Detecting the moisture content of stored maize kernels is critical for minimizing post-harvest losses. To measure the moisture content of maize kernels under low-temperature conditions, a small-strip transmission line device was employed to construct a non-destructive measurement platform. The dielectric constant of maize kernels with varying moisture content was measured at temperatures ranging from −15 °C to 20 °C and frequencies between 1 and 200 MHz. By using the dielectric constant, frequency, and temperature as input variables, along with volume density and scattering parameter characteristics, three moisture content prediction models—SPO-SVM, XGBoost, and GA-BP—were established. The results show that temperature significantly affects the dielectric constant of maize kernels, especially when the moisture levels exceed 22.4%. The prediction model significantly improves the prediction accuracy under low-temperature conditions after introducing the volume density feature. Furthermore, incorporating the multi-phase and amplitude characteristics of scattering parameters further improves the model’s performance. This study verifies the mechanism and behavior of dielectric constant variations in maize kernels under low-temperature conditions. The proposed model effectively mitigates measurement errors caused by the icing of free water and is well suited for measuring maize moisture content under low-temperature conditions.

To address the issues of corn harvester field operations relying on driver visual guidance for row alignment, high labor intensity, and unstable operation accuracy, this study innovatively proposes a “vision-dominant, gateway-enhanced” dual-mode collaborative row-alignment assistance architecture, and independently develops the R²DC-Mask R-CNN instance segmentation network and MCC-KF robust filtering algorithm to form a deeply coupled hardware–software-assisted driving system. The R²DC-Mask R-CNN network is autonomously designed for corn row-detection scenarios, achieving accurate perception in complex field environments; the MCC-KF algorithm innovatively solves the state estimation divergence problem during transient vision failures through a multi-criteria constraint mechanism, ensuring continuous navigation capability; the intelligent gateway and vision system form a confidence-driven master–slave switching mechanism that adaptively enhances system robustness when vision is restricted. Field experiments demonstrate that within the speed range of 0.5–5.0 km/h, the average lateral deviation in the row alignment assisted by the system is 3.82–5.30 cm, the proportion of deviations less than 10 cm exceeds 96%, and all sample deviations remain within 20 cm; at a speed of 3.5 km/h, the system reduces the average grain loss rate from 3.76% under manual operation to 2.65%, a decrease of 29.5%. This system effectively improves row alignment accuracy and harvest quality, providing a practical human–machine collaborative solution for intelligent harvester operations.