Fengchen Huang

A kernel-based block matrix decomposition approach for the classification of remotely sensed images

The classification problem of remotely sensed images with hyperspectral and hyperspatial resolution images is being paid more and more attention. The success of remotely sensed images classification depends on many facts, such as the availability of high-quality images and ancillary data, proper classification procedure, and the analytical ability of scientific researcher. Therefore, lots of methods of combing spatial, spectral and texture information were proposed. However, these methods may ignore these facts as below. On the one hand, many details of the original remotely sensed images may be covered up by the too much overlapping information. On the other hand, the classification process is time-consuming. Therefore, a new and efficient classification of remotely sensed images method is introduced to overcome these shortcomings. The proposed method deals with the original information provided by the remotely sensed images is considered. The block matrix is made of training samples of the same class. The details of original remotely sensed images is obtained from the QR decomposition with column pivoting (QRcp) or singular value decomposition (SVD). And then, using fisher linear discriminant analysis (FLDA) methods, the projection data information of original remotely sensed images is jointly used for the classification through a support vector machines (SVMs) formulation. Experiments on hyperspatial and hyperspectral images are performed to test and evaluate the effectiveness of the proposed method.

A spectral---textural kernel-based classification method of remotely sensed images

Most studies have been based on the original computation mode of semivariogram and discrete semivariance values. In this paper, a set of texture features are described to improve the accuracy of object-oriented classification in remotely sensed images. So, we proposed a classification method support vector machine (SVM) with spectral information and texture features (ST-SVM), which incorporates texture features in remotely sensed images into SVM. Using kernel methods, the spectral information and texture features are jointly used for the classification by a SVM formulation. Then, the texture features were calculated based on segmented block matrix image objects using the panchromatic band. A comparison of classification results on real-world data sets demonstrates that the texture features in this paper are useful supplement information for the spectral object-oriented classification, and proposed ST-SVM classification accuracy than the traditional SVM method with only spectral information.

A Biological Hierarchical Model Based Underwater Moving Object Detection

Underwater moving object detection is the key for many underwater computer vision tasks, such as object recognizing, locating, and tracking. Considering the super ability in visual sensing of the underwater habitats, the visual mechanism of aquatic animals is generally regarded as the cue for establishing bionic models which are more adaptive to the underwater environments. However, the low accuracy rate and the absence of the prior knowledge learning limit their adaptation in underwater applications. Aiming to solve the problems originated from the inhomogeneous lumination and the unstable background, the mechanism of the visual information sensing and processing pattern from the eye of frogs are imitated to produce a hierarchical background model for detecting underwater objects. Firstly, the image is segmented into several subblocks. The intensity information is extracted for establishing background model which could roughly identify the object and the background regions. The texture feature of each pixel in the rough object region is further analyzed to generate the object contour precisely. Experimental results demonstrate that the proposed method gives a better performance. Compared to the traditional Gaussian background model, the completeness of the object detection is 97.92% with only 0.94% of the background region that is included in the detection results.

Fuzzy Integral Based Information Fusion for Water Quality Monitoring Using Remote Sensing Data

To improve the monitoring precision of lake chlorophyll a (Chl-a), this paper presents a fusion method based on Choquet Fuzzy Integral (CFI) to estimate the Chl-a concentration. A group of BPNN models are designed. The output of multiple BPNN model is fused by the CFI. Meanwhile, to resolve the over-fitting problem caused by a small number of training sets, we design an algorithm that fully considers neighbor sampling information. A classification experiment of the Chl-a concentration of the Taihu Lake is conducted. The result shows that, the proposed approach is superior to the classification using a single neural network classifier, and the CFI fusion method has higher identification accuracy.

Fusion of Multispectral and Panchromatic Images Using Fuzzy Integral Based on Fast Intensity-Hue-Saturation Transform

To fuse multispectral images and panchromatic images, this paper proposes a new fused method using fuzzy integral based on fast intensity-hue-saturation (IHS) transform. The proposed method enables fast, easy implementation. We choose the fuzzy density according to the importance of the spectral and spatial resolution in the fused images respectively. With an appropriate fuzzy density, the new approach can update the spatial detail quality of the fused image while minimizing the spectral distortion relative to the original low-resolution multispectral images. The experiment results carried out on Landsat-7 ETM+ mutlispectral and panchromatic image show the proposed approach effective.

High-Resolution Remotely Sensed Small Target Detection by Imitating Fly Visual Perception Mechanism

The difficulty and limitation of small target detection methods for high-resolution remote sensing data have been a recent research hot spot. Inspired by the information capture and processing theory of fly visual system, this paper endeavors to construct a characterized model of information perception and make use of the advantages of fast and accurate small target detection under complex varied nature environment. The proposed model forms a theoretical basis of small target detection for high-resolution remote sensing data. After the comparison of prevailing simulation mechanism behind fly visual systems, we propose a fly-imitated visual system method of information processing for high-resolution remote sensing data. A small target detector and corresponding detection algorithm are designed by simulating the mechanism of information acquisition, compression, and fusion of fly visual system and the function of pool cell and the character of nonlinear self-adaption. Experiments verify the feasibility and rationality of the proposed small target detection model and fly-imitated visual perception method.

Self-Adaptive Image Reconstruction Inspired by Insect Compound Eye Mechanism

Inspired by the mechanism of imaging and adaptation to luminosity in insect compound eyes (ICE), we propose an ICE-based adaptive reconstruction method (ARM-ICE), which can adjust the sampling vision field of image according to the environment light intensity. The target scene can be compressive, sampled independently with multichannel through ARM-ICE. Meanwhile, ARM-ICE can regulate the visual field of sampling to control imaging according to the environment light intensity. Based on the compressed sensing joint sparse model (JSM-1), we establish an information processing system of ARM-ICE. The simulation of a four-channel ARM-ICE system shows that the new method improves the peak signal-to-noise ratio (PSNR) and resolution of the reconstructed target scene under two different cases of light intensity. Furthermore, there is no distinct block effect in the result, and the edge of the reconstructed image is smoother than that obtained by the other two reconstruction methods in this work.

Design of water quality monitoring based on SVM and its simulation platform by remote sensing

Monitoring water quality using remote sensing technology is current research focus, the main challenge of which is to design an appropriate inversion model of water quality and an effective simulation platform. For the Small Sample Size problem, this paper proposes a water quality inversion method based on SVM. Such method uses ε-SVR whose kernel is RBF to build the inversion model. Besides, we design a water quality monitoring simulation platform (WRS) based on MVC pattern. WRS is developed by MFC, GDAL and LIBSVM to realize the function of graphical interface, image read/write, modeling and inversion. Furthermore, the divide and conquer algorithm is utilized to speed up the huge-volume remote sensing image processing. Finally, we simulate this SVM method on WRS, and the results show the feasibility of our method and the effectiveness of the simulation platform.

Image Registration Using Ant Colony and Particle Swarm Hybrid Algorithm Based on Wavelet Transform

Mutual information based image registration has the advantages of high precision and strong robustness. However, the solution of this registration method is easy to fall into the local extremes. To overcome this problem, in this paper we propose a new optimal algorithm for image registration, which combines ant colony algorithm with particle swarm algorithm based on wavelet transform. Experiment results demonstrate our proposed approach effective.

Remotely Sensed Images Registration Based on Wavelet Transform Using Affine Invariant Moment

This paper presents an accurate and automatic feature-based method for registration of remotely sensed images.The proposed method uses the redundant wavelet transform to obtain feature points. Firstly, modulus maximum of wavelet coefficients of reference and sensed images are detected based on multi-scale multiplication, respectively. Then, affine invariant moments are calculated using a circular neighborhood area centered on the detected modulus maximum point. After that, corresponding feature points are detected by minimum distance rule with the threshold in the Euclidean space of the invariants. Finally, the transformation parameters are obtained by least square method. Also,the center spline function is used as interpolation function when wrapping the sensed image to reference image. Experiment applying our proposed method on Landsat TM remotely sensed images prove our proposed method effective.