| 多尺度融合增强的图像语义分割算法 |
| |
| 引用本文： | 田启川,孟颖. 多尺度融合增强的图像语义分割算法[J]. 计算机工程与应用, 2021, 57(2): 177-185. DOI: 10.3778/j.issn.1002-8331.2005-0420 |
| |
| 作者姓名： | 田启川 孟颖 |
| |
| 作者单位： | 1.北京建筑大学 电气与信息工程学院，北京 1000442.北京建筑大学 建筑大数据智能处理方法研究北京市重点实验室，北京 100044 |
| |
| 基金项目： | 北京高等学校高水平人才交叉培养"实培计划"支持项目;北京建筑大学研究生教学质量提升项目;北京市教育委员会科技发展计划面上项目;北京建筑大学研究生创新项目 |
| |
| 摘 要： | 针对现有的图像语义分割算法存在小尺度目标丢失和分割不连续的问题，提出多尺度融合增强的图像语义分割算法，该算法在DeeplabV3+网络模型的基础上，通过构建多尺度特征提取和融合增强网络提高了对小目标特征的描述能力，使网络在分割大目标的同时也能获得小目标的特征信息，从而解决了语义分割时小尺度目标丢失和分割不连续的问题。在Cityscapes数据集上实验的结果表明，改进后的算法明显提升了小目标分割精度，解决了分割不连续的问题。最后在公开数据集PASCAL VOC 2012上进一步验证了改进算法的泛化性。
|
| 关 键 词： | 图像语义分割 DeeplabV3+ 高分辨率信息 小目标分割 |
Image Semantic Segmentation Algorithm with Multi-scale Feature Fusion and Enhancement |
| |
| TIAN Qichuan,MENG Ying. Image Semantic Segmentation Algorithm with Multi-scale Feature Fusion and Enhancement[J]. Computer Engineering and Applications, 2021, 57(2): 177-185. DOI: 10.3778/j.issn.1002-8331.2005-0420 |
| |
| Authors: | TIAN Qichuan MENG Ying |
| |
| Affiliation: | 1.School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture Beijing, Beijing 100044 China2.Beijing Key Laboratory of Intelligent Processing for Building Big Data, Beijing University of Civil Engineering and Architecture, Beijing 100044 China |
| |
| Abstract: | For the problems of small-scale target losing and discontinuous segmentation in existing image semantic segmentation, an image semantic segmentation algorithm with multi-scale feature fusion and enhancement is proposed. Based on DeeplabV3+ network, the algorithm improves the ability to describe small target features by building a multi-scale feature extraction and fusion enhancement network. The network can also obtain small target feature while segmenting large targets, so it can solve the problem of the small target losing and the discontinuous segmentation in the semantic segmentation. Experimental results on the Cityscapes dataset show that the improved algorithm significantly improves the accuracy of small target segmentation and optimizes the problem of discontinuous segmentation. Finally, the generalization of the improved algorithm is verified on the public dataset PASCAL VOC 2012. |
| |
| Keywords: | image semantic segmentation DeeplabV3+ high resolution characterizations small target segmentation |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载免费的PDF全文 |
