GENG Hui-qiang,ZHANG Hua,XUE Yan-bing,ZHOU Mian,XU Guang-ping,GAO Zan.Semantic image segmentation with fused CNN features[J].Optoelectronics Letters,2017,13(5):381-385 |
Semantic image segmentation with fused CNN features |
Author Name | Affiliation | GENG Hui-qiang | Key Laboratory of Computer Vision and System of Ministry of Education, Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology, Tianjin University of Technology, Tianjin 300384, China | ZHANG Hua | Key Laboratory of Computer Vision and System of Ministry of Education, Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology, Tianjin University of Technology, Tianjin 300384, China | XUE Yan-bing | Key Laboratory of Computer Vision and System of Ministry of Education, Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology, Tianjin University of Technology, Tianjin 300384, China | ZHOU Mian | Key Laboratory of Computer Vision and System of Ministry of Education, Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology, Tianjin University of Technology, Tianjin 300384, China | XU Guang-ping | Key Laboratory of Computer Vision and System of Ministry of Education, Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology, Tianjin University of Technology, Tianjin 300384, China | GAO Zan | Key Laboratory of Computer Vision and System of Ministry of Education, Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology, Tianjin University of Technology, Tianjin 300384, China |
|
Abstract: |
Semantic image segmentation is a task to predict a category label for every image pixel. The key challenge of it is to design a strong feature representation. In this paper, we fuse the hierarchical convolutional neural network (CNN) features and the region-based features as the feature representation. The hierarchical features contain more global information, while the region-based features contain more local information. The combination of these two kinds of features significantly enhances the feature representation. Then the fused features are used to train a softmax classifier to produce per-pixel label assignment probability. And a fully connected conditional random field (CRF) is used as a post-processing method to improve the labeling consistency. We conduct experiments on SIFT flow dataset. The pixel accuracy and class accuracy are 84.4% and 34.86%, respectively. |
Hits: 4253 |
Download times: 0 |
|
View Full Text Download reader |
|
|
|