AUTHOR=Lv Meibo , Zhou Pengyao , Yu Tong , Wang Wuwei , Zhou Daming 

TITLE=Leaf and Stem-Based Dew Detection Algorithm via Multi-Convolutional Edge Detection Networks

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.861534

DOI=10.3389/fpls.2022.861534

ISSN=1664-462X

ABSTRACT=During the process of drought and rehydration, dew can promote the rapid activation of photosynthetic activity and delay the wilting time of plant leaves, etc. It can be seen that the amount of dew will affect the growth of plants. However, limited work is being done to detect and measure the dew.  Accordingly, in this work, a dew statistical method based on computer vision processing was developed. In our framework, the dew can be accurately measured by isolating the background area based on color features and detecting the edge and statistical area. In this scheme, the multi-convolutional edge detection networks based on contour search loss function are proposed as the main implementation algorithm of edge detection. Through color feature background region segmentation and the proposed edge detection networks, our algorithm can detect dew in complex plant background. Experimental results show that the proposed method gains a favorable detection accuracy compared with other edge detection methods. Moreover, we achieve the best Optimal Image Scale (OIS) and Optimal Dataset Scale (ODS) when testing with different pixel values, which illustrates the robustness of our method in dew detection.