The utilization of multi-source sensing data to achieve intelligent perception and refined management of farmland has become a vital research direction in modern agriculture. However, traditional inspection approaches based solely on visual information are highly susceptible to illumination variations, occlusion, and background interference, which makes stable pest detection and accurate crop growth assessment difficult to achieve. To address these problems, we propose a multimodal target perception network for intelligent farmland inspection. By integrating UAV imagery, ground environmental sensor data, and spatial location information, joint perception of farmland pests, diseases, and crop growth status is achieved. In the proposed framework, cross-modal alignment and collaborative encoding mechanisms, a multi-scale target perception structure, and a dynamic multimodal fusion strategy are introduced to collaboratively model information within a unified semantic space. Experimental results on a constructed multimodal farmland dataset demonstrate that the proposed method achieved 87.53% Precision and 89.16% mAP in the pest and disease detection task, and 88.04% Accuracy in the crop growth assessment task, significantly outperforming several mainstream visual detection models and multimodal fusion approaches. The results indicate that this intelligent perception framework can significantly improve the robustness of farmland inspection systems, providing an effective technical pathway for AI-driven precision agriculture decision-making. This technology breaks the barrier between production-side sensing data and e-commerce demand, providing a practical technical solution for agricultural production-marketing synergy, quality premium realization and digital rural revitalization.

In UAV (unmanned aerial vehicle)-enabled precision agriculture, achieving high-accuracy disease diagnosis and yield estimation simultaneously on resource-constrained edge devices remains a significant challenge. Existing solutions are commonly hindered by conflicts in visual feature scales, the absence of explicit agronomic causal logic, and the trade-off between lightweight design and global modeling capability. To address these challenges, a heterogeneous dual-stream state-space framework termed SymbioMamba is proposed. The proposed framework incorporates three key innovations: first, a heterogeneous dual-stream encoder is constructed, in which a micro-texture stream captures high-frequency disease details while a macro-context-scan stream models field-scale biomass continuity; second, a pathology–biomass collaborative interaction (PBCI) module is designed to explicitly inject the biological prior—disease stress leading to yield reduction—into the feature space. Third, a topology-aligning cross-architecture distillation (TACAD) paradigm is introduced to transfer global knowledge from a heavyweight teacher to a lightweight student. Experimental results from a maize UAV dataset comprising 12,074 annotated image patches demonstrate that SymbioMamba achieves 89.4% mAP@0.5 and an $R^2$ of 0.915. Compared to the industry-standard YOLOv11, the framework improves mAP@0.5:0.95 by 2.4% while reducing the parameter count to 6.2 M—a 50% decrease relative to monolithic state-space baselines. Furthermore, yield prediction error is significantly reduced to an RMSE of 485.6 kg/ha. With a compact model size of 6.2 M parameters and 2.4 G FLOPs, SymbioMamba attains an inference speed of 38.2 FPS on the NVIDIA Jetson AGX Orin platform, providing a high-performance, real-time solution for intelligent agricultural phenotypic analysis.