Abstract
Excessive use of agrochemicals for weed controlling infestation has serious agronomic and environmental repercussions associated. An appropriate amount of pesticide/ chemicals is essential for achieving the desired smart farming and precision agriculture (PA). In this regard, targeted weed control will be a critical component significantly helping in achieving the goal. A prerequisite for such control is a robust classification system that could accurately identify weed crops in a field. In this regard, Unmanned Aerial Vehicles (UAVs) can acquire high-resolution images providing detailed information for the distribution of weeds and offers a cost-efficient solution. Most of the established classification systems deploying UAV imagery are supervised, relying on image labels. However, this is a time-consuming and tedious task. In this study, the development of an optimized semi-supervised learning approach is proposed, offering a semi-supervised generative adversarial network for crops and weeds classification at early growth stage. The proposed algorithm consists of a generator that provides extra training data for the discriminator, which distinguishes weeds and crops using a small number of image labels. The proposed system was evaluated extensively on the Red Green Blue (RGB) images obtained by a quadcopter in two different croplands (pea and strawberry). The method achieved an average accuracy of 90% when 80% of training data was unlabeled. The proposed system was compared with several standards supervised learning classifiers and the results demonstrated that this technique could be applied for challenging tasks of crops and weeds classification, mainly when the labeled samples are small at less training time.
Highlights
Agriculture plays a vital role in the global economy and has led to extensive studies to increase crop yield [1, 2]
supervised generative adversarial network (SGAN) application has not been explored for classifying Red Green Blue (RGB) imagery of early growth stage crops and our study aims to address this research gap, by using SGAN for classifying crops and weeds in early growth croplands, using Unmanned Aerial Vehicles (UAVs) RGB imagery
The developed semi-supervised method achieved an overall accuracy of almost 90% for two croplands when the labeled samples were only 20%. It performed better classification performance when the labeled samples were increased and achieved an overall accuracy of 94.17% when 80% of the samples were labeled; it is because that the proposed semi-supervised Generative Adversarial Network (GAN) might result in incorrectly labeled samples, which made it impossible for newly labeled images to perform to the original labeled samples
Summary
Agriculture plays a vital role in the global economy and has led to extensive studies to increase crop yield [1, 2]. Agrochemicals (Herbicides and Pesticides) are used for controlling weed infestation and allow the efficacy of almost 75% [3, 4] Site-specific weed management (SSWM) recommends chemical saving by utilizing an adequate amount of chemicals based on weed density [4] In this regard, an accurate classification system of crops and weeds could significantly promote chemical saving while enhancing its effectiveness by providing decision-making information for variable-rate spraying machines. An accurate classification system of crops and weeds could significantly promote chemical saving while enhancing its effectiveness by providing decision-making information for variable-rate spraying machines This classification system is obtained either by ground sampling or by remote detection [3]. The reliability of remote sensing fields is significantly higher than ground visits [4, 6]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
