Automatic Road Detection and Centerline Extraction via Cascaded End-to-end Convolutional Neural NetworkGuangliang Cheng, Ying Wang, Shibiao Xu, Hongzhen Wang, Shiming Xiang and Chunhong Pan.IEEE Transactions on Geoscience and Remote Sensing:2017 (IF=3.36),16AbstractAccurate road detection and centerline extraction
from very-high-resolution (VHR) remote sensing imagery is of central importance in a wide range of applications. Due to the complex backgrounds and occlusions of trees and cars, most road detection methods bring in the heterogeneous segments; besides for the centerline extraction task, most current approaches fail to extract a wonderful centerline network, that appears smooth,
complete as well as single-pixel width. To address the above complex issues, we propose a novel deep model, i.e. a cascaded endto-end convolutional neural network (CasNet), to simultaneously
cope with the road detection and centerline extraction tasks. Specifically, CasNet consists of two networks. One aims at the road detection task, whose strong representation ability is well
able to tackle the complex backgrounds and occlusions of trees and cars. The other is cascaded to the former one, making full use of the feature maps produced formerly, to obtain the good
centerline extraction. Finally, a thinning algorithm is proposed to obtain smooth, complete and single-pixel width road centerline network. Extensive experiments demonstrate that CasNet outperforms the state-of-the-art methods greatly in learning quality and learning speed. That is, CasNet exceeds the comparing methods by a large margin in quantitative performance, and it is nearly 25
times faster than the comparing methods. Moreover, as another contribution, a large and challenging road centerline dataset for the VHR remote sensing image will be publicly available forfurther studies
Accurate urban road centerline extraction from VHR imagery via multiscale segmentation and tensor votingGuangliang Cheng, Feiyun Zhu, Shiming Xiang, Ying Wang, Chunhong Pan.Neurocomputing:2016,205,(IF=2.392)AbstractAccurate road centerline extraction from very-high-resolution (VHR) remote sensing imagery has various applications, such as road map generation and updating etc. There are three shortcomings of existing methods: (a) Due to noise and occlusions, most road extraction methods bring in heterogeneous
classification results; (b) Morphological thinning algorithm is widely used to extract road centerlines, while it produces small spurs; (c) Many methods are
ineffective to extract centerlines around the road intersections. To address the above three issues, we propose a novel road centerline extraction method
via three techniques: fused multiscale collaborative representation (FMCR) & graph cuts (GC), tensor voting (TV) & non-maximum suppression (NMS)
and fitting based connection algorithm. Specifically, a FMCR-GC based road segmentation method is proposed by incorporating multiscale features and
spatial information. In this way, a homogenous road segmentation result is achieved. Then, to obtain a smooth and correct road centerline network, a
TV-NMS based algorithm is introduced. It not only extracts smooth road centerlines, but also connects the discontinuous road centerlines. Finally, to
overcome the ineffectiveness of existing methods in the road intersections, a fitting based algorithm is proposed. Extensive experiments on two datasets
demonstrate that our method achieves higher quantitative results, as well as more satisfactory visual performances by comparing with state-of-the-art methods.
Road Centerline Extraction via Semisupervised Segmentation and Multidirection Nonmaximum SuppressionGuangliang Cheng, Feiyun Zhu, Shiming Xiang and Chunhong Pan.IEEE Geoscience and Remote Sensing Letters (GRSL):2016 (IF=2.228),13,545-549AbstractDownloadAccurate road centerline extraction from remotely
sensed images plays a significant role in road map generation and updating. In the road extraction problem, the acquisition of labeled data is time consuming and costly; thus, there are only a small amount of labeled samples in reality. In the existing centerline extraction algorithms, the thinning-based algorithms always produce small spurs that reduce the smoothness and accuracy of the road centerline; the regression-based algorithms can extract a smooth road network, but they are time consuming. To solve the aforementioned problems, we propose a novel road centerline extraction method, which is constructed based on semisupervised segmentation and multiscale filtering (MF) and multidirection nonmaximum suppression (M-NMS) (MF&M-NMS). Specifically, a semisupervised method, which explores the intrinsic structures between the labeled samples and the unlabeled ones, is introduced to obtain the segmentation result. Then, a novel MF&M-NMS-based algorithm is proposed to gain a smooth and complete road centerline network. Experimental results on a public data set demonstrate that the proposed method achieves comparable or better performances by comparing with the state-of-the-art methods. In addition, our method is nearly ten times faster than the state-of-the-art methods.
Semi-supervised Hyperspectral Image Classification via Discriminant Analysis and Robust RegressionGuangliang Cheng, Feiyun Zhu, Shiming Xiang, Ying Wang and Chunhong Pan.IEEE Journal of Selected Topics in Applied Earth Observation and Remote Sensing (Jstars):2016 (IF=3.026),9,595-608AbstractDownloadIn recent years, hyperspectral image classification (HSIC) has received increasing attention in a wide range of hyperspectral applications. It is still very challenging due to the following factors: 1) there are not enough labeled samples; 2) the images are easy to be polluted by outlier channels; 3) different objects may have similar spectra. Considering these three factors, we propose a novel semi-supervised HSIC method, which is constructed on Discriminant Analysis and Robust Regression (DARR). Specifically, a regression based semi-supervised technique is employed by not only exploiting the rich information in labeled samples, but also taking advantage of abundant unlabeled ones. In this way, the true data distribution can be obtained accurately. Then, we introduce a robust adaptive loss function to measure the representation loss. As a result, it can greatly relieve the side effects of outlier channels. Finally, to increase discriminating power of our approach for different objects, we utilize the pairwise
constraints to incorporate the discriminant information among labeled samples. Through these constraints, the samecategory samples are projected to be close to each other, while the different-category samples are as far apart as
possible. The above three components can be integrated into a graph based objective function, whose optimization is systematically provided. Extensive experiments on four datasets demonstrate that our method achieves higher quantitative results, as well as more satisfactory visual performances by comparing with state-of-the-art methods and using different parameter settings.
Road Extraction via Adaptive Graph Cuts with Multiple FeaturesGuangliang Cheng, Ying Wang, Feiyun Zhu and Chunhong Pan.IEEE International Conference on Image Processing (ICIP):2015,5 pagesAbstractDownloadAccurate road extraction from complex backgrounds plays a fundamental role in a wide range of remote sensing applications. There are two shortcomings for the existing methods: 1) Most of them ignore the spatially contextual information inherent in images; 2) Few existing methods show robustness to the occlusions of cars or trees. To address these two problems, we propose a novel approach via
adaptive graph cuts with multiple features. Specifically, for the former problem, we apply multiple features (spectral feature, spatial
feature and gradient feature) to obtain not only the spectral characteristic but also the spatially contextual feature. In this way, the structural information of road network can be effectively captured. For the latter, adaptive graph cuts based algorithm is adopted. These two schemes show better performance than state-of-the-art methods
under the conditions of occlusions. Experiments on 25 images indicate the validity and effectiveness of our method by comparing with state-of-the-art approaches.
Urban Road Extraction via Graph Cuts based Probability PropagationGuangliang Cheng, Ying Wang, Yongchao Gong, Feiyun Zhu and Chunhong Pan.IEEE International Conference on Image Processing (ICIP):2014,5072-5076AbstractDownloadIn this paper, we propose a graph cuts (GC) based probability propagation approach to automatically extract road network from complex remote sensing images. First, the support vector machine (SVM) classifier with a sigmoid model is applied
to assign each pixel a posterior probability of being labelled as road class, which avoids the weaknesses of hard labels in general SVM. Then a GC based probability propagation algorithm is employed to keep the extracted road results smooth and coherent, which can reduce the connections between roads and road-like objects. Finally, a road-geometrical prior is considered to refine the extraction result, so that the non-road objects in images can be removed. Experimental results on
two remote sensing image datasets indicate the validity and effectiveness of our method by comparing with two other approaches.
SeNet: Structured Edge Network for Sea-Land SegmentationDongcai Cheng, Gaofeng Meng, Guangliang Cheng, Chunhong Pan.IEEE Geoscience and Remote Sensing Letters:2017 (IF=2.228),14(2),5AbstractSeparating an optical remote sensing image into sea and land areas is very challenging yet of great importance to coastline extraction and subsequent object detection. Traditional methods based on handcrafted feature extraction and image processing often face this dilemma when confronting high-resolution remote sensing images for their complicated texture and intensity distribution. In this letter, we apply the prevalent deep convolutional neural networks to the sea-land segmentation problem and make two innovations on top of the traditional structure. First, we propose a local smooth regularization to achieve better spatially consistent results, which frees us from the complicated morphological operations that are commonly used in traditional methods. Second, we use a multitask loss to simultaneously obtain the segmentation and edge detection results. The attached structured edge detection branch can further refine the segmentation result and dramatically improve edge accuracy. Experiments on a set of natural-colored images from Google Earth demonstrate the effectiveness of our approach in terms of quantitative and visual performances compared with state-of-the-art methods.
Building Extraction from Multi-source Remote Sensing Images via Deep Deconvolution Neural Networks
Zuming Huang, Guangliang Cheng, Hongzhen Wang, Haichang Li and Chunhong Pan.IEEE International Geoscience and Remote Sensing Society:2016,Accepted
Fast Aircraft Detection Using End-to-end Fully Convolutional Network
Tingbing Xu. Guangliang Cheng, Jie Yang and Cheng-lin Liu.IEEE International Conference on Digital Signal Processing:2016,Accepted
Semantic Segmentation with Modified Deep Residual Network
Xinze Chen, Guangliang Cheng and Yinghao Cai.Chinese Conference on Pattern Recognition:2016,Accepted