Next Article in Journal
Implementation of a Modified Faster R-CNN for Target Detection Technology of Coastal Defense Radar
Previous Article in Journal
Horizon Line Detection in Historical Terrestrial Images in Mountainous Terrain Based on the Region Covariance
Previous Article in Special Issue
Assessing Forest Phenology: A Multi-Scale Comparison of Near-Surface (UAV, Spectral Reflectance Sensor, PhenoCam) and Satellite (MODIS, Sentinel-2) Remote Sensing
Article

Optimized Deep Learning Model as a Basis for Fast UAV Mapping of Weed Species in Winter Wheat Crops

1
Leibniz Institute for Agricultural Engineering and Bioeconomy e.V., Potsdam-Bornim, Max-Eyth-Allee 100, 14469 Potsdam, Germany
2
Institute of Computer Science, University of Potsdam, August-Bebel-Str. 89, 14482 Potsdam, Germany
3
Julius Kühn-Institut, Institute for Plant Protection in Field Crops and Grassland, Messeweg 11–12, 38104 Braunschweig, Germany
*
Author to whom correspondence should be addressed.
Academic Editors: Javier Cardenal Escarcena, Jorge Delgado García and Joaquim João Sousa
Remote Sens. 2021, 13(9), 1704; https://doi.org/10.3390/rs13091704
Received: 7 March 2021 / Revised: 9 April 2021 / Accepted: 25 April 2021 / Published: 28 April 2021
(This article belongs to the Special Issue UAV Photogrammetry for Environmental Monitoring)
Weed maps should be available quickly, reliably, and with high detail to be useful for site-specific management in crop protection and to promote more sustainable agriculture by reducing pesticide use. Here, the optimization of a deep residual convolutional neural network (ResNet-18) for the classification of weed and crop plants in UAV imagery is proposed. The target was to reach sufficient performance on an embedded system by maintaining the same features of the ResNet-18 model as a basis for fast UAV mapping. This would enable online recognition and subsequent mapping of weeds during UAV flying operation. Optimization was achieved mainly by avoiding redundant computations that arise when a classification model is applied on overlapping tiles in a larger input image. The model was trained and tested with imagery obtained from a UAV flight campaign at low altitude over a winter wheat field, and classification was performed on species level with the weed species Matricaria chamomilla L., Papaver rhoeas L., Veronica hederifolia L., and Viola arvensis ssp. arvensis observed in that field. The ResNet-18 model with the optimized image-level prediction pipeline reached a performance of 2.2 frames per second with an NVIDIA Jetson AGX Xavier on the full resolution UAV image, which would amount to about 1.78 ha h−1 area output for continuous field mapping. The overall accuracy for determining crop, soil, and weed species was 94%. There were some limitations in the detection of species unknown to the model. When shifting from 16-bit to 32-bit model precision, no improvement in classification accuracy was observed, but a strong decline in speed performance, especially when a higher number of filters was used in the ResNet-18 model. Future work should be directed towards the integration of the mapping process on UAV platforms, guiding UAVs autonomously for mapping purpose, and ensuring the transferability of the models to other crop fields. View Full-Text
Keywords: ResNet; deep residual networks; UAV imagery; embedded systems; crop monitoring; image classification; site-specific weed management; real-time mapping ResNet; deep residual networks; UAV imagery; embedded systems; crop monitoring; image classification; site-specific weed management; real-time mapping
Show Figures

Graphical abstract

MDPI and ACS Style

de Camargo, T.; Schirrmann, M.; Landwehr, N.; Dammer, K.-H.; Pflanz, M. Optimized Deep Learning Model as a Basis for Fast UAV Mapping of Weed Species in Winter Wheat Crops. Remote Sens. 2021, 13, 1704. https://doi.org/10.3390/rs13091704

AMA Style

de Camargo T, Schirrmann M, Landwehr N, Dammer K-H, Pflanz M. Optimized Deep Learning Model as a Basis for Fast UAV Mapping of Weed Species in Winter Wheat Crops. Remote Sensing. 2021; 13(9):1704. https://doi.org/10.3390/rs13091704

Chicago/Turabian Style

de Camargo, Tibor; Schirrmann, Michael; Landwehr, Niels; Dammer, Karl-Heinz; Pflanz, Michael. 2021. "Optimized Deep Learning Model as a Basis for Fast UAV Mapping of Weed Species in Winter Wheat Crops" Remote Sens. 13, no. 9: 1704. https://doi.org/10.3390/rs13091704

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop