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.
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
Framework source code: https://github.com/AlexeyAB/darknet.
References
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
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)
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
Elsken, T., Metzen, J.H., Hutter, F.: Neural architecture search: A survey. J. Mach. Learn. Res. 20(55), 1–21 (2019)
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
Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002). https://doi.org/10.1162/106365602320169811
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
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
Redmon, J., Farhadi, A.: YOLOv3: An incremental improvement. arXiv (2018). https://doi.org/10.48550/ARXIV.1804.02767
Hinton, G., Vinyals, O., Dean, J.: Distilling the Knowledge in a Neural Network. arXiv (2015). https://doi.org/10.48550/ARXIV.1503.02531
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
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
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
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
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
Liu, H., Simonyan, K., Yang, Y.: DARTS: Differentiable architecture search. In: Int. Conf. Learn. Represent. (2019)
Tsukada, R., Zou, L., Iba, H.: Evolving Deep Neural Networks for X-ray Based Detection of Dangerous Objects, pp. 325–355. Springer, Singapore (2020)
Redmon, J., Farhadi, A.: YOLO9000: Better, Faster, Stronger. arXiv (2016). https://doi.org/10.48550/ARXIV.1612.08242
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
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
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
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
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
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
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
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
Funding
This work was partially funded by AtlanSpace by providing cloud services.
Author information
Authors and Affiliations
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
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.
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.
About this article
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
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11554-023-01332-5