提出了一种基于特征的双向视差域约束匹配方法。首先提取图像特征点约简候选匹配像素集，然后进行双向唯一性匹配并在匹配过程中根据双目图像的投影特性设计视差域约束，最后设计了一个滑动平均邻域视差来剔除视差值偏差太大的匹配对。实验结果表明，该方法简单快速，匹配成功率高，可处理复杂场景，具有良好的实用价值。

A bidirectional disparity area feature-constrained match method is proposed in this paper. In this method, after feature points of two images extracted, disparity area constraint is designed to reduce candidate match point sets during the process of bidirectional uniqueness constraint correspondence according to the binocular projection characteristics. Then the slipping neighborhood disparity is designed to reject false match points. Experimental results show that the proposed method can be easily implemented for processing complicated scenes and get high precision matching quickly.