Abstract
Deep learning computer vision research has been widely used agriculture field to reduce labor costs and provide technical support for fruit farmers. At present, most object detection algorithms cannot effectively extend to the mountain orchard scene. This paper designs a fast and efficient citrus detection system, which combines unmanned aerial photography and edge computing device. The system uses low altitude UAV to take an omnidirectional image of citrus at different angles. Then, we optimize the state-of-the-art object detection model, use the attention mechanism to enhance the detection effect of small citrus objects. We use UAV to collect citrus fruit images and use the improved model for detection. The experimental results show that the detection accuracy of the model for citrus fruit data set is 93.42%. The detection time of single citrus fruit image in the edge device is 310 ms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Lan, Y., Deng, X., Zeng, G.: Advances in diagnosis of crop diseases, pests and weeds by UAV remote sensing. Smart Agric. 1(2), 1–19 (2019). (in Chinese)
Harrell, R.C., Adsit, P.D., Munilla, R.D., et al.: Robotic picking of citrus. Robotica 8(04), 269–278 (1990)
Dorj, U.O., Lee, M., Yun, S.S.: A yield estimation in citrus orchards via fruit detection and counting using image processing. Comput. Electron. Agric. 140, 103–112 (2017)
Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: Convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1
Fan, X., Zhou, J., Xu, Y.: Research progress of UAV low altitude remote sensing monitoring agricultural information. J. Xinjiang Univ. (Natural Science Edition) (Chinese and English) 38(05), 623–631 (2021). (in Chinese)
Liu, S.B., et al.: Information extraction of maize seedling number based on UAV remote sensing image. J. Agric. Eng. 34(22), 69–77 (2018). (in Chinese)
Mazzia, V., Salvetti, F., Khaliq, A., et al.: Real-time apple detection system using embedded systems with hardware accelerators: An edge AI application. IEEE Access 8, 9102–9114 (2020)
Sa, I., Chen, Z., Popovic, M., et al.: : WeedNet: Dense semantic weed classification using multispectral images and MAV for smart farming. IEEE Robot. Autom. Lett. 3, 588–595 (2017)
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
Huang, H., Kadoch, M. (2022). Portable Citrus Detection System Combining UAV and Edge Equipment. In: Sun, S., Hong, T., Yu, P., Zou, J. (eds) Signal and Information Processing, Networking and Computers. ICSINC 2021. Lecture Notes in Electrical Engineering, vol 895. Springer, Singapore. https://doi.org/10.1007/978-981-19-4775-9_49
Download citation
DOI: https://doi.org/10.1007/978-981-19-4775-9_49
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-4774-2
Online ISBN: 978-981-19-4775-9
eBook Packages: Computer ScienceComputer Science (R0)