详细信息
基于PP-MRF模型的单目车载红外图像三维重建
Three-Dimensional Reconstruction from Monocular Vehicular Infrared Images Based on PP-MRF Model
文献类型:期刊文献
中文题名:基于PP-MRF模型的单目车载红外图像三维重建
英文题名:Three-Dimensional Reconstruction from Monocular Vehicular Infrared Images Based on PP-MRF Model
作者:沈振一[1,2];孙韶媛[1,2];赵海涛[3]
机构:[1]东华大学信息科学与技术学院,上海201620;[2]东华大学数字化纺织服装技术教育部工程研究中心,上海201620;[3]华东理工大学信息科学与工程学院,上海200237
年份:2015
卷号:41
期号:3
起止页码:341
中文期刊名:东华大学学报(自然科学版)
外文期刊名:Journal of Donghua University(Natural Science)
收录:CSTPCD;;北大核心:【北大核心2014】;CSCD:【CSCD2015_2016】;
基金:国家自然科学基金资助项目(61072090;61205017;61375007)
语种:中文
中文关键词:图像处理;三维重建;车载红外图像;面板参数马尔科夫随机场(PP-MRF);深度估计
外文关键词:image processing; three-dimensional reconstruction; vehicular infrared image; planeparameter-Markov Random Field(PP-MRF); depth estimation
摘要:针对车载红外图像的特点,提出了一种使用超像素分割和面板参数马尔科夫随机场(PPMRF)相结合的单目车载红外图像三维重建方法.该方法首先通过超像素分割得到在纹理和亮度上相近的一系列小的区域,即超像素,然后训练PP-MRF模型,使它能对待测试图像的各个超像素进行面板参数的分析和深度估计.通过实验证明了该方法能够有效地对单目车载红外图像做出深度估计及三维重建.
A three-dimensional reconstruction method of monocular vehicular infrared image, which combines super pixels segmentation and the plane parameter-Markov Random Field ( PP-MRF ) model, is proposed based on the characteristics of the vehicular infrared image. Firstly, the image is segmented into a series of small areas where the texture and brightness are similar, i.e. super-pixels. Then the PP- MRF model is trained, which can analyze the plane parameters and estimate the depth of each super- pixel of the testing image. The experimental results show that the proposed method can estimate the depth value of monocular vehicular infrared images and rebuild the 3D scene properly.
参考文献:
正在载入数据...
