A multi-input multi-output (MIMO) detection scheme that requires considerable low complexity but still achieves the near optimal performance is proposed. The fundamental idea of the proposed MIMO detection scheme consists of two points: 1) the computational complexity is restrained by a complexity limit in low signal-to-noise ratio (SNR) region; 2) while in high SNR region, the complexity is significantly reduced by the proposed search space method. Comparing with existing fixed-complexity techniques of MIMO detection (e.g., K-best sphere detector and reduced-search maximum-likelihood (RS ML) detection), the significant benefit of proposed detection scheme is that less computational power will be spent for the given data rate, or the throughput of detector can be increased for high SNR cases. According to the simulation results, the near optimal performance can be obtained while the detection complexity is kept considerable small.