Abstract
Crop diseases and insect pests detection is a necessary means to ensure the healthy growth of crops. With the increase of crop planting area, in order to improve the detection efficiency, the application of deep learning algorithm to crop diseases and insect pests detection has become a research hotspot. However, the accuracy and efficiency of the traditional deep learning model is not high because of the natural concern of crop diseases and pests and the complex background. In this paper, we learn from and improve the fast-RCNN method which performs well in the task of target segmentation. We use cyclegan to supplement illumination and fast-RCNN to extract contour. In order to alleviate the problem of insufficient labeled samples, this paper studies the transfer learning mechanism of fast-RCNN, designs and implements the importance sampling of training data, parameter transfer mapping and other methods. Experiments on real data sets show that the algorithm can better extract the contour of the image and further identify the disease and insect pests in natural light with only a small number of labeled samples.
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
Tivive, F.H.C., Bouzerdoum, A.: A new class of convolutional neural networks (SICoNNets) and their application of face detection. In: International Joint Conference on Neural Networks, svol. 3, pp. 2157–2162. IEEE (2003)
Tivive, F.H.C., Bouzerdown, A.: An eye feature detector based on convolutional neural network. In: Eighth International Symposium on Signal Processing and ITS Applications, pp. 90–93. IEEE (2006)
Chen, Y.N., Han, C.C., Wang, C.T., et al.: The application of a convolution neural network on face and license plate detection. In: International Conference on Pattern Recognition, pp. 552–555. IEEE Computer Society (2006)
Szarvas, M., Yoshizawa, A., Yamamoto, M., et al.: Pedestrian detection with convolutional neural networks. In: IEEE Proceedings. Intelligent Vehicles Symposium, 2005, pp. 224–229. IEEE (2005)
Subr, K., Majumder, A., Irani, S.: Greedy algorithm for local contrast enhancement of images. In: Roli, F., Vitulano, S. (eds.) Image Analysis and Processing – ICIAP 2005, pp. 171–179. Springer, Berlin, Heidelberg (2005). https://doi.org/10.1007/11553595_21
Land, E.H.: Recent advances in Retinex theory and some implications for cortical computations: color vision and the natural image. Proc. Nat. Acad. Sci. 80(16), 5163–5169 (1983)
Lau, H., Levine, M.: Finding a small number of regions in an image using low-level features. Pattern Recogn. 35(11), 2323–2339 (2002). https://doi.org/10.1016/S0031-3203(01)00230-8
Girshick, R., Donahue, J., Darrell, T., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, pp. 580–587 (2014)
Uijlings, J.R.R., Van De Sande, K.E.A., Gevers, T., et al.: Selective search for object recognition. Int. J. Comput. Vis. 104(2), 154–171 (2013)
Zitnick, C.L., Dollár, P.: Edge boxes: locating object proposals from edges. In: Fleet, David, Pajdla, Tomas, Schiele, Bernt, Tuytelaars, Tinne (eds.) Computer Vision – ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V, pp. 391–405. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_26
Girshick R. Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, Honolulu, HI, pp. 1440–1448 (2015)
Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, SPAIN, Barcelona, pp. 91–99 (2015)
Acknowledgements
This work was supported by Heilongjiang Provincial Natural Science Foundation of China: LH2020F039.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Xin, M., Wang, Y., Suo, X. (2021). Based on Fast-RCNN Multi Target Detection of Crop Diseases and Pests in Natural Light. In: Abawajy, J., Xu, Z., Atiquzzaman, M., Zhang, X. (eds) 2021 International Conference on Applications and Techniques in Cyber Intelligence. ATCI 2021. Lecture Notes on Data Engineering and Communications Technologies, vol 81. Springer, Cham. https://doi.org/10.1007/978-3-030-79197-1_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-79197-1_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-79196-4
Online ISBN: 978-3-030-79197-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)