Next Article in Journal
Derivation of Three-Dimensional Displacement Vectors from Multi-Temporal Long-Range Terrestrial Laser Scanning at the Reissenschuh Landslide (Tyrol, Austria)
Next Article in Special Issue
Real-Time Prediction of Crop Yields From MODIS Relative Vegetation Health: A Continent-Wide Analysis of Africa
Previous Article in Journal
Assessment of Multi-Source Evapotranspiration Products over China Using Eddy Covariance Observations
Previous Article in Special Issue
Remotely Estimating Beneficial Arthropod Populations: Implications of a Low-Cost Small Unmanned Aerial System
Article

Deep Learning with Unsupervised Data Labeling for Weed Detection in Line Crops in UAV Images

1
University of Orleans, PRISME, EA 4229, F45072 Orleans, France
2
INSA Centre Val de Loire, PRISME, EA 4229, F18020 Bourges, France
*
Author to whom correspondence should be addressed.
Remote Sens. 2018, 10(11), 1690; https://doi.org/10.3390/rs10111690
Received: 4 September 2018 / Revised: 15 October 2018 / Accepted: 18 October 2018 / Published: 26 October 2018
In recent years, weeds have been responsible for most agricultural yield losses. To deal with this threat, farmers resort to spraying the fields uniformly with herbicides. This method not only requires huge quantities of herbicides but impacts the environment and human health. One way to reduce the cost and environmental impact is to allocate the right doses of herbicide to the right place and at the right time (precision agriculture). Nowadays, unmanned aerial vehicles (UAVs) are becoming an interesting acquisition system for weed localization and management due to their ability to obtain images of the entire agricultural field with a very high spatial resolution and at a low cost. However, despite significant advances in UAV acquisition systems, the automatic detection of weeds remains a challenging problem because of their strong similarity to the crops. Recently, a deep learning approach has shown impressive results in different complex classification problems. However, this approach needs a certain amount of training data, and creating large agricultural datasets with pixel-level annotations by an expert is an extremely time-consuming task. In this paper, we propose a novel fully automatic learning method using convolutional neuronal networks (CNNs) with an unsupervised training dataset collection for weed detection from UAV images. The proposed method comprises three main phases. First, we automatically detect the crop rows and use them to identify the inter-row weeds. In the second phase, inter-row weeds are used to constitute the training dataset. Finally, we perform CNNs on this dataset to build a model able to detect the crop and the weeds in the images. The results obtained are comparable to those of traditional supervised training data labeling, with differences in accuracy of 1.5% in the spinach field and 6% in the bean field. View Full-Text
Keywords: weed detection; deep learning; unmanned aerial vehicle; image processing; precision agriculture; crop line detection weed detection; deep learning; unmanned aerial vehicle; image processing; precision agriculture; crop line detection
Show Figures

Figure 1

MDPI and ACS Style

Bah, M.D.; Hafiane, A.; Canals, R. Deep Learning with Unsupervised Data Labeling for Weed Detection in Line Crops in UAV Images. Remote Sens. 2018, 10, 1690. https://doi.org/10.3390/rs10111690

AMA Style

Bah MD, Hafiane A, Canals R. Deep Learning with Unsupervised Data Labeling for Weed Detection in Line Crops in UAV Images. Remote Sensing. 2018; 10(11):1690. https://doi.org/10.3390/rs10111690

Chicago/Turabian Style

Bah, M D., Adel Hafiane, and Raphael Canals. 2018. "Deep Learning with Unsupervised Data Labeling for Weed Detection in Line Crops in UAV Images" Remote Sensing 10, no. 11: 1690. https://doi.org/10.3390/rs10111690

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
Back to TopTop