“Perception-Topology” Decoupling Framework for Missing Seedling Diagnosis in High-Density Sorghum Rows

The diagnosis of missing seedlings in high-density drill-seeded crops is often hindered by the strong coupling between visual perception and diagnostic rules, which leads to an irreversible cascade amplification of underlying missed detection errors. To address this dilemma, this paper proposes a “Perception–Topology” collaborative decoupling framework oriented toward row structure perception. In the perception phase, a row-structure-enhanced detection model (RS-YOLO) is constructed. It integrates Space-to-Depth (SPD) conversion, a Selective Frequency-domain Aggregation Module (SFAM), and a Row-Structure Attention Mechanism (RSM) to effectively suppress tire rut interference and explicitly reinforce the spatial topological priors of crops. In the diagnostic phase, an Adaptive Intra-row Gap Analysis (AIGA) algorithm is proposed. By utilizing a dynamic median intra-plant spacing scale and core canopy geometric pruning, this algorithm fundamentally reformulates missing seedling diagnosis into a physical interruption metric of one-dimensional graph connectivity. Evaluated on a finely reconstructed UAV-based sorghum imagery dataset, RS-YOLO achieved a significant improvement of 2.7% in precision and 3.2% in recall over the baseline model, providing a structure-aligned, high-confidence input for the diagnostic process. Based on this perceptual foundation, the AIGA algorithm ultimately achieved a diagnostic precision of 96.11% and a recall of 91.48% without the need for negative sample annotations. This framework effectively severs the propagation chain of perceptual errors, providing a noise-robust and highly physically interpretable new paradigm for the automated inspection of field population structures.