AgriGAN: Unpaired image dehazing via A Cycle-Consistent Generative Adversarial Network for the Agricultural Plant Phenotype

Abstract

Abstract Artificially extracted agricultural phenotype information has high subjectivity and low accuracy, and the use of image extraction information is easily disturbed by haze. Moreover, the agricultural image dehazing method used to extract such information is ineffective, as the images often contain unclear texture information and image colors. To address these shortcomings, we propose unpaired image dehazing via a cycle-consistent generative adversarial network for the agricultural plant phenotype (AgriGAN). The algorithm improves the dehazing performance of the network by adding the atmospheric scattering model, which improves the discriminator model, and uses the whole-detail consistent discrimination method to improve the efficiency of the discriminator so that the adversarial network can accelerate the convergence to the Nashi equilibrium state. Finally, the dehazed images are obtained by training with network adversarial loss + cycle consistent loss. Experiments and a comparative analysis were conducted to evaluate the algorithm, and the results show that it improved the dehazing accuracy of agricultural images, retained detailed texture information, and mitigated the problem of color deviation. In turn, useful information was obtained, such as crop height, chlorophyll and nitrogen content, and the presence and extent of disease. The algorithm's object identification and information extraction can be useful in crop growth monitoring and yield and quality estimation.

Plant phenotyping relevance

植物表現型画像から情報を抽出するための画像デヘイズ手法を開発・評価しており、表現型取得の技術が中心である。

Code and data availability

The paper's Data availability section states that the authors' dataset (hazy/haze-free agricultural plant images) and code will be publicly available at the GitHub repository HZSUZJ/DLDF, which matches an allowed URL. This is a paper-specific, publicly actionable asset for the dehazing/phenotyping analysis.