To address the limitations of existing wearable gait recognition, such as drift in static actions and difficulty in recognizing transition states, this paper proposed a gait recognition system based on the data fusion of MEMS Inertial Measurement Units (IMUs) and flexible plantar pressure sensors. A low-power wearable device comprising four inertial and two pressure sensing nodes was developed to achieve synchronized multi-source data collection. Regarding the algorithm, a sensor-characteristic-based two-stage hierarchical framework was constructed. The first stage utilized plantar pressure features to efficiently decouple static postures from dynamic gaits. The second stage employed a lightweight Support Vector Machine combined with a Finite State Machine for static and transitional actions, while an ensemble learning model based on Soft Voting was used for complex dynamic gaits. Experimental results under Leave-One-Out Cross-Validation demonstrate a comprehensive recognition accuracy of 96.17%, with 100% accuracy for standing and 97% for sit-to-stand transitions. These findings validate the significant advantages of the multi-modal fusion approach in enhancing the robustness and generalization capabilities of gait recognition.