Abstract
Mechanical water stress assessment is needed in agriculture to mechanically cultivate high-sugar-content crops. Although previous methods estimate water stress accurately, no method has been practically applied yet due to the high cost of equipment. Thus, the previous methods have a trade-off relationship between cost and estimation accuracy. In this paper, we propose a method for estimating water stress on the basis of plant images and sensor data collected from inexpensive equipment. Specifically, a motion-specialized deep convolutional descriptor (MDCD), which is a novel image descriptor that extracts motion features among multiple sequential images without considering appearance in each image, expresses plant wilt strongly related to water stress. Implicit exclusion of appearance enables extraction of general features of plant wilt, which is insulated from the effect of differences in shapes and colors of places and individual plants. We evaluated the performance of the proposed method using enormous agricultural data collected from a greenhouse. Accordingly, the proposed method reduced the error of mean absolute error (MAE) by approximately 25% compared with a naive convolutional neural network (CNN) using original images. The results show that the MDCD enhances temporal information, while reducing spatial information, and expresses the features of plant wilt appropriately.
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
Similar content being viewed by others
References
Richards, L.A., Gardner, W.: Tensiometers for measuring the capillary tension of soil water. J. Am. Soc. Agron. 28(1), 352–358 (1936)
Topp, G.C., Davis, J.L., Annan, A.P.: Electromagnetic determination of soil water content: measurements in coaxial transmission lines. Water Resour. Res. 16(3), 574–582 (1980)
López-López, R., RamÃrez, R.A., Sánchez-Cohen, I., Bustamante, W.O., González-Lauck, V.: Evapotranspiration and crop water stress index in mexican husk tomatoes (Physalis ixocarpa Brot). In: Evapotranspiration–From Measurements to Agricultural and Environmental Applications, p. 187. InTech (2011)
Takayama, K., Nishina, H., Iyoki, S., Arima, S., Hatou, K., Ueka, Y., Miyoshi, Y.: Early detection of drought stress in tomato plants with chlorophyll fluorescence imaging–practical application of the speaking plant approach in a greenhouse–. IFAC Proc. (IFAC-PapersOnline) 44(1), 1785–1790 (2011)
Othman, M.F., Shazali, K.: Wireless sensor network applications: a study in environment monitoring system. Procedia Eng. 41, 1204–1210 (2012)
Park, D.H., Park, J.W.: Wireless sensor network-based greenhouse environment monitoring and automatic control system for dew condensation prevention. Sensors 11(4), 3640–3651 (2011)
Ibayashi, H., Kaneda, Y., Imahara, J., Oishi, N., Kuroda, M., Mineno, H.: A reliable wireless control system for tomato hydroponics. Sensors 16(5), 644 (2016)
Huguet, J.G., Li, S.H., Lorendeau, J.Y., Pelloux, G.: Specific micromorphometric reactions of fruit trees to water stress and irrigation scheduling automation. J. Hortic. Sci. 67(5), 631–640 (1992)
Goldhamer, D.A., Fereres, E.: Irrigation scheduling protocols using continuously recorded trunk diameter measurements. Irrig. Sci. 20(3), 115–125 (2001)
Gallardo, M., Thompson, R.B., Valdez, L.C., Fernández, M.D.: Use of stem diameter variations to detect plant water stress in tomato. Irrig. Sci. 24(4), 241–255 (2006)
Wang, X., Meng, Z., Chang, X., Deng, Z., Li, Y., Lv, M.: Determination of a suitable indicator of tomato water content based on stem diameter variation. Sci. Hortic. 215, 142–148 (2017)
Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS, Montreal, pp. 568–576 (2014)
Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: CVPR, Las Vegas, pp. 1933–1941 (2016)
Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV, Santiago, pp. 4489–4497 (2015)
Zhou, J., Hong, X., Su, F., Zhao, G.: Recurrent convolutional neural network regression for continuous pain intensity estimation in video. In: CVPR Workshops, Las Vegas, pp. 84–92 (2016)
Weinzaepfel, P., Revaud, J., Harchaoui, Z., Schmid, C.: DeepFlow: large displacement optical flow with deep matching. In: ICCV, Sydney, pp. 1385–1392 (2013)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: ICCV, Santiago, pp. 1026–1034 (2015)
Smith, L.N., Topin, N.: Deep convolutional neural network design patterns. arXiv preprint arXiv:1609.05672 (2016)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
Acknowledgements
This work was supported by JST PRESTO Grant Number JPMJPR15O5, Japan. And, we greatly appreciate Mr. Oishi, Mr. Imahara and Mr. Maejima, Shizuoka Prefectural Research Institute of Agriculture and Forestry.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Shibata, S., Kaneda, Y., Mineno, H. (2017). Motion-Specialized Deep Convolutional Descriptor for Plant Water Stress Estimation. In: Boracchi, G., Iliadis, L., Jayne, C., Likas, A. (eds) Engineering Applications of Neural Networks. EANN 2017. Communications in Computer and Information Science, vol 744. Springer, Cham. https://doi.org/10.1007/978-3-319-65172-9_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-65172-9_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-65171-2
Online ISBN: 978-3-319-65172-9
eBook Packages: Computer ScienceComputer Science (R0)