Maolin Gan
Zhichao Cao
ABSTRACT
Leaf wetness detection is one of the key technologies for preventing plant diseases in agriculture. In this poster, we propose mmLeaf, leveraging a commercial off-the-shelf millimeter-wave (mmWave) radar to detect actual leaf wetness in diverse environments and lighting conditions. mmLeaf captures mmWave signals reflected by monitored leaves with a two-dimensional (2D) scanning system. Then, we use a multiple-input multiple-output (MIMO) array and synthetic aperture radar (SAR) to reconstruct the signal distribution of different planes of the leaves. A deep learning model takes the fused signal distribution as inputs to classify the leaf wetness. We implement mmLeaf using a frequency-modulated continuous-wave (FMCW) radar and evaluate its performance with a potted plant indoors. By exploring the use of mmWave signals, mmLeaf delivers an end-to-end detection framework that achieves up to 90% accuracy in classifying leaf wetness under different distances.
- L Huber and TJ Gillespie. Modeling leaf wetness in relation to plant disease epidemiology. Annual review of phytopathology, 30(1):553--577, 1992.Google Scholar
- Tracy Rowlandson, Mark Gleason, Paulo Sentelhas, Terry Gillespie, Carla Thomas, and Brian Hornbuckle. Reconsidering leaf wetness duration determination for plant disease management. Plant Disease, 99(3):310--319, 2015.Google ScholarCross Ref
- Arth Patel, Won Suk Lee, Natalia A Peres, and Clyde W Fraisse. Strawberry plant wetness detection using computer vision and deep learning. Smart Agricultural Technology, 1:100013, 2021.Google ScholarCross Ref
- PC Sentelhas, JEBA Monteiro, and TJ Gillespie. Electronic leaf wetness duration sensor: why it should be painted. International Journal of Biometeorology, 48(4):202--205, 2004.Google ScholarCross Ref
- eBay. Leaf wetness sensor. https://www.ebay.com/sch/i.html?_from=R40&_trksid=p2047675.m570.l1313&_nkw=Leaf+Wetness+Sensor&_sacat=0.Google Scholar
- Muhammet Emin Yanik, Dan Wang, and Murat Torlak. Development and demonstration of mimo-sar mmwave imaging testbeds. IEEE Access, 8:126019--126038, 2020.Google ScholarCross Ref
- Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.Google Scholar
Index Terms
- Poster: mmLeaf: Versatile Leaf Wetness Detection via mmWave Sensing
Recommendations
A corded shape printed wideband antenna design for multi-standard mobile applications
This paper presents a printed wideband monopole antenna for multi-standard handheld terminals in mobile wireless communications that covers the operating frequency bands of GPS (1.565---1.585 GHz), GSM (1800, 1900, and 2100 MHz), WiMAX (3.2---3.6 GHz), ...
Ultra Wideband PIFA Antenna with Supporting GSM and WiMAX for Mobile Phone Applications
ACCT '15: Proceedings of the 2015 Fifth International Conference on Advanced Computing & Communication TechnologiesIn this paper the PIFA antenna with multiband resonance for GSM 900, GSM 1800, WLAN 2400MHz, Bluetooth, WiMAX, 3G, 4G and UWB frequency from 3.1-10.6 GHz application is presented. Slots or stubs on the ground plane produce lower frequency resonance. ...
Detection of leaf and canopy EWT by calculating REWT from reflectance spectra
The spectral characteristics of and the interaction between leaves and light were analysed based on the optical absorption coefficients of foliar water and biochemical components. The equations for calculating the radiative-equivalent water thickness ...
Comments