Accurate Weed Mapping and Prescription Map Generation Based on Fully Convolutional Networks Using UAV Imagery

• Published in: Sensors (Basel, Switzerland) Switzerland), 2018-10, Vol.18 (10), p.3299
• Main Authors: Huang, Huasheng, Deng, Jizhong, Lan, Yubin, Yang, Aqing, Deng, Xiaoling, Wen, Sheng, Zhang, Huihui, Zhang, Yali
• Format: Article
• Language: English
• Subjects: FCN; prescription map; semantic labeling; UAV; weed mapping
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s18103299

Chemical control is necessary in order to control weed infestation and to ensure a rice yield. However, excessive use of herbicides has caused serious agronomic and environmental problems. Site specific weed management (SSWM) recommends an appropriate dose of herbicides according to the weed coverage, which may reduce the use of herbicides while enhancing their chemical effects. In the context of SSWM, the weed cover map and prescription map must be generated in order to carry out the accurate spraying. In this paper, high resolution unmanned aerial vehicle (UAV) imagery were captured over a rice field. Different workflows were evaluated to generate the weed cover map for the whole field. Fully convolutional networks (FCN) was applied for a pixel-level classification. Theoretical analysis and practical evaluation were carried out to seek for an architecture improvement and performance boost. A chessboard segmentation process was used to build the grid framework of the prescription map. The experimental results showed that the overall accuracy and mean intersection over union (mean IU) for weed mapping using FCN-4s were 0.9196 and 0.8473, and the total time (including the data collection and data processing) required to generate the weed cover map for the entire field (50 × 60 m) was less than half an hour. Different weed thresholds (0.00⁻0.25, with an interval of 0.05) were used for the prescription map generation. High accuracies (above 0.94) were observed for all of the threshold values, and the relevant herbicide saving ranged from 58.3% to 70.8%. All of the experimental results demonstrated that the method used in this work has the potential to produce an accurate weed cover map and prescription map in SSWM applications.