Search

Benggang as a fragmented landform type, can be characterized by a deep-cut slope with various shapes and depressions on the vast weathered crust slopes in southern China. Normally, the gully heads have been continuously collapsed to form a typical landform, such as chair-like erosion. Benggang usually develops rapidly due to large amount of erosion, and thereby to threaten land resources and ecological environment. The identification of Benggang development become necessary to control erosion, and then clarify the behind mechanism. However, conventional methods have low levels of automation for a large-scale work, particularly on local inquiry, in-situ search, and manual interpretation for high-resolution images from satellite remote sensing. This paper proposes a novel Bag of Visual-Topographic Words (BoV-TW) model combining high resolution Digital Orthophoto Map (DOM) and Digital Surface Model (DSM) local features to represent Benggang areas, according to the classification and recognition methods in remote sensing images. The local features of DOM can be set in Harris-Affine and Maximally Stable Extremal Regions (MSER), with Scale-Invariant Feature Transform (SIFT) descriptors. The local features of DSM were extracted by a 3D Douglas-Peucker algorithm, representing by gradient direction-invariant descriptors developed in this study. A Latent Dirichlet Allocation (LDA) was used to balance latent semantic analysis, thereby to construct low-dimensional high-level semantic representations. Support Vector Machine (SVM) was used as a supervised learning training classifier to achieve high-precision and fast automatic Benggang recognition. Three Benggang areas in Tongcheng County, Hubei Province were selected as the experimental objects. The original data were collected by DJI Phantom 3 Pro micro UAV in September 2016. Photoscan processing was used to obtain the DOM and DSM of three Benggang areas. Uniform grid division can be used to achieve DOM and DSM tiles in 0.15 m resolution of 256 × 256 pixels. A high-resolution 3D Benggang model was used to mark the areas with/without Benggang. Two Benggang areas were taken as the training set, and the rest were taken as the test set, in three comparative experiments. The results show that: 1) With changing numbers of LDA topics, the proposed method can maintain a total accuracy of 95%, while the recall rate and precision of Benggang 80%, indicating the maximums were 97.22% and 94.44%, respectively. The total accuracy, recall and precision have increased by 12%, 11% and 32%, respectively, compared with that of only DOM features. The recognition performance was significantly improved after combining with DSM features. 2) With changing sizes of the BoV-TW vocabulary, the total accuracy was 90%, and the maximum was 96.10%, while the recall rate reached 90%, the maximum recall rate of 100%. Precision gradually increased as the increase of vocabulary size, with the maximum of 85.00%. Compared with that of only BoV-TW, three performance indicators increased by 13%, 12% and 30%, respectively, indicating that LDA for latent semantic analysis can greatly improve the recognition detection performance. 3) The proposed method was better than that on the ResNet50 network using DOM and DOM + DSM as the data source. It infers that Benggang as a landform type cannot be well recognized using only DOM, or the simple combination of DOM and DSM. Meanwhile, it needs to combine feature extraction and fusion strategy for efficient application. This finding can deliver a useful tool for the quantitative analysis on the identification, control and erosion mechanism for Benggang. [ABSTRACT FROM AUTHOR]

Evolution of cultivated land needs to be clarified in the driving mechanism for the sustainable land use in China. Most studies generally focused on the relationship between the evolutionary data and the driving mechanism in the evolution of cultivated land use. However, research on the drivers of marginal impact is rare, such as the spatial factor density that represented by the POI points. There can be a tipping point of marginal impact, when the quantity reaches a specific region, in the distance to the main road represented by the human factors. In this paper, the marginal effect analysis was used to make a preliminary evaluation, taking Southern Hubei as an example. Landsat remote sensing images were selected for the interpretation data of three periods from the year of 2000-2005, 2005-2010 and 2010-2015, including 15 types of POI spatial data. Firstly, the evaluation system of spatial factors was constructed from three aspects, including Euclidean distance indices, POI kernel density indices and locational indices. The Spatio-temporal evolution of cultivated land was systematically analyzed, together with dynamic change in the area from 2000 to 2015. Secondly, the principal component analysis was used to integrate the driving factors for the change of cultivated land. The extracted principal components were selected to construct the multiple Logistic regression models, including interaction terms. Lastly, an emphasis was put on the bidirectional marginal effect of spatial elements in the driving mechanism, and the change rule that illustrated by the graph of marginal effect. The results indicated that: (1) The evolution types of cultivated land showed the agglomeration of the same type, while the specific conversion type strongly depended on the spillover effect of neighboring land use. There was obvious evolution trend from cultivated land to construction, but others were not, possibly due to the influence from the macro-control policy of land use. From 2000 to 2015, the proportion of cultivated land converted to construction land increased from 28% to 44%, and then jumped to 96%, mainly concentrated in areas around towns and along major roads. (2) Marginal effects of spatial factors depend on types of cultivated land and periods. From 2000 to 2015, there was a gradual decrease in the variation range of marginal effect for different conversion types of cultivated land, while the homogeneous intersection point moved in the same direction for marginal effect curves of different transformation types. The dominated marginal effect of natural location factors was on the conversion of cultivated land to construction land, and cultivated land to water area, when the spatial elements of POI were different values. (3) The curve of spatial factors implied that there was a critical value of marginal effect. In the range of critical values, marginal effect changed significantly with the spatial factors, but outside the range, marginal effect tended to be stable. The qualitative and quantitative analysis on the marginal effect of spatial factors can offer a theoretical reference for the optimization of cultivated land layout, and the formulation of regional coordinated development strategy. [ABSTRACT FROM AUTHOR]