Rui Ming ^1,2 Qian Gong ^1,2 Chen Yang ^1,2 Haibo Luo ^1,2 Cancan Song ³ Zhiyan Zhou ^4*

• ¹ College of Computer and Big Data, Minjiang University, Fuzhou, China
• ² Fujian Provincial Key Laboratory of Information Processing and Intelligent Control, Minjiang University, Fuzhou, Fujian Province, China
• ³ School of Agricultural Engineering and Food Science, Shandong University of Technology, Zibo, China
• ⁴ Guangdong Laboratory for Lingnan Modern Agriculture, College of Engineering, South China Agricultural University, Guangzhou, China

Monitoring crop spike growth using low-altitude remote sensing images is essential for precision agriculture, as it enables accurate crop health assessment and yield estimation. Despite the advancements in deep learning-based visual recognition, existing crop spike detection methods struggle to balance computational efficiency with accuracy in complex multi-scale environments, particularly on resource-constrained low-altitude remote sensing platforms. To address this gap, we propose FDRMNet, a novel feature diffusion reconstruction mechanism network designed to accurately detect crop spikes in challenging scenarios. The core innovation of FDRMNet lies in its multi-scale feature focus reconstruction and lightweight parameter-sharing detection head, which can effectively improve the computational efficiency of the model while enhancing the model's ability to perceive spike shape and texture.FDRMNet introduces a Multi-Scale Feature Focus Reconstruction module that integrates feature information across different scales and employs various convolutional kernels to capture global context effectively. Additionally, an Attention-Enhanced Feature Fusion Module is developed to improve the interaction between different feature map positions, leveraging adaptive average pooling and convolution operations to enhance the model's focus on critical features. To ensure suitability for low-altitude platforms with limited computational resources, we incorporate a Lightweight Parameter Sharing Detection Head, which reduces the model's parameter count by sharing weights across convolutional layers. According to the evaluation experiments on the global wheat head detection dataset and diverse rice panicle detection dataset, FDRMNet outperforms other state-of-the-art methods with $mAP@.5$ of 94.23\%, 75.13\% and $R^2$ value of 0.969, 0.963 between predicted values and ground truth values. In addition, the model's frames per second and parameters in the two datasets are 227.27,288 and 6.8M, respectively, which maintains the top three position among all the compared algorithms. Extensive qualitative and quantitative experiments demonstrate that FDRMNet significantly outperforms existing methods in spike detection and counting tasks, achieving higher detection accuracy with lower computational complexity. The results underscore the model's superior practicality and generalization capability in real-world applications. This research contributes a highly efficient and computationally effective solution for crop spike detection, offering substantial benefits to precision agriculture practices.