Chongqing Geomatics Center

Chongqing, China

Chongqing Geomatics Center

Chongqing, China
SEARCH FILTERS
Time filter
Source Type

Deng F.,Wuhan University | Li P.,Wuhan University | Li P.,Chongqing Geomatics Center | Kan Y.,The Land Remediation Bureau of Hubei Province | And 2 more authors.
Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University | Year: 2017

To solve the problem of large-scale urban true orthophoto generation, the paper proposes an occlusion detection based on the overall projection of digital building models (DBMs). Using the surface of DBM storage with triangular facets and raster inside projection of plane graphics do not shelter, weuse triangular face as a unit to orthographic projection of the entire buildings to get polygon of the roof. Make perspective projection of the entire buildings to get the polygon of the building on the image, then get the polygon of the whole building on traditional orthophoto based on DEM projection iteration. We can get the occlusion areas of the building by subtracting two polygons. Finally, we get the true orthophoto after repairing the occlusion areas with the best image. The experiment shows that the method can detect the occlusion areas quickly and accurately and provide a prediction to generate high-quality true orthophoto. © 2017, Research and Development Office of Wuhan University. All right reserved.


Lin N.,Chongqing Jiaotong University | Lin N.,Chengdu University of Technology | Yang W.,Chengdu University of Technology | Wang B.,Chongqing Geomatics Center
Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University | Year: 2017

In order to improve the accuracy of hyperspectral pixel un-mixing, a Kernel based pixel un-mixing method was proposed in this paper. By kernelizing orthogonal subspace projection(OSP)operator, least squares OSP(LSOSP)operator, nonnegative constrained least squares(NCLS)operator and fully constrained least squares(FCLS)operator respectively, the authors established Kernel OSP(KOSP), Kernel LSOSP(KLSOSP), Kernel NCLS(KNCLS)and Kernel FCLS(KFCLS)to hyperspectral imagery pixel un-mixing. The comparison experiments of abundance inversion by using KLSOSP, KNCLS, KFCLS and LSOSP, NCLS, FCLS to CUPRITE AVIRIS data were carried out. The results show that for heavily mixed hyperspectral images, the pixel un-mixing accuracy of Kernels based KLSOSP, KNCLS and KFCLS is higher than that of LSOSP, NCLS and FCLS. Meanwhile, the constraint conditions can improve the accuracy of abundance estimates. © 2017, Research and Development Office of Wuhan University. All right reserved.


Su S.,Wuhan University | Wan C.,Wuhan University | Li J.,Chongqing Geomatics Center | Jin X.,Chongqing Geomatics Center | And 3 more authors.
Land Use Policy | Year: 2017

Cash crop expansion has become a global land use issue in recent decades. While the enlarging cash crop cultivation brings promising profitability, it can impair the delivery of various ecosystem services, with a risk of threat to sustainability and human well being. In order to make well-informed land use policy decisions, it requires elaborate efforts to characterize the trade-off between the benefit and cost of cash crop cultivation. This paper focuses on the enlarging tea cultivation in subtropical China, using a case of Anji County. We first monitor tea expansion from 1985 to 2016 based on time-series Landsat imageries, and then analyze the subsequent changes of water conservation service through an in-field survey of soil loss. Monetary approach is finally employed to evaluate the trade-off between economic benefit and ecological cost associated with the growing age of tea plantations. Results show that tea plantations expanded rapidly from 1985 to 2016 in Anji County. Delivery of water conservation service has been significantly impaired by the conversion from natural forests to tea plantations, but it can be gradually improved during the long rotational life cycles of tea plantations. For a given plot (1 ha at moderate slope), in theory, the economic benefit and ecological cost exhibit opposite trend associated the growing age of tea plantations, and an equilibrium point is approximately achieved at the 12-year growing age. In reality, ecological cost exceeds the economic benefit throughout the study period in Anji County. More specifically, the net difference increases from 11575 Yuan in 1985–1469167 Yuan in 2016. It denotes that economic benefit fails to compromise the ecological cost of the enlarging tea cultivation in Anji County. Conflicting land use policies (ecological conservation vs cash cropping promotion) and ‘household contract responsibility’ system should account for the unbalanced relationship between economic benefit and ecological conservation. We finally propose four major options towards the win–win possibilities between economic gain and ecological conservation associated with tea cultivation. © 2017 Elsevier Ltd


Hu Y.,Chongqing Geomatics Center | Hu Y.,Wuhan University | Li Z.,Chongqing University | Li P.,Chongqing Geomatics Center | And 2 more authors.
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives | Year: 2017

This paper presents a non-interactive building detection approach employing binary bag-of-features (BBOF), namely, extracting building roof contours in remote sensing images automatically, rapidly and accurately. The proposed method includes two major stages, i.e., building area detection and building contours extraction. In the first stage, it contains three modules. i.e., over-segmentation, intersection point classification, building area detection. Firstly, the orthophoto is over-segmented by the Simple Linear Iterative Clustering (SLIC) superpixel segmentation method, and the intersection points is obtained. Secondly, the oriented FAST and rotated BRIEF (ORB) descriptors are generated in LAB colour space from the patches that centred on the intersection points, and the BBOF classifier is adopted to classify the intersection points into two categories. Thirdly, the area that contains of the building roof are detected through reserving the regions around the intersection points in inner parts of building roof, and eliminating the regions around the intersection points in non-building roof. At last, we can roughly generate the building area. For the second stage, it is similar to the first one while the main difference is that its classifier has three categories. Finally, we provide an evaluation between two different classifiers, including ORB+BBOF and SURF+BOF. This evaluation is conducted on orthophotos with different roof colours, texture, shape, size and orientation. The proposed approach presents several advantages in terms of scalability, suitability and simplicity with respect to the existing methods.


Li P.,Chongqing Geomatics Center | Hu Y.,Chongqing Geomatics Center | Ding Y.,Chongqing Geomatics Center | Wang L.,Chongqing Geomatics Center | Li L.,Chongqing Geomatics Center
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives | Year: 2017

In order to solve the problem of automatic detection of artificial objects in high resolution remote sensing images, a method for detection of artificial areas in high resolution remote sensing images based on multi-scale and multi feature fusion is proposed. Firstly, the geometric features such as corner, straight line and right angle are extracted from the original resolution, and the pseudo corner points, pseudo linear features and pseudo orthogonal angles are filtered out by the self-constraint and mutual restraint between them. Then the radiation intensity map of the image with high geometric characteristics is obtained by the linear inverse distance weighted method. Secondly, the original image is reduced to multiple scales and the visual saliency image of each scale is obtained by adaptive weighting of the orthogonal saliency, the local brightness and contrast which are calculated at the corresponding scale. Then the final visual saliency image is obtained by fusing all scales' visual saliency images. Thirdly, the visual saliency images of artificial areas based on multi scales and multi features are obtained by fusing the geometric feature energy intensity map and visual saliency image obtained in previous decision level. Finally, the artificial areas can be segmented based on the method called OTSU. Experiments show that the method in this paper not only can detect large artificial areas such as urban city, residential district, but also detect the single family house in the countryside correctly. The detection rate of artificial areas reached 92%.


Chen C.,Chongqing University | Gong W.,Chongqing University | Hu Y.,Chongqing Geomatics Center | Chen Y.,Chongqing University | Ding Y.,Chongqing Geomatics Center
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives | Year: 2017

The automated building detection in aerial images is a fundamental problem encountered in aerial and satellite images analysis. Recently, thanks to the advances in feature descriptions, Region-based CNN model (R-CNN) for object detection is receiving an increasing attention. Despite the excellent performance in object detection, it is problematic to directly leverage the features of R-CNN model for building detection in single aerial image. As we know, the single aerial image is in vertical view and the buildings possess significant directional feature. However, in R-CNN model, direction of the building is ignored and the detection results are represented by horizontal rectangles. For this reason, the detection results with horizontal rectangle cannot describe the building precisely. To address this problem, in this paper, we proposed a novel model with a key feature related to orientation, namely, Oriented R-CNN (OR-CNN). Our contributions are mainly in the following two aspects: 1) Introducing a new oriented layer network for detecting the rotation angle of building on the basis of the successful VGG-net R-CNN model; 2) the oriented rectangle is proposed to leverage the powerful R-CNN for remote-sensing building detection. In experiments, we establish a complete and bran-new data set for training our oriented R-CNN model and comprehensively evaluate the proposed method on a publicly available building detection data set. We demonstrate State-of-the-art results compared with the previous baseline methods.


Li Z.,Chongqing University | Li Z.,Chongqing Academy of Science and Technology | Liu Y.,Chongqing University | Hu Y.,Chongqing Geomatics Center | And 2 more authors.
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives | Year: 2017

Building extraction in aerial orthophotos is crucial for various applications. Currently, deep learning has been shown to be successful in addressing building extraction with high accuracy and high robustness. However, quite a large number of samples is required in training a classifier when using deep learning model. In order to realize accurate and semi-interactive labelling, the performance of feature description is crucial, as it has significant effect on the accuracy of classification. In this paper, we bring forward a compact and hybrid feature description method, in order to guarantees desirable classification accuracy of the corners on the building roof contours. The proposed descriptor is a hybrid description of an image patch constructed from 4 sets of binary intensity tests. Experiments show that benefiting from binary description and making full use of color channels, this descriptor is not only computationally frugal, but also accurate than SURF for building extraction.


Xu Y.,China Agricultural University | Luo D.,Chongqing Geomatics Center | Peng J.,Central University of Costa Rica
Journal of Geographical Sciences | Year: 2011

Due to the extremely poor soil cover, a low soil-forming rate, and inappropriate intensive land use, soil erosion is a serious problem in Guizhou Province, which is located in the centre of the karst areas of Southwest China. In order to bring soil erosion under control and restore environment, the Chinese Government has initiated a serious of ecological rehabilitation projects such as the Grain-for-Green Programme and Natural Forest Protection Program and brought about tremendous influences on land-use change and soil erosion in Guizhou Province. This paper explored the relationship between land use and soil erosion in the Maotiao River watershed, a typical agricultural area with severe soil erosion in central Guizhou Province. In this study, we analyzed the spatio-temporal dynamic change of land-use type in Maotiao River watershed from 1973 to 2007 using Landsat MSS image in 1973, Landsat TM data in 1990 and 2007. Soil erosion change characteristics from 1973 to 2007, and soil loss among different land-use types were examined by integrating the Revised Universal Soil Loss Equation (RUSLE) with a GIS environment. The results indicate that changes in land use within the watershed have significantly affected soil erosion. From 1973 to 1990, dry farmland and rocky desertified land significantly increased. In contrast, shrubby land, other forestland and grassland significantly decreased, which caused accelerated soil erosion in the study area. This trend was reversed from 1990 to 2007 with an increased area of land-use types for ecological use owing to the implementation of environmental protection programs. Soil erosion also significantly varied among land-use types. Erosion was most serious in dry farmland and the lightest in paddy field. Dry farmland with a gradient of 6°-25° was the major contributor to soil erosion, and conservation practices should be taken in these areas. The results of this study provide useful information for decision makers and planners to take sustainable land use management and soil conservation measures in the area. © 2011 Science China Press and Springer-Verlag Berlin Heidelberg.


Zhang Q.,China Agricultural University | Xiao H.,China Agricultural University | Xiao H.,Chongqing Geomatics Center | Duan M.,China Agricultural University | And 2 more authors.
Land Use Policy | Year: 2015

Agricultural infrastructure construction is an important component of agricultural policies in China that aim to increase production and ensure food security. One objective of agricultural infrastructure is to promote modern intensive agriculture, which has already caused agri-environmental problems including environmental pollution, landscape degradation, and biodiversity loss. In European countries, agri-environmental measures are widely implemented with farmers' participation, and it is anticipated that these measures will be introduce into agricultural policies, such as agricultural infrastructure projects, in China. As one of the direct stakeholders, farmers and their attitudes towards agricultural infrastructure projects and their perceptions of agri-environmental issues need to be understood before the policy is implemented. This research aimed to determine farmers' attitudes towards agricultural infrastructure projects and the possible incorporation of agri-environmental measures in these projects using a questionnaire survey in Beijing and Changsha. The results showed that farmers were generally unsatisfied with the top-down implementation process of agricultural infrastructure projects because they were seldom involved and felt their needs were not considered by the authorities. Most farmers would accept at least one simple agri-environmental measure, and subsidies could significantly increase the acceptance level. Economic risk and farm business type were crucial factors influencing farmers' acceptance of measures. We suggested that if governments hope to implement agri-environmental measures as part of agricultural infrastructure projects, improving the public participation process should be a priority, and a combination of top-down and bottom-up approaches should be considered with respect to farmers' knowledge, opinions and farm business types to design suitable measures for local conditions. © 2015 Elsevier Ltd.


Lin N.,Chongqing Jiaotong University | Lin N.,Chengdu University of Technology | Yang W.,Chengdu University of Technology | Wang B.,Chongqing Geomatics Center
Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University | Year: 2013

Hyperspectral image linear feature extraction methods often cause information loss and distortion. In view of this, a new kernel minimum noise fraction (KMNF) transform hyperspectral image nonlinear feature extraction method is proposed that introduces a kernel method to minimum noise fraction (MNF) transform. Hyperspectral image KMNF feature extraction experiments were carried out. CUPRITE AVIRIS data experimental results show that sample number influences KMNF slightly, a small number of samples can get almost the same result as a large number of samples; KMNF feature extraction reflects the nonlinear characteristics of hyperspectral images, and endmember extraction effects based on KMNF images outweigh MNF images.

Loading Chongqing Geomatics Center collaborators
Loading Chongqing Geomatics Center collaborators