Abstract
When facing practical underwater applications, how to improve environmental perception and autonomous decision-making ability in unstructured and complex dynamic underwater environment is a challenge for bionic robotic fish. In order to improve the environmental perception ability of bionic robot fish, a scene perception method of bionic robot fish based on MobileNetV3 is proposed in this paper. Firstly, the basic framework of bionic robotic fish scene perception based on MobileNetV3 network is designed. This method uses the transfer learning strategy to train the model, and optimizes the model according to the super parameters. Secondly, the scene perception and tracking control software platform of bionic robotic fish is developed and experiments are carried out. Thirdly, the robot fish scene perception algorithm based on SIFT-SVM is constructed and compared with the scene perception method based on MobileNetV3. The experimental results show that the scene perception method based on MobileNetV3 is feasible and effective, and can be applied to the environment perception of bionic robotic fish.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhou, Z., Liu, J., Yu, J.: A survey of underwater multi-robot systems. IEEE/CAA J. Autom. Sinica 9(1), 1–18 (2021)
Liu, X., Jia, Z., Hou, X., Fu, M., Ma, L., Sun, Q.: Real-time marine animal images classification by embedded system based on MobileNet and transfer learning. In: OCEANS 2019, Marseille, France, pp. 1–5. IEEE (2019)
Quiñonez, Y., Lizarraga, C., Peraza, J., Zatarain, O.: Image recognition in UAV videos using convolutional neural networks. IET Softw. 14(2), 176–181 (2020)
Zhu, J., Zhu, J., Wan, X., Wu, C., Xu, C.: Object detection and localization in 3D environment by fusing raw fisheye image and attitude data. J. Vis. Commun. Image Represent. 59, 128–139 (2019)
Li, P., Che, C.: SeMo-YOLO: a multiscale object detection network in satellite remote sensing images. In: 2021 International Joint Conference on Neural Networks (IJCNN), Shenzhen, China, pp. 1–8. IEEE (2021)
Yu, D., Xu, Q., Guo, H., Zhao, C., Lin, Y., Li, D.: An efficient and lightweight convolutional neural network for remote sensing image scene classification. Sensors 20(7), 1999 (2020)
Wang, J., He, X., Faming, S., Lu, G., Jiang, Q., Hu, R.: Multi-Size object detection in large scene remote sensing images under dual attention mechanism. IEEE Access 10, 8021–8035 (2022)
Shuai, Y., Zhiyu, C., Shangdong, L., Mengxue, W., Feng, T., Yimu, J.: YoLite+: a lightweight multi-object detection approach in traffic scenarios. Procedia Comput. Sci. 199, 346–353 (2022)
Wu, X., Qiu, T., Wang, Y.: Multi-object detection and segmentation for traffic scene based on improved Mask R-CNN. Chin. J. Sci. Instrum. 42(07), 242–249 (2021). (in Chinese)
Lin, B., Mu, Y., Fu, Z., Li, C., Duan, X.: A network for detecting facial features during the COVID-19 epidemic. In: Zhang, D. (ed.) CCEAI 2021: 5th International Conference on Control Engineering and Artificial Intelligence (CCEAI), pp. 141–146. Association for Computing Machinery, New York (2021)
AL-Marghilani, A.A.: Target detection algorithm in crime recognition using artificial intelligence. CMC Comput. Mater. Continua 71(1), 809–824 (2022)
Wan, Y., Zhang, M.X., Zhang, Y.A., Yao, L.: Research on unconstrained face recognition based on deep learning. In: 2020 International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE), Bangkok, Thailand, pp. 219–227. IEEE (2020)
Nan, Y., Ju, J., Hua, Q., Zhang, H., Wang, B.: A-MobileNet: an approach of facial expression recognition. Alex. Eng. J. 61(6), 4435–4444 (2022)
Su, C., Wang, G.: Design and application of learner emotion recognition for classroom. J. Phys. Conf. Ser. 1651(1), 1–9 (2020)
Awalgaonkar, N., Bartakke, P., Chaugule, R.: Automatic license plate recognition system using SSD. In: 2021 International Symposium of Asian Control Association on Intelligent Robotics and Industrial Automation (IRIA), Goa, India, pp. 394–399. IEEE (2021)
Kong, Y., Han, S., Li, X., Lin, Z., Zhao, Q.: Object detection method for industrial scene based on MobileNet. In: 2020 12th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), Hangzhou, China, pp. 79–82. IEEE (2020)
Acknowledgement
This work is supported by the National Natural Science Foundation of China under Grant Nos. 62073196 and U1806204.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, M., Du, X., Chang, Z., Wang, K. (2022). A Scene Perception Method Based on MobileNetV3 for Bionic Robotic Fish. In: Zhang, H., et al. Neural Computing for Advanced Applications. NCAA 2022. Communications in Computer and Information Science, vol 1638. Springer, Singapore. https://doi.org/10.1007/978-981-19-6135-9_30
Download citation
DOI: https://doi.org/10.1007/978-981-19-6135-9_30
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-6134-2
Online ISBN: 978-981-19-6135-9
eBook Packages: Computer ScienceComputer Science (R0)