CTHNet: a network for wheat ear counting with local-global features fusion based on hybrid architecture.

Abstract

Accurate wheat ear counting is one of the key indicators for wheat phenotyping. Convolutional neural network (CNN) algorithms for counting wheat have evolved into sophisticated tools, however because of the limitations of sensory fields, CNN is unable to simulate global context information, which has an impact on counting performance. In this study, we present a hybrid attention network (CTHNet) for wheat ear counting from RGB images that combines local features and global context information. On the one hand, to extract multi-scale local features, a convolutional neural network is built using the Cross Stage Partial framework. On the other hand, to acquire better global context information, tokenized image patches from convolutional neural network feature maps are encoded as input sequences using Pyramid Pooling Transformer. Then, the feature fusion module merges the local features with the global context information to significantly enhance the feature representation. The Global Wheat Head Detection Dataset and Wheat Ear Detection Dataset are used to assess the proposed model. There were 3.40 and 5.21 average absolute errors, respectively. The performance of the proposed model was significantly better than previous studies.

Plant phenotyping relevance

小麦穂数という植物形質をRGB画像から推定する深層学習手法を開発し、複数データセットで性能評価しており、表現型取得・抽出法が中心である。

Code and data availability

The paper uses two publicly available wheat ear image datasets (GWHD and WEDD) as its phenotyping inputs, with explicit public URLs in the data availability statement. No authors' analysis code or trained model is deposited.