scholarly journals Fully Connected Conditional Random Fields for High-Resolution Remote Sensing Land Use/Land Cover Classification with Convolutional Neural Networks

2018 ◽  
Author(s):  
Bin Zhang ◽  
Cunpeng Wang ◽  
Yonglin Shen ◽  
Yueyan Liu
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Random Fields ◽  
Conditional Random Fields ◽  
Svm Classifier ◽  
Spectral Features ◽  
Remote Sensing Images ◽  
Feature Descriptors ◽  
New Feature ◽  
Fully Connected

The interpretation of land use and land cover (LULC) is an important issue in the fields of high-resolution remote sensing (RS) image processing and land resource management. Fully training a new or existing convolutional neural network (CNN) architecture for LULC classification requires a large amount of remote sensing images. Thus, fine-tuning a pre-trained CNN for LULC detection is required. To improve the classification accuracy for high resolution remote sensing images, it is necessary to use another feature descriptor and to adopt a classifier for post-processing. A fully connected conditional random fields (FC-CRF), to use the fine-tuned CNN layers, spectral features, and fully connected pairwise potentials, is proposed for image classification of high-resolution remote sensing images. First, an existing CNN model is adopted, and the parameters of CNN are fine-tuned by training datasets. Then, the probabilities of image pixels belong to each class type are calculated. Second, we consider the spectral features and digital surface model (DSM) and combined with a support vector machine (SVM) classifier, the probabilities belong to each LULC class type are determined. Combined with the probabilities achieved by the fine-tuned CNN, new feature descriptors are built. Finally, FC-CRF are introduced to produce the classification results, whereas the unary potentials are achieved by the new feature descriptors and SVM classifier, and the pairwise potentials are achieved by the three-band RS imagery and DSM. Experimental results show that the proposed classification scheme achieves good performance when the total accuracy is about 85%.

scholarly journals Fully Connected Conditional Random Fields for High-Resolution Remote Sensing Land Use/Land Cover Classification with Convolutional Neural Networks

2018 ◽  
Vol 10 (12) ◽  
pp. 1889 ◽  
Author(s):  
Bin Zhang ◽  
Cunpeng Wang ◽  
Yonglin Shen ◽  
Yueyan Liu
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Random Fields ◽  
Conditional Random Fields ◽  
Svm Classifier ◽  
Spectral Features ◽  
Remote Sensing Images ◽  
Feature Descriptors ◽  
New Feature ◽  
Fully Connected

The interpretation of land use and land cover (LULC) is an important issue in the fields of high-resolution remote sensing (RS) image processing and land resource management. Fully training a new or existing convolutional neural network (CNN) architecture for LULC classification requires a large amount of remote sensing images. Thus, fine-tuning a pre-trained CNN for LULC detection is required. To improve the classification accuracy for high resolution remote sensing images, it is necessary to use another feature descriptor and to adopt a classifier for post-processing. A fully connected conditional random fields (FC-CRF), to use the fine-tuned CNN layers, spectral features, and fully connected pairwise potentials, is proposed for image classification of high-resolution remote sensing images. First, an existing CNN model is adopted, and the parameters of CNN are fine-tuned by training datasets. Then, the probabilities of image pixels belong to each class type are calculated. Second, we consider the spectral features and digital surface model (DSM) and combined with a support vector machine (SVM) classifier, the probabilities belong to each LULC class type are determined. Combined with the probabilities achieved by the fine-tuned CNN, new feature descriptors are built. Finally, FC-CRF are introduced to produce the classification results, whereas the unary potentials are achieved by the new feature descriptors and SVM classifier, and the pairwise potentials are achieved by the three-band RS imagery and DSM. Experimental results show that the proposed classification scheme achieves good performance when the total accuracy is about 85%.

Fully Connected Conditional Radom Fields for High Resolution Remote Sensing Land Use/Land Cover Classification with Convolutional Neural Networks

2018 ◽  
Author(s):  
Bin Zhang ◽  
Cunpeng Wang ◽  
Yonglin Shen ◽  
Yueyan Liu
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Land Use ◽  
High Resolution ◽  
Svm Classifier ◽  
Land Use Land Cover ◽  
Remote Sensing Images ◽  
Feature Descriptors ◽  
New Feature ◽  
Fully Connected

The interpretation of land use/land cover (LULC) is a hotspot and difficult issue in the field of high resolution remote sensing image processing as well as land resource management. Training a new (or existing) Convolutional Neural Networks (CNNs) architecture fully for LULC classification needs a large amount of remote sensing images. Thus, fine-tuning a pre-trained CNNs for LULC is acceptable. To improve the classification accuracy for high resolution remote sensing images, it is necessary to utilize some hand-crafted features and adopt a classifier for post-processing. A Fully Connected Conditional Radom Fields (FC-CRFs), to utilize the fine-tuned CNNs layers, hand-crafted features and fully connected pairwise potentials, is proposed for image classification of high resolution remote sensing images. First, an existing CNNs model is adopted, and the parameters of CNNs are fine-tuned by training datasets. Then, the probabilities of image pixels belong to each class type also could be calculated. Second, we consider the hand-craft features, combined with Support Vector Machine (SVM) classifier, the probabilities belong to each LULC class type are achieved. Combined with the probabilities achieved by fine-tuned CNNs, new feature descriptors are built. Finally, FC-CRFs are introduced to get the classification results, while the unary potentials are achieved by the new feature descriptors and SVM classifier, and the pairwise potentials are achieved by the hand-crafted features. Experimental results show that the proposed classification scheme can achieve impressive performance when the total accuracy reached to about 85%.

scholarly journals Road Segmentation on Remotely-Sensed Images Using Deep Convolutional Neural Networks with Landscape Metrics and Conditional Random Fields

2017 ◽  
Author(s):  
Teerapong Panboonyuen ◽  
Peerapon Vateekul ◽  
Kulsawasd Jitkajornwanich ◽  
Siam Lawawirojwong ◽  
Panu Srestasathiern
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Landscape Metrics ◽  
Random Fields ◽  
Conditional Random Fields ◽  
Object Segmentation ◽  
Remotely Sensed ◽  
Road Extraction ◽  
Remote Sensing Images ◽  
Remotely Sensed Images

Object segmentation on remotely-sensed images: aerial (or very high resolution, VHS) images and satellite (or high resolution, HR) images, has been applied to many application domains, especially road extraction in which the segmented objects are served as a mandatory layer in geospatial databases. Several attempts in applying deep convolutional neural network (DCNN) to extract roads from remote sensing images have been made; however, the accuracy is still limited. In this paper, we present an enhanced DCNN framework specifically tailored for road extraction on remote sensing images by applying landscape metrics (LMs) and conditional random fields (CRFs). To improve DCNN, a modern activation function, called exponential linear unit (ELU), is employed in our network resulting in a higher number of and yet more accurate extracted roads. To further reduce falsely classified road objects, a solution based on an adoption of LMs is proposed. Finally, to sharpen the extracted roads, a CRF method is added to our framework. The experiments were conducted on Massachusetts road aerial imagery as well as THEOS satellite imagery data sets. The results showed that our proposed framework outperformed Segnet, the state-of-the-art object segmentation technique on any kinds of remote sensing imagery, in most of the cases in terms of precision, recall, and F1.

scholarly journals Road Segmentation on Remotely-Sensed Images Using Deep Convolutional Neural Networks with Landscape Metrics and Conditional Random Fields

2017 ◽  
Author(s):  
Teerapong Panboonyuen ◽  
Peerapon Vateekul ◽  
Kulsawasd Jitkajornwanich ◽  
Siam Lawawirojwong ◽  
Panu Srestasathiern
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Landscape Metrics ◽  
Random Fields ◽  
Conditional Random Fields ◽  
Object Segmentation ◽  
Remotely Sensed ◽  
Road Extraction ◽  
Remote Sensing Images ◽  
Remotely Sensed Images

Object segmentation on remotely-sensed images: aerial (or very high resolution, VHS) images and satellite (or high resolution, HR) images, has been applied to many application domains, especially road extraction in which the segmented objects are served as a mandatory layer in geospatial databases. Several attempts in applying deep convolutional neural network (DCNN) to extract roads from remote sensing images have been made; however, the accuracy is still limited. In this paper, we present an enhanced DCNN framework specifically tailored for road extraction on remote sensing images by applying landscape metrics (LMs) and conditional random fields (CRFs). To improve DCNN, a modern activation function, called exponential linear unit (ELU), is employed in our network resulting in a higher number of and yet more accurate extracted roads. To further reduce falsely classified road objects, a solution based on an adoption of LMs is proposed. Finally, to sharpen the extracted roads, a CRF method is added to our framework. The experiments were conducted on Massachusetts road aerial imagery as well as THEOS satellite imagery data sets. The results showed that our proposed framework outperformed Segnet, the state-of-the-art object segmentation technique on any kinds of remote sensing imagery, in most of the cases in terms of precision, recall, and F1.

scholarly journals Road Segmentation on Remotely-Sensed Images Using Deep Convolutional Neural Networks with Landscape Metrics and Conditional Random Fields

2017 ◽  
Author(s):  
Teerapong Panboonyuen ◽  
Peerapon Vateekul ◽  
Kulsawasd Jitkajornwanich ◽  
Siam Lawawirojwong ◽  
Panu Srestasathiern
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Landscape Metrics ◽  
Random Fields ◽  
Conditional Random Fields ◽  
Object Segmentation ◽  
Remotely Sensed ◽  
Road Extraction ◽  
Remote Sensing Images ◽  
Remotely Sensed Images

Object segmentation on remotely-sensed images: aerial (or very high resolution, VHS) images and satellite (or high resolution, HR) images, has been applied to many application domains, especially road extraction in which the segmented objects are served as a mandatory layer in geospatial databases. Several attempts in applying deep convolutional neural network (DCNN) to extract roads from remote sensing images have been made; however, the accuracy is still limited. In this paper, we present an enhanced DCNN framework specifically tailored for road extraction on remote sensing images by applying landscape metrics (LMs) and conditional random fields (CRFs). To improve DCNN, a modern activation function, called exponential linear unit (ELU), is employed in our network resulting in a higher number of and yet more accurate extracted roads. To further reduce falsely classified road objects, a solution based on an adoption of LMs is proposed. Finally, to sharpen the extracted roads, a CRF method is added to our framework. The experiments were conducted on Massachusetts road aerial imagery as well as THEOS satellite imagery data sets. The results showed that our proposed framework outperformed Segnet, the state-of-the-art object segmentation technique on any kinds of remote sensing imagery, in most of the cases in terms of precision, recall, and F1.

scholarly journals Road Extraction from Remote Sensing Images Using the Inner Convolution Integrated Encoder-Decoder Network and Directional Conditional Random Fields

2021 ◽  
Vol 13 (3) ◽  
pp. 465
Author(s):  
Shuyang Wang ◽  
Xiaodong Mu ◽  
Dongfang Yang ◽  
Hao He ◽  
Peng Zhao
Keyword(s):  
Remote Sensing ◽  
Random Fields ◽  
Conditional Random Fields ◽  
Road Extraction ◽  
Remote Sensing Images ◽  
Feature Maps ◽  
Convolutional Network ◽  
The Road ◽  
Disaster Assessment

Road extraction from remote sensing images is of great significance to urban planning, navigation, disaster assessment, and other applications. Although deep neural networks have shown a strong ability in road extraction, it remains a challenging task due to complex circumstances and factors such as occlusion. To improve the accuracy and connectivity of road extraction, we propose an inner convolution integrated encoder-decoder network with the post-processing of directional conditional random fields. Firstly, we design an inner convolutional network which can propagate information slice-by-slice within feature maps, thus enhancing the learning of road topology and linear features. Additionally, we present the directional conditional random fields to improve the quality of the extracted road by adding the direction of roads to the energy function of the conditional random fields. The experimental results on the Massachusetts road dataset show that the proposed approach achieves high-quality segmentation results, with the F1-score of 84.6%, which outperforms other comparable “state-of-the-art” approaches. The visualization results prove that the proposed approach is able to effectively extract roads from remote sensing images and can solve the road connectivity problem produced by occlusions to some extent.

Sign in / Sign up

Export Citation Format

Share Document