文献类型： 外文期刊

作者： Lu, Xiangyu ¹ ; Zhou, Jun ¹ ; Yang, Rui ¹ ; Yan, Zhiyan ⁴ ; Lin, Yiyuan ¹ ; Jiao, Jie ¹ ; Liu, Fei ¹ ;

作者机构： 1.Zhejiang Univ, Coll Biosyst Engn & Food Sci, Hangzhou 310058, Peoples R China

2.Zhejiang Univ, Huanan Ind Technol Res Inst, Guangzhou 510700, Peoples R China

3.Xinjiang Agr Univ, Coll Mech & Elect Engn, Urumqi 830052, Peoples R China

4.Jiangxi Acad Agr Sci, Inst Agr Econ & informat, Nanchang 330200, Peoples R China

关键词： rice phenology; image segmentation; deep learning; UAV images; direct geo-locating

期刊名称：DRONES （ 影响因子：4.8； 五年影响因子：5.5 ）

ISSN：

年卷期： 2023 年 7 卷 2 期

页码：

收录情况： SCI

摘要： Accurate monitoring of rice phenology is critical for crop management, cultivars breeding, and yield estimating. Previously, research for phenology detection relied on time-series data and orthomosaic and manually plotted regions, which are difficult to automate. This study presented a novel approach for extracting and mapping phenological traits directly from the unmanned aerial vehicle (UAV) photograph sequence. First, a multi-stage rice field segmentation dataset containing four growth stages and 2600 images, namely PaddySeg, was built. Moreover, an efficient Ghost Bilateral Network (GBiNet) was proposed to generate trait masks. To locate the trait of each pixel, we introduced direct geo-locating (DGL) and incremental sparse sampling (ISS) techniques to eliminate redundant computation. According to the results on PaddySeg, the proposed GBiNet with 91.50% mean-Intersection-over-Union (mIoU) and 41 frames-per-second (FPS) speed outperformed the baseline model (90.95%, 36 FPS), while the fastest GBiNet_t reached 62 FPS which was 1.7 times faster than the baseline model, BiSeNetV2. Additionally, the measured average DGL deviation was less than 1% of the relative height. Finally, the mapping of rice phenology was achieved by interpolation on trait value-location pairs. The proposed approach demonstrated great potential for automatic rice phenology stage surveying and mapping.