Attention mechanism is beneficial to capture the contextual information in visual task. This paper proposes a feature-enhanced position attention network (FPANet) for semantic segmentation based on framework of FCN. On the top of dilated FCN, we design a feature integration module, which aggregates the context over local features by expanding the receptive field and multiscale representation, to promote a position attention module, which models spatial interdependencies over features, so as to form a feature-enhanced position attention module to enhance the discrimination of features for better semantic segmentation. Experimental comparisons show that our proposed FPANet is superior to other state-of-the-art models in the performance of segmentation accuracy on datasets PASCAL VOC 2012 and Cityscapes.