搜索结果: 1-8 共查到“测绘科学技术 MRF”相关记录8条 . 查询时间(0.125 秒)
融合CNN和MRF的激光点云层次化语义分割方法
激光点云 语义分割 层次化提取 残差学习 马尔可夫随机场(MRF)
2021/3/30
三维点云语义分割的结果包含着对场景中多个目标的识别，是三维场景信息提取的重要环节，在智慧城市等多个领域扮演关键角色。由于三维激光点云数据量庞大、场景复杂性高等问题，大多数现有方法只能以相对较低的识别率提取有限类型的对象。本文提出了一种在三维激光点云场景中结合残差学习和马尔可夫随机场（MRF）优化的层次化多类型目标自动提取框架。该框架首先将点云滤波为地面点和非地面点；然后从非地面点中提取建筑物以降低...
CHANGE DETECTION OF REMOTE SENSING IMAGES BY DT-CWT AND MRF
Change Detection DT-CWT MRF Multi-Scale Decomposition ICM Segmentation
2017/7/12
Aiming at the significant loss of high frequency information during reducing noise and the pixel independence in change detection of multi-scale remote sensing image, an unsupervised algorithm is prop...
OPTIMIZING CLOUD BASED IMAGE STORAGE, DISSEMINATION AND PROCESSING THROUGH USE OF MRF AND LERC
OPTIMIZING CLOUD BASED IMAGE STORAGE DISSEMINATION AND PROCESSING THROUGH USE OF MRF AND LERC
2016/11/8
The volume and numbers of geospatial images being collected continue to increase exponentially with the ever increasing number of airborne and satellite imaging platforms, and the increasing rate of d...
Markov Random Fields (MRF) - Based Texture Segmentation for Road Detection
Mapping Photogrammetry Vision Fusion Identification Monitoring Real-time Platforms
2015/12/9
Traffic observation from airplane platforms using digital cameras is a fairly new application of Video Image Detection Systems (VIDS). These systems are also particularly interesting for observations ...
CONTEXTUAL CLASSIFICATION OF REMOTELY SENSED DATA USING MAP APPROACH AND MRF
Remote sensing classification supervised Bayes contextual Markov optimisation
2015/7/29
CLASSIFICATION OF ACTIVE MICROWAVE AND PASSIVE OPTICAL DATA BASED ON BAYESIAN THEORY AND MRF
Active and passive remote sensing Classification Bayesian theory MRF ASAR TM
2014/4/29
A classifier based on Bayesian theory and Markov random field (MRF) is presented to classify the active microwave and passive optical remote sensing data, which have demonstrated their respective adva...
MRF框架下的区域增长模型在城镇识别中的应用
城镇识别 MRF 区域增长
2011/8/1
提出一种MRF框架下以过分割区域为基本生长单位的区域增长模型，并以其实现城镇识别。该模型首先通过纹理分析和滤波运算得到初始种子点；然后由均值漂移算法运算过分割区域，并将种子点对应的区域设为种子区域；最后，从种子区域开始，根据MRF框架下提出的增长准则，得到最终的城镇识别结果。对QuickBird和Ikonos遥感影像的实验表明，该模型能有效地识别出影像中的城镇区域，城镇平均识别率达到84.35%，...