激光与光电子学进展, 2020, 57 (14): 141004, 网络出版: 2020-07-24  

用于多光谱语义分割的LBP特征增强神经网络 下载: 543次

A Neural Network for Multi-Spectral Semantic Segmentation Based on LBP Feature Enhancement
作者单位
1 天津大学微电子学院, 天津 300072
2 天津市成像与感知微电子技术重点实验室, 天津 300072
摘要
为了提升多光谱图像语义分割的精度,提出了一种基于局部二值模式(LBP)特征增强的语义分割神经网络模型。该模型通过两个大小分别为3×3和5×5的LBP特征提取算子,对原始红外图像进行边缘信息提取,获得了边缘特征图。将原始RGB图像、红外图像和获得的LBP特征图输入到一个包含34层残差网络的模型中进行语义分割。实验结果表明,本文提出的基于LBP特征增强的神经网络模型,在RGB-Thermal数据集上取得了60.7%的平均准确率和51.9%的平均交并比,明显优于其他对比模型。同时在可视化结果上,本文模型的结果也更加清晰准确。
Abstract
In order to improve the accuracy of multi-spectral image semantic segmentation, a neural network model based on local binary pattern (LBP) feature enhancement is proposed. The model obtains two feature maps from a single infrared image by two LBP feature extraction operators with the size of 3×3 and 5×5, respectively. The RGB image, the infrared image, and the LBP feature maps are imported into a neural network model with a 34-layer residual network for semantic segmentation. The experimental results show that the proposed neural network model can achieve an average accuracy of 60.7% and an average intersection over union of 51.9% on the RGB-Thermal dataset. The results are superior to other comparative methods. At the same time, in the visualization results, the results of proposed model are also more clear and accurate.

史兴萍, 徐江涛, 蒋永唐, 秦书臻, 路凯歌. 用于多光谱语义分割的LBP特征增强神经网络[J]. 激光与光电子学进展, 2020, 57(14): 141004. Xingping Shi, Jiangtao Xu, Yongtang Jiang, Shuzhen Qin, Kaige Lu. A Neural Network for Multi-Spectral Semantic Segmentation Based on LBP Feature Enhancement[J]. Laser & Optoelectronics Progress, 2020, 57(14): 141004.

引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!