Scholar 

  18. Redmon, J., Farhadi, A.: YOLO9000: Better, Faster, Stronger. arXiv (2016). https://doi.org/10.48550/ARXIV.1612.08242

  19. Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., Li, Y., Zhang, B., Liang, Y., Zhou, L., Xu, X., Chu, X., Wei, X., Wei, X.: YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications. arXiv (2022). https://doi.org/10.48550/ARXIV.2209.02976

  20. Chen, D., Shen, H., Shen, Y.: PT-NAS: Designing efficient keypoint-based object detectors for desktop cpu platforms. Neurocomputer 476, 38–52 (2022). https://doi.org/10.1016/j.neucom.2021.12.067

    Article  Google Scholar 

  21. Shashirangana, J., Padmasiri, H., Meedeniya, D., Perera, C., Nayak, S.R., Nayak, J., Vimal, S., Kadry, S.: License plate recognition using neural architecture search for edge devices. Int. J. Intell. Syst. 37(12), 10211–10248 (2022). https://doi.org/10.1002/int.22471

    Article  Google Scholar 

  22. Lyu, B., Yuan, H., Lu, L., Zhang, Y.: Resource-constrained neural architecture search on edge devices. IEEE Trans. Netw. Sci. and Eng. 9(1), 134–142 (2022). https://doi.org/10.1109/TNSE.2021.3054583

    Article  Google Scholar 

  23. Cai, H., Zhu, L., Han, S.: ProxylessNAS: Direct neural architecture search on target task and hardware. Int. Conf. Learn. Represent. (2019). https://doi.org/10.48550/arXiv.1812.00332

  24. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going Deeper with Convolutions. arXiv (2014). https://doi.org/10.48550/ARXIV.1409.4842

  25. Zerrouk, I., Moumen, Y., Khiati, W., Berrich, J., Bouchentouf, T.: Detection process of ships in aerial imagery using two convnets. Int. Conf. Wirel. Technol. Embed. Intell. Syst. (2019). https://doi.org/10.1109/WITS.2019.8723734

    Article  Google Scholar 

  26. Zerrouk, I., Moumen, Y., Khiati, W., El Habchi, A., Berrich, J., Bouchentouf, T.: CNN adaptations for boat detection in aerial images tested on yolo v2. Int. Symp. Adv. Electr. Commun. Technol. (2020). https://doi.org/10.1109/ISAECT50560.2020.9523704

    Article  Google Scholar 

Download references

Funding

This work was partially funded by AtlanSpace by providing cloud services.

Author information

Authors and Affiliations

  1. LaRSA Laboratory, Université Mohammed Premier, Oujda, Morocco

    Ilham Zerrouk, Wassim Khiati, Ali El Habchi, Jamal Berrich & Toumi Bouchentouf

  2. RnD Department, AtlanSpace, Casablanca, Morocco

    Younes Moumen, Wassim Khiati & Ali El Habchi

Authors
  1. Ilham Zerrouk
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Younes Moumen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wassim Khiati
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ali El Habchi
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jamal Berrich
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Toumi Bouchentouf
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

The authors confirm contribution to the paper as follows: study conception, design and coding: IZ; data collection: IZ, YM; analysis and interpretation of results: IZ, YM; draft manuscript preparation: IZ, YM. All authors reviewed the results and approved the final version of the manuscript.

Corresponding author

Correspondence to Ilham Zerrouk.

Ethics declarations

Conflict of interest

Author Jamal Berrich and Toumi Bouchentouf declare they have no financial interests. Author Ilham Zerrouk was an employee in Company AtlanSpace until August 2021. Younes Moumen, Wassim khiati and Ali El Habchi still employees in Company AtlanSpace at the date of submission.

Ethical approval

This article does not contain any studies involving human participants/animals performed by any of the authors.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Call for Papers: Special Issue on Real-Time Machine Vision Acceleration Technology and Applications.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (XLSX 66 KB)

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

Zerrouk, I., Moumen, Y., Khiati, W. et al. Evolutionary algorithm for optimized CNN architecture search applied to real-time boat detection in aerial images. J Real-Time Image Proc 20, 78 (2023). https://doi.org/10.1007/s11554-023-01332-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11554-023-01332-5

Keywords

Search

Navigation