To solve the problems of low recognition rate and poor adaptability of single feature, a feature extraction method named Hilbert-CSP-Huang Transform (HCHT) was proposed based on Hilbert-Huang Transform (HHT) and Common Spatial Pattern (CSP). Firstly, the Intrinsic Mode Function (IMF) was obtained by the Empirical Mode Decomposition (EMD) of original ElectroEncephaloGram (EEG) signals, and the IMF components were merged into a new signal matrix. Secondly, the time-frequency domain features were obtained by Hilbert spectrum analysis. Thirdly, the time-frequency domain features were extended into time-frequency-space features by further CSP decomposition of the constructed signal matrix. Finally, the feature set was classified by Support Vector Machine (SVM). Experiments on the BCI Competition II dataset show that compared with methods based on HHT time-frequency and CSP spatial domain features, the proposed method has the recognition accuracy increased by 7.5, 10.3 and 9.2 percentage points respectively with smaller standard deviation. The online experimental results on the intelligent wheelchair platform show that HCHT can effectively improve the recognition accuracy and robustness.