AUTHOR=Adhikari Shyam Prasad , Yang Heechan , Kim Hyongsuk TITLE=Learning Semantic Graphics Using Convolutional Encoder–Decoder Network for Autonomous Weeding in Paddy JOURNAL=Frontiers in Plant Science VOLUME=Volume 10 - 2019 YEAR=2019 URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2019.01404 DOI=10.3389/fpls.2019.01404 ISSN=1664-462X ABSTRACT=Weeds in agricultural farms are aggressive growers which compete for nutrition and other resources with the crop and reduce production. The increasing use of chemicals to control them has inadvertent consequences to the human health and the environment. In this work a novel neural network training method combining semantic graphics for data annotation and an advanced encoder-decoder network for (a) automatic crop line detection, and (b) weed (wild millet) detection in paddy field is proposed. The detected crop lines act as guiding line for an autonomous weeding robot for inter-row weeding, whereas the detection of weeds enables autonomous intra-row weeding. The proposed data annotation method, semantic graphics, is intuitive and the desired targets can be annotated easily with minimal labor. Also the proposed “Extended Skip Network” is an improved deep convolutional encoder-decoder network for efficient learning of semantic graphics. Quantitative evaluations of the proposed method demonstrated an increment of 8.04% in mean intersection over union (mIoU), and a significantly higher recall compared to a popular deep learning based object detection approach on the wild-millet detection problem. The proposed method of learning semantic graphics with the enhanced Extended Skip Network leads to 2.08% and 14.75% improvement in IoU and mean pixel deviation, respectively, over the baseline network.