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.

Traditional weeds controlling tended to be spraying herbicides in all the fields. Such method not only requires huge quantities of herbicides but impact environment and humans health. In this paper, we propose a new method of crop/weeds discrimination using imagery provided by an unmanned aerial vehicle (UAV). This method is based on the vegetation skeleton, the Hough transform and the spatial relationship of superpixels created by the simple linear iterative clustering (SLIC). The combination of the spatial relationship of superpixels and their positions in the detected crop lines allows to detect intraline weeds. Our method shows its robustness in presence of weed patches close to crop lines as well as for the detection of crop lines as for weed detection.

In recent years, weeds is responsible for most of the agricultural yield losses. To deal with this problem Omega, farmers resort to spraying pesticides throughout the field. Such method not only requires huge quantities of herbicides but impact environment and humans health. In this paper, we propose a new vision-based classification system for identifying weeds in vegetable fields such as spinach, beet and bean by applying convolutional neural networks (CNNs) and crop lines information. In this study, we combine deep learning with line detection to enforce the classification procedure. The proposed method is applied to high-resolution Unmanned Aerial Vehicles (UAV) images of vegetables taken about 20 m above the soil. We have performed an extensive evaluation of the method with real data. The results showed that the proposed method of weeds detection was effective in different crop fields. The overall precision for the beet, spinach and bean is respectively of 93%, 81% and 69%.