用高效注意力机制解决无人机影像中玉米点定位难题
An Efficient Additive Kolmogorov-Arnold Transformer for Point-Level Maize Localization in Unmanned Aerial Vehicle Imagery
- 引入柯尔莫哥洛夫-阿诺德网络替代传统模块，增强小目标特征提取能力
- 在超高清图像上实现62.8% F1分数，计算量降低12.6%，推理速度提升20.7%
- 适用于高分辨率农业遥感，尤其适合稀疏分布的作物点定位任务
高分辨率无人机摄影测量已成为精准农业关键技术，支持厘米级作物监测与点级植株定位。然而，无人机影像中的点级玉米定位仍面临三大挑战：（1）目标像素比极低，通常不足0.1%；（2）对超过3000×4000像素的超高清图像，传统二次注意力计算成本过高；（3）农田场景特有的稀疏分布与环境变化，通用视觉模型难以应对。为此，本文提出加性柯尔莫哥洛夫-阿诺德变换器（AKT），以帕德柯尔莫哥洛夫-阿诺德网络（PKAN）模块替代标准MLP，提升小目标特征表达能力，并设计PKAN加性注意力（PAA）建模多尺度空间依赖，显著降低计算复杂度。此外，构建了点级玉米定位（PML）数据集，包含1,928张高分辨率无人机图像及约501,000个点标注，覆盖真实田间条件。大量实验表明，AKT平均F1得分达62.8%，优于现有方法4.2%，同时减少12.6%的浮点运算量，推理吞吐量提升20.7%。下游任务中，株距计数均方误差为7.1，植株间距估计均方根误差为1.95–1.97厘米。结果表明，将柯尔莫哥洛夫-阿诺德表示理论与高效注意力机制结合，可有效支撑高分辨率农业遥感应用。
原文摘要 · Abstract (English)
High-resolution UAV photogrammetry has become a key technology for precision agriculture, enabling centimeter-level crop monitoring and point-level plant localization. However, point-level maize localization in UAV imagery remains challenging due to (1) extremely small object-to-pixel ratios, typically less than 0.1%, (2) prohibitive computational costs of quadratic attention on ultra-high-resolution images larger than 3000 x 4000 pixels, and (3) agricultural scene-specific complexities such as sparse object distribution and environmental variability that are poorly handled by general-purpose vision models. To address these challenges, we propose the Additive Kolmogorov-Arnold Transformer (AKT), which replaces conventional multilayer perceptrons with Pade Kolmogorov-Arnold Network (PKAN) modules to enhance functional expressivity for small-object feature extraction, and introduces PKAN Additive Attention (PAA) to model multiscale spatial dependencies with reduced computational complexity. In addition, we present the Point-based Maize Localization (PML) dataset, consisting of 1,928 high-resolution UAV images with approximately 501,000 point annotations collected under real field conditions. Extensive experiments show that AKT achieves an average F1-score of 62.8%, outperforming state-of-the-art methods by 4.2%, while reducing FLOPs by 12.6% and improving inference throughput by 20.7%. For downstream tasks, AKT attains a mean absolute error of 7.1 in stand counting and a root mean square error of 1.95-1.97 cm in interplant spacing estimation. These results demonstrate that integrating Kolmogorov-Arnold representation theory with efficient attention mechanisms offers an effective framework for high-resolution agricultural remote sensing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。