Automated Rice Phenology Stage Mapping Using UAV Images and Deep Learning

  1. Lu, Xiangyu 14
  2. Zhou, Jun 12
  3. Yang, Rui 1
  4. Yan, Zhiyan 3
  5. Lin, Yiyuan 1
  6. Jiao, Jie 1
  7. Liu, Fei 14
  8. González Aguilera, Diego 5
  1. 1 College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China
  2. 2 College of Mechanical and Electrical Engineering, Xinjiang Agricultural University, Urumqi 830052, China
  3. 3 Institute of Agricultural Economics and information, Jiangxi Academy of Agricultural Sciences, Nanchang 330200, China
  4. 4 Huanan Industrial Technology Research Institute, Zhejiang University, Guangzhou 510700, China
  5. 5 Universidad de Salamanca

    Universidad de Salamanca

    Salamanca, España



ISSN: 2504-446X

Year of publication: 2023

Volume: 7

Issue: 2

Pages: 83

Type: Article

DOI: 10.3390/DRONES7020083 GOOGLE SCHOLAR lock_openOpen access editor

More publications in: Drones


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.

Funding information