Abstract
Weed control is necessary in rice cultivation, but the excessive use of herbicide treatments has led to serious agronomic and environmental problems. Suitable site-specific weed management (SSWM) is a solution to address this problem while maintaining the rice production quality and quantity. In the context of SSWM, an accurate weed distribution map is needed to provide decision support information for herbicide treatment. UAV remote sensing offers an efficient and effective platform to monitor weeds thanks to its high spatial resolution. In this work, UAV imagery was captured in a rice field located in South China. A semantic labeling approach was adopted to generate the weed distribution maps of the UAV imagery. An ImageNet pre-trained CNN with residual framework was adapted in a fully convolutional form, and transferred to our dataset by fine-tuning. Atrous convolution was applied to extend the field of view of convolutional filters; the performance of multi-scale processing was evaluated; and a fully connected conditional random field (CRF) was applied after the CNN to further refine the spatial details. Finally, our approach was compared with the pixel-based-SVM and the classical FCN-8s. Experimental results demonstrated that our approach achieved the best performance in terms of accuracy. Especially for the detection of small weed patches in the imagery, our approach significantly outperformed other methods. The mean intersection over union (mean IU), overall accuracy, and Kappa coefficient of our method were 0.7751, 0.9445, and 0.9128, respectively. The experiments showed that our approach has high potential in accurate weed mapping of UAV imagery.
Highlights
Rice is the world’s most important crop
Our current work (Figure 5) shared the same fully convolutional framework with previous fully convolutional network (FCN)-8s (Figure 9), there were several new features added to the current approach: (1) residual learning was adopted to address the delegation problem of deep network; (2) atrous convolution was used to reduce the resolution downsampling, the skip architecture in FCN-8s was discarded, resulting in a simplified architecture; (3) simple bilinear interpolation was applied for signal upsampling; unlike deconvolutional operation in FCN-8s, parameters in bilinear interpolation does not require optimization, which may significantly accelerate the training process; (4) the fully connected
From Section 2.2.2, it can be seen that our dataset was split into training set convolution was used to reduce the resolution downsampling, the skip architecture in FCN-8s
Summary
Rice is the world’s most important crop. More than one third of the world’s population relies on rice as their principal food [1]. Weed infestations present great challenges for rice cultivation. Weedy rice populations have been reported in many rice growing areas in the world, from rice transplanting to direct seeding [2]. The weeds compete with rice for light, water, and nutrients, which may cause serious yield losses [3]. Weed control in rice fields is necessary, Sensors 2018, 18, 2113; doi:10.3390/s18072113 www.mdpi.com/journal/sensors
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
