AUTHOR=Li Jia-Le , Su Wen-Hao , Zhang He-Yi , Peng Yankun TITLE=A real-time smart sensing system for automatic localization and recognition of vegetable plants for weed control JOURNAL=Frontiers in Plant Science VOLUME=Volume 14 - 2023 YEAR=2023 URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2023.1133969 DOI=10.3389/fpls.2023.1133969 ISSN=1664-462X ABSTRACT=Weeds in the early growth stage have a significant impact on the normal growth of vegetable crops. Weeds compete with the crops resulting in reduced crop yields. The increasing labor cost of manual weeding and the negative impact on human health and the environment caused by the overuse of herbicides are driving the development of smart weeders. The core task that needs to be addressed in developing a smart weeder is to accurately distinguish vegetable crops from weeds in real time. An integrated sensing system can identify target plants with color labels online in an efficient way. In this study, appropriate plant labels allowed the tomato plant locations to be reliably detectable by an integrated system combining computer vision with color mark sensors. The selection scheme of reference, color, area, and category of plant labels for sensor identification was examined. The color mark sensor using the green stem of tomato as the reference exhibited higher performance than that of weed in identifying the plant label. The white physical labels were more readily detected than those in red and green. The lower areas of the plant labels showed a higher recognition accuracy than the middle and upper areas. The topical marker applied to the lower part of the plant stem is an alternative to that of the physical label. The effectiveness of the six sensors used by the system to detect plant labels was demonstrated. The computer vision algorithm proposed in this study was specially developed for the sensing system, yielding the highest overall accuracy of 95.19% for tomato and pakchoi localization. The proposed sensor-based system is highly accurate and reliable for automatic localization of different vegetables in real time.