Abstract
Appropriate Site Specific Weed Management (SSWM) is crucial to ensure the crop yields. Within SSWM of large-scale area, remote sensing is a key technology to provide accurate weed distribution information. Compared with satellite and piloted aircraft remote sensing, unmanned aerial vehicle (UAV) is capable of capturing high spatial resolution imagery, which will provide more detailed information for weed mapping. The objective of this paper is to generate an accurate weed cover map based on UAV imagery. The UAV RGB imagery was collected in 2017 October over the rice field located in South China. The Fully Convolutional Network (FCN) method was proposed for weed mapping of the collected imagery. Transfer learning was used to improve generalization capability, and skip architecture was applied to increase the prediction accuracy. After that, the performance of FCN architecture was compared with Patch_based CNN algorithm and Pixel_based CNN method. Experimental results showed that our FCN method outperformed others, both in terms of accuracy and efficiency. The overall accuracy of the FCN approach was up to 0.935 and the accuracy for weed recognition was 0.883, which means that this algorithm is capable of generating accurate weed cover maps for the evaluated UAV imagery.
Highlights
Many agricultural crops require the use of herbicides as essential tools for maintaining the quality and quantity of crop production [1]
The objectives of this paper are to: (1) Evaluate the feasibility of Fully Convolutional Network (FCN) method, which is usually used in computer vision field, on application of accurate weed mapping from the unmanned aerial vehicle (UAV) imagery; (2) Apply transfer learning method to improve the generalization capability; (3) Use skip architecture to increase the prediction accuracy; (4) Compare the proposed method with other methods in the application of weed mapping
In contrast with AlexNet and GoogLeNet, the FCN network based on the pretrained VGG-16 achieved the highest score in terms of prediction accuracy, so the VGG 16-layer net was chosen as the basic architecture extended to FCN
Summary
Many agricultural crops require the use of herbicides as essential tools for maintaining the quality and quantity of crop production [1]. The inappropriate use of herbicides could cause yield reduction and environmental pollution. The main reason for this problem is that, the usual practice of weed management is to broadcast herbicides over the entire field, even within the weed-free areas [2]. In the field of Site Specific Weed Management (SSWM), there is a need for developing a new strategy to solve the problem of current weed control practices.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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
