Zezhong Zheng

Vehicle detection based on morphology from highway aerial images

Vehicle detection from high resolution aerial images has been studied for many years. However, a robust and efficient vehicle detection method is still challenging. In this paper, a novel and robust method for automatic vehicle detection from highway aerial image was presented. In this method, a GIS road vector map is used to constrain a vehicle detection system to the highway networks. After the structure element is identified, morphological preprocessing method is used to identify candidate vehicles. Experiment is conducted with 0.15 m resolution aerial image. And the result demonstrated that the novel method has an excellent detection performance, thus the method is very promising.

Sparse coding based dense feature representation model for hyperspectral image classification

Abstract. We present a sparse coding based dense feature representation model (a preliminary version of the paper was presented at the SPIE Remote Sensing Conference, Dresden, Germany, 2013) for hyperspectral image (HSI) classification. The proposed method learns a new representation for each pixel in HSI through the following four steps: sub-band construction, dictionary learning, encoding, and feature selection. The new representation usually has a very high dimensionality requiring a large amount of computational resources. We applied the l1/lq regularized multiclass logistic regression technique to reduce the size of the new representation. We integrated the method with a linear support vector machine (SVM) and a composite kernels SVM (CKSVM) to discriminate different types of land cover. We evaluated the proposed algorithm on three well-known HSI datasets and compared our method to four recently developed classification methods: SVM, CKSVM, simultaneous orthogonal matching pursuit, and image fusion and recursive filtering. Experimental results show that the proposed method can achieve better overall and average classification accuracies with a much more compact representation leading to more efficient sparse models for HSI classification.

Analysis of land use and cover change in Sichuan province, China

Abstract. A series of environmental policies in Sichuan province was executed to restore the grassland and forestland on some degraded lands after 2000. But the effectiveness on land use and cover change (LUCC) has not yet been systematically investigated. We undertook a detailed analysis about land use and cover change between 2000 and 2005 in Sichuan province. Our study mainly utilized remotely sensed data of 2005 China-Brazil Earth Resources Satellite II (CBERS II) and 2000 Landsat 5 thematic mapper (TM) data. Land use and cover change between 2000 and 2005 was visually interpreted by CBERS II with ArcInfo Workstation based on land use and cover database interpreted from TM. Then LUCC was validated by ground truth with global positioning system receivers. Our analysis illustrates that the conservation policies to restore the grassland and forestland were successful to a lesser extent. But more measures to restore the grassland and forestland of Sichuan province have to be taken further in the future.

The manifold learning for dimensionality reduction with hyperspectral image

Hyperspectral remote sensing image (HSI) consists of hundreds of bands that contain rich space, radiation and spectral information. The high-dimensional data can also lead to the curse of dimensionality problem making it difficult to be used effectively. In this paper, we proposed a manifold learning algorithm to reduce the dimensionality for HSI data. For high dimensional datasets with continuous variables, it is often the case that the data points are arranged along with low dimensional structures, named manifolds, in the high dimensional space. Manifold learning aims to identifying those special low dimensional structures for subsequent usage such as classification or regression. However, many manifold learning algorithms perform an eigenvector analysis on a data similarity matrix whose size is N×N, where N is the number of data points. The memory complexity of the analysis is at least O(N2) that is not feasible for a regular computer to compute or storage for very large datasets. To solve this problem, we used statistical sampling methods to sample a subset of data points as landmarks. A skeleton of the manifold was then identified based on the landmarks. The remaining data points were then inserted into the skeleton by Locally Linear Embedding (LLE). We tested our algorithm on AVIRIS Salinas-A data set. The experimental results showed that the HSI dataset could be reduced to a lower-dimensional space for land use classification with good performance, and the main structure was preserved well.

The tradeoff of accuracy with different landmarks with manifold learning

High-dimensional data such as hyperspectral images contain abundant information of surface radiation. But the massive redundant information makes it complex to be utilized conveniently. To solve this problem, a manifold learning dimensionality reduction framework for hyperspectral image is proposed. Firstly, statistical sampling methods were used to sample a subset of data points as landmarks. A skeleton of the manifold was then identified basing on the landmarks. The remaining data points were then inserted into the skeleton by Locally Linear Embedding algorithm. At last, original data sets and data sets reduced with different manifold learning approaches were classified by KNN classifier to evaluate the performance of the proposed framework. The framework was tested on AVIRIS Salinas-A dataset. The experimental results showed that the tradeoff of accuracy with different landmarks is of great significant. Insufficient landmarks lead to low accuracy and excess landmarks may spend a considerable amount of time.

Adaptive graph construction for Isomap manifold learning

Isomap is a classical manifold learning approach that preserves geodesic distance of nonlinear data sets. One of the main drawbacks of this method is that it is susceptible to leaking, where a shortcut appears between normally separated portions of a manifold. We propose an adaptive graph construction approach that is based upon the sparsity property of the ℓ1 norm. The ℓ1 enhanced graph construction method replaces k-nearest neighbors in the classical approach. The proposed algorithm is first tested on the data sets from the UCI data base repository which showed that the proposed approach performs better than the classical approach. Next, the proposed approach is applied to two image data sets and achieved improved performances over standard Isomap.

Classification based on deep convolutional neural networks with hyperspectral image

Hyperspectral image (HSI) is usually composed of hundreds of bands which contain very rich spatial and spectral information. However, the high-dimensional data may lead to the curse of dimensionality phenomenon when it is used for land use classification or other applications, making it difficult to be utilized effectively. In this paper, we developed a deep learning classification framework based on the spectral and spatial information of hyperspectral image. Firstly, the deep learning features in different layers could be extracted automatically. Secondly, based on the learned deep learning features, we could obtain the classification of hyperspectral image with logistic regression (LR) classifier. Finally, we compared our approach with other methods including quadratic discriminant analysis with the multilevel logistic spatial prior (QDAMLL), logistic discriminant analysis with the multilevel logistic spatial prior (logDAMLL), linear discriminant analysis with the multilevel logistic spatial prior (LDAMLL), subspace multiclass logistic regression with the multilevel logistic spatial prior (MLRsub MLL), support vector machine on extended morphological profiles (SVM/EMP), support vector machine on expectation maximization and post-regularization (SVM-EM-PR). The experimental results showed that our method obtained the optimum accuracy, which was better than the other six approaches. And the OA was up to 99.39%. Therefore, the deep convolutional neural networks (DCNNs) is a robust method for land use classification with hyperspectral image. Index Terms — Classification; deep convolutional neural networks; hyperspectral image.

A novel manifold learning for dimensionality reduction and classification with hyperspectral image

Hyperspectral remote sensing image (HSI) consists of hundreds of bands that contain rich space, radiation and spectral information. The high-dimensional data can also lead to the course of dimensionality problem making it difficult to be used effectively. In this paper, we proposed a manifold learning algorithm to reduce the dimensionality for HSI data. For high dimensional datasets with continuous variables, it is often the case that the data points are arranged along with low dimensional structures, named manifolds, in the high dimensional space. Manifold learning aims to identifying those special low dimensional structures for subsequent usage such as classification or regression. However, many manifold learning algorithms perform an eigenvector analysis on a data similarity matrix whose size is N∗N, where N is the number of data points. The memory complexity of the analysis is at least O(N2) that is not feasible for a regular computer to compute or storage for very large datasets. To solve this problem, we used statistical sampling methods to sample a subset of data points as landmarks. A skeleton of the manifold was then identified based on the landmarks. The remaining data points were then inserted into the skeleton by Locally Linear Embedding (LLE). We tested our algorithm on AVIRIS Salinas-A data set. The experimental results showed that the HSI dataset could be reduced to a lower-dimensional space for land use classification with good performance, and the main structure was preserved well.

The monitoring of land use and land cover change of Sichuan province and Chengdu district, China

Land use and land cover change (LUCC) is necessary to explore the factors leading to heavy drought and rainy-flood disaster in some districts of Sichuan province. A method based RS, GIS, GPS and Google earth (GE) is presented to establish LUCC database in Sichuan province and Chengdu district. At first, LUCC is interpreted based on the new temporal images and the land use and land cover database from TM in 2000.Secondly, some ground objects, which could not be identified in the new temporal images, were interpreted utilizing GE with some higher spatial resolution images. Thirdly, the new interpreted LUCC was validated in the field with GPS handheld receiver. Then, LUCC of Sichuan province was updated. A comparative analysis of LUCC between in Sichuan province and in Chengdu district was conducted and the result showed: (1) a large amount of farmland in Sichuan Province was occupied from 2000 to 2005 and the area is 84 573 ha. While construction land gained obviously and the area was 35 828 ha. The dynamic degree of construction land was 111.100/00 from 2000 to 2005. The LUCC demonstrated that the economy of Sichuan province continued to develop, the cities were overspreading and the urban heat island effect was deteriorated from 2000 to 2005. (2) A large amount of farmland was also occupied in Chengdu district from 2000 to 2005, the area amounted to 12 989 ha. The farmland lost was mainly changed to construction land, amounting to 93%. And the dynamic degree was 117.410/00 from 2000 to 2005, which was bigger than that in Sichuan province.

Progressive Network Transmission Method Research of Vector Data

Vector data contains a lot of important features. Progressive transmission is a key technology to solve the real-time rendering and network transmission of vector data. By studying the traditional progressive transmission method of vector data and considering the spatial position and geometric features of vector data, we proposed an efficient progressive transmission method. We divided the vector data into blocks based on spatial location, then applied a Visvalingam-Whyatt algorithm to build a multi-scale model. Finally the progressive transmission of vector data was achieved. Our method satisfies the viewer’s needs to display data from different rendering scale and has important significance for client users to interact in real time.