Yao Zhixin, Xi Renna, Zhang Taihong, Zhao Yunjie, Tian Yongqiang, Hou Wenjing
College of Computer and Information Engineering, Xinjiang Agricultural University, Urumqi 830052, China.
Research Center for Intelligent Agriculture, Ministry of Education Engineering, Urumqi 830052, China.
Sensors (Basel). 2025 Apr 15;25(8):2477. doi: 10.3390/s25082477.
With the advancement of agricultural automation, the demand for road recognition and understanding in agricultural machinery autonomous driving systems has significantly increased. To address the scarcity of instance segmentation data for rural roads and rural unstructured scenes, particularly the lack of support for high-resolution and fine-grained classification, a 20-class instance segmentation dataset was constructed, comprising 10,062 independently annotated instances. An improved StyleGAN2-ADA data augmentation method was proposed to generate higher-quality image data. This method incorporates a decoupled mapping network (DMN) to reduce the coupling degree of latent codes in W-space and integrates the advantages of convolutional networks and transformers by designing a convolutional coupling transfer block (CCTB). The core cross-shaped window self-attention mechanism in the CCTB enhances the network's ability to capture complex contextual information and spatial layouts. Ablation experiments comparing the improved and original StyleGAN2-ADA networks demonstrate significant improvements, with the inception score (IS) increasing from 42.38 to 77.31 and the Fréchet inception distance (FID) decreasing from 25.09 to 12.42, indicating a notable enhancement in data generation quality and authenticity. In order to verify the effect of data enhancement on the model performance, the algorithms Mask R-CNN, SOLOv2, YOLOv8n, and OneFormer were tested to compare the performance difference between the original dataset and the enhanced dataset, which further confirms the effectiveness of the improved module.
随着农业自动化的发展，农业机械自动驾驶系统对道路识别与理解的需求显著增加。为解决农村道路和农村非结构化场景实例分割数据稀缺的问题，特别是缺乏对高分辨率和细粒度分类的支持，构建了一个包含20个类别的实例分割数据集，其中包含10062个独立标注的实例。提出了一种改进的StyleGAN2-ADA数据增强方法来生成更高质量的图像数据。该方法引入了解耦映射网络（DMN）以降低W空间中潜在代码的耦合度，并通过设计卷积耦合传输块（CCTB）融合了卷积网络和Transformer的优点。CCTB中的核心十字形窗口自注意力机制增强了网络捕捉复杂上下文信息和空间布局的能力。对比改进后的StyleGAN2-ADA网络与原始网络的消融实验表明有显著改进，其中初始得分（IS）从42.38提高到77.31，弗雷歇初始距离（FID）从25.09降低到12.42，表明数据生成质量和真实性有显著提高。为验证数据增强对模型性能的影响，对Mask R-CNN、SOLOv2、YOLOv8n和OneFormer算法进行了测试，以比较原始数据集和增强数据集之间的性能差异，这进一步证实了改进模块的有效性。
