Research Article | Open Access

Volume 2024 |Article ID 0122 | https://doi.org/10.34133/plantphenomics.0122

Channel Attention GAN-Based Synthetic Weed Generation for Precise Weed Identification

Tang Li,¹ Motoaki Asai,² Yoichiro Kato,¹ Yuya Fukano,³ and Wei Guo ¹

¹Graduate School of Agricultural and Life Sciences, The University of Tokyo, Tokyo 188-0002, Japan.
²Institute for Plant Protection, National Agriculture and Food Research Organization, Fukushima 960-2156, Japan
³Graduate School of Horticulture, Chiba University, Chiba 271-0092, Japan

Abstract

Weed is a major biological factor causing declines in crop yield. However, widespread herbicide application and indiscriminate weeding with soil disturbance are of great concern because of their environmental impacts. Site-specific weed management (SSWM) refers to a weed management strategy for digital agriculture that results in low energy loss. Deep learning is crucial for developing SSWM, as it distinguishes crops from weeds and identifies weed species. However, this technique requires substantial annotated data, which necessitates expertise in weed science and agronomy. In this study, we present a channel attention mechanism-driven generative adversarial network (CA-GAN) that can generate realistic synthetic weed data. The performance of the model was evaluated using two datasets: the public segmented Plant Seedling Dataset (sPSD), featuring nine common broadleaf weeds from arable land, and the Institute for Sustainable Agro-ecosystem Services (ISAS) dataset, which includes five common summer weeds in Japan. Consequently, the synthetic dataset generated by the proposed CA-GAN obtained an 82.63% recognition accuracy on the sPSD and 93.46% on the ISAS dataset. The Fréchet inception distance (FID) score test measures the similarity between a synthetic and real dataset, and it has been shown to correlate well with human judgments of the quality of synthetic samples. The synthetic dataset achieved a low FID score (20.95 on the sPSD and 24.31 on the ISAS dataset). Overall, the experimental results demonstrated that the proposed method outperformed previous state-of-the-art GAN models in terms of image quality, diversity, and discriminability, making it a promising approach for synthetic agricultural data generation.