Artificial neural networks paddy-field classifier using spatiotemporal remote sensing data

Monitoring changes in a paddy-field area is important since rice is a staple food and paddy agriculture is a major cropping system in Asia. For monitoring changes in land surface, various applications using different satellites have been researched in the field of remote sensing. However, monitoring a paddy-field area with remote sensing is difficult owing to the temporal changes in the land surface, and the differences in the spatiotemporal characteristics in countries and regions. In this article, we used an artificial neural network to classify paddy-field areas using moderate resolution sensor data that includes spatiotemporal information. Our aim is to automatically generate a paddy-field classifier in order to create localized classifiers for each country and region.     

改进卷积神经网络在遥感图像分类中的应用

针对传统卷积神经网络（CNN）稀疏网络结构无法保留全连接网络密集计算的高效性和实验过程中激活函数的经验性选择造成结果不准确或计算量大的问题,提出一种改进卷积神经网络方法对遥感图像进行分类。首先,利用Inception模块的不同尺度卷积核提取图像多尺度特征,然后利用Maxout模型学习隐藏层节点的激活函数,最后通过Softmax方法对图像进行分类。在美国土地使用分类数据集（UCM_LandUse_21）上进行的实验结果表明,在卷积层数相同的情况下,所提方法比传统的CNN方法分类精度提高了约3.66%,比同样也基于多尺度深度卷积神经网络（MS_DCNN）方法分类精度提高了2.11%,比基于低层特征和中层特征的视觉词典等方法分类精度更是提高了10%以上。因此,所提方法具有较高的分类效率,适用于图像分类。     

Improved convolutional neural network in remote sensing image classification

Neural Computing and Applications - The classification of land cover is the first step in the analysis and application of remote sensing data in land resources. How to solve the multi-category...     

基于粒子群优化的深度神经网络分类算法

针对神经网络分类算法中节点函数不可导,分类精度不够高等问题,提出了一种基于粒子群优化(PSO)算法的深度神经网络分类算法.使用深度学习中的自动编码机,结合PSO算法优化权值,利用自动编码机对输入样本数据进行编解码,为提高网络分类精度,以编码机本身的误差函数和Softmax分类器的代价函数加权求和共同作为PSO算法的评价函数,使编码后的数据更加适应分类器.实验结果证明:与其他传统的神经网络相比,在邮件分类问题上,此分类算法有更高的分类精度.     

基于自编码神经网络的航空物探遥感数据分类方法研究

航空物探遥感数据的采集过程中受到电磁波辐射等外界因素的影响,导致航空物探遥感数据分类准确率较低,为此提出基于自编码神经网络的航空物探遥感数据分类方法;根据航空物探对象的基本特征,设置遥感数据的分类标准;通过辐射校正、几何纠正、噪声消除等步骤,完成航空物探遥感数据的预处理;构建自编码神经网络,利用自编码神经网络算法,从光谱、形状、纹理等方面提取遥感数据特征,通过特征匹配确定航空物探遥感数据的所属类型;通过分类性能测试实验得出结论：所提方法的全局遥感数据分类成功率和错误率的平均值分别为99.8%和0.6%,局部遥感数据分类的成功率和错误率的平均值分别为99.8%和0.3%,即所提方法在分类性能方面具有明显优势。     

An efficient radial basis function neural network for hyperspectral remote sensing image classification

A very simple radial basis function neural network (RBFNN) is investigated for hyperspectral remote sensing image classification. Its training can be analytically solved with a closed-form equation, and no parameter needs to be manually tuned. Its computational cost is much lower than the popular support vector machine (SVM). Surprisingly, such an RBFNN can achieve the performance that is similar to or even better than the SVM. By incorporating a simple spatial averaging filter or a Gaussian lowpass filter with negligible additional computational cost, classification accuracy can be further improved. Considering the large matrix inversion operation in the RBFNN when the number of training samples being very large, we also propose a parallel processing method to reduce computing time in matrix inversion.     

基于Kohonen神经网络聚类方法在遥感分类中的比较

设计完成和比较了基于Kohonen自组织网络的Kohonen聚类网络（Kohonen Clustering Network, KCN）、模糊Kohonen聚类网络（Fluzzy KCN, FKCN）和基于进化规划的Kohonen聚类网络（Evalutionary Programming based KCN, EPKCN）三种聚类算法在遥感土地利用/覆盖分类中的应用。结果表明三种非监督学习方法在进行遥感土地利用/覆盖分类过程中，在分类性能上有显著差异。EPKCN分类目视效果最好，单次迭代的速度最快；FKCN总的收敛速度最快；而按遥感土地利用/覆盖分类要求而言，EPKCN方法在三种分类方法中效果最好，因此可采用该算法进行遥感土地利用/覆盖的非参数分类。     

模糊神经网络高分辨率遥感影像监督分类

目的 针对高分辨率带来的像素类属不确定性增大及各类属间相关性增强引起的影像分类问题,提出一种模糊神经网络高分辨遥感影像监督分类方法。方法 提出的模型为包含输入层,隐含层（隶属函数层）及输出层的三层前向模糊神经网络,输入层用于接收来自训练样本的灰度值;隐含层每个神经元节点的模糊隶属函数为对各类别定义的高斯隶属函数模型,以实现对输入变量隶属程度的不确定表达;输出层的输入变量为隐含层各神经元节点输出变量的线性组合,激活函数为分段线性函数,该层实现输入变量隶属程度的相关性表达。以训练数据直方图作为期望输出,梯度下降法求解模型参数,最后按最大隶属度准则实现分类决策。结果 利用本文算法和经典算法对合成影像进行实验,本文方法总体精度达到0.931,相对于高斯隶属函数方法总体精度提高了5.3%,相对于最大似然法提高了4.2%,相对于FCM方法提高了5.9%,对真实WorldView-2全色影像的实验中文中方法分割精度也高于传统方法。结论 提出的模糊神经网络模型可以更加精确的拟合高分辨率遥感影像复杂的分布特征,有效处理高分辨率遥感影像的上述分类问题。     

SOM神经网络改进及在遥感图像分类中的应用*

针对自组织特征神经网络自身算法的特点和缺陷,采用遗传算法对网络进行改进,形成了基于遗传算法的自组织特征神经网络,并从输入向量、竞争层神经元数量设置和初始权向量设定三方面,结合遥感图像的特性对自组织特征映射网络遥感图像分类的方法进行了改进。将该方法应用于择西安地区的ETM+卫星遥感图像进行分类试验,结果表明,基于遗传算法的自组织特征映射网络使得遥感图像的分类精度更高,且该算法实现简单,具有一定的工程应用价值。     

Hyperspectral remote sensing image classification based on dense residual three-dimensional convolutional neural network

Multimedia Tools and Applications - Data-driven deep learning techniques set the current state of the art in image classification for hyperspectral remote sensing images. The lack of labeled...     

密集反卷积网络在遥感建筑物提取中的应用

遥感图像覆盖范围广、场景复杂,目前基于卷积神经网络的建筑物提取方法因层数较少,不能充分挖掘图像的抽象信息,导致正确率较低,错检率较高。简单地增加网络的层数会导致梯度流消失和信息流弥散等问题,无法有效地训练网络。将密集连接方式引入到反卷积网络中,提出了一种新型的深层密集反卷积神经网络。该网络共有51层卷积权重层,能够自动学习多层级图像的特征,充分挖掘图像信息,并且该网络是端对端可训练的,避免了深层网络中信息传递消失的问题。同时利用反卷积网络实现了像素级别的建筑物提取,在ISPRS 2D的遥感标注数据集上有良好的表现,具有较强的实际应用价值。     

Semisupervised self-learning granular neural networks for remote sensing image classification

Accuracy of a pattern classification model mostly depends on ample number of training samples, which is the major bottleneck for classifying land cover of remote sensing images. Further, the unbalance scenario typically encountered in hyperspectral remote sensing images, i.e., limited number of training samples with more dimensions, makes the decision-making process cumbersome. Under such inevitable constraints, the article aims to develop an improved classification model using semisupervised self-learning granular neural networks (GNNs) for remote sensing images. The proposed semisupervised method has adopted a new strategy for selecting the potential candidate samples from the unlabeled dataset and used GNN as the base classifier. We have considered GNN because of its transparent architecture that leads to improved performance with less computational complexity compared to the conventional neural networks. Performance of the model is further enhanced with fuzzy granulation of features using class belonging information and selection of granulated features using neighborhood rough sets (NRS). The proposed model thus takes the mutual advantages of GNN architecture, fuzzy granulation with class belonging information, NRS-based feature selection and the most important, improved semisupervised self-learning approach. Performance of the model is compared with other similar methods and verified in terms of different performance measurement indexes, using two multispectral and two hyperspectral remote sensing images.     

Minimal neural network topology optimization for aesthetic classification

Neural Computing and Applications - In this article, a minimum neural network topology in terms of units and connections (neurons and weights), making visual aesthetically categorized images, will...     

基于改进的三维卷积神经网络的高光谱遥感影像分类技术研究

高光谱遥感影像数据具有多样化的光谱信息和空间信息,然而传统的高光谱影像分类只是针对目标的光谱特征进行处理。基于三维空间滤波操作可以作为一种简单高效的提取高光谱影像光谱和空间特征的方式,基于此提出一种改进的三维卷积神经网络框架以实现更加准确的高光谱遥感影像分类。利用高光谱遥感影像数据立方体有效地提取光谱-空间组合特征,而不依赖于任何预处理或后期处理。另外,与其他传统的基于深度学习的方法相比,该方法去除了池化层,从而达到所需参数更少,模型规模更小,更容易训练的效果。将该方法与其他基于深度学习的高光谱遥感影像分类方法进行了比较,并使用两个真实场景的高光谱遥感影像数据集作为测试。实验结果表明,该方法在地物分类准确度方面较传统的基于深度学习的高光谱遥感影像分类方法取得了更好的分类效果。     

Research on hyper-spectral remote sensing image classification by applying stacked de-noising auto-encoders neural network

Multimedia Tools and Applications - Hyper-spectral image can provide precise information on land surface targets identification and classification thanks to its advanced feature on spectral...     

Analysis of classification accuracy for pre-filtered multichannel remote sensing data

Noise is one of the main factors degrading the quality of original multichannel remote sensing data and its presence influences classification efficiency, object detection, etc. Thus, pre-filtering is often used to remove noise and improve the solving of final tasks of multichannel remote sensing. Recent studies indicate that a classical model of additive noise is not adequate enough for images formed by modern multichannel sensors operating in visible and infrared bands. However, this fact is often ignored by researchers designing noise removal methods and algorithms. Because of this, we focus on the classification of multichannel remote sensing images in the case of signal-dependent noise present in component images. Three approaches to filtering of multichannel images for the considered noise model are analysed, all based on discrete cosine transform in blocks. The study is carried out not only in terms of conventional efficiency metrics used in filtering (MSE) but also in terms of multichannel data classification accuracy (probability of correct classification, confusion matrix). The proposed classification system combines the pre-processing stage where a DCT-based filter processes the blocks of the multichannel remote sensing image and the classification stage. Two modern classifiers are employed, radial basis function neural network and support vector machines. Simulations are carried out for three-channel image of Landsat TM sensor. Different cases of learning are considered: using noise-free samples of the test multichannel image, the noisy multichannel image and the pre-filtered one. It is shown that the use of the pre-filtered image for training produces better classification in comparison to the case of learning for the noisy image. It is demonstrated that the best results for both groups of quantitative criteria are provided if a proposed 3D discrete cosine transform filter equipped by variance stabilizing transform is applied. The classification results obtained for data pre-filtered in different ways are in agreement for both considered classifiers. Comparison of classifier performance is carried out as well. The radial basis neural network classifier is less sensitive to noise in original images, but after pre-filtering the performance of both classifiers is approximately the same.     

Decision tree regression for soft classification of remote sensing data

In recent years, decision tree classifiers have been successfully used for land cover classification from remote sensing data. Their implementation as a per-pixel based classifier to produce hard or crisp classification has been reported in the literature. Remote sensing images, particularly at coarse spatial resolutions, are contaminated with mixed pixels that contain more than one class on the ground. The per-pixel approach may result in erroneous classification of images dominated by mixed pixels. Therefore, soft classification approaches that decompose the pixel into its class constituents in the form of class proportions have been advocated. In this paper, we employ a decision tree regression approach to determine class proportions within a pixel so as to produce soft classification from remote sensing data. Classification accuracy achieved by decision tree regression is compared with those achieved by the most widely used maximum likelihood classifier, implemented in the soft mode, and a supervised version of the fuzzy c-means classifier. Root Mean Square Error (RMSE) and fuzzy error matrix based measures have been used for accuracy assessment of soft classification.     

递阶遗传粒子群算法在神经网络设计中的应用

将递阶遗传粒子群算法（HGAPSO）应用于神经网络设计,可以在对网络拓扑结构优化的同时对连接权重进行求解。该算法结合了遗传算法在解决离散问题和粒子群算法在解决连续问题上的优势,并利用BP算法沿误差最速下降的能力对连接权重进一步学习,达到全局最优和快速搜索的有机结合。通过对混沌时序信号的预测,表明递阶遗传粒子群算法在较大程度上提高了神经网络的学习性能和泛化能力。     

综合改进的粒子群神经网络算法

粒子群优化算法是一种解决非线性、不可微和多峰值复杂优化问题的优秀算法,但该算法在进化后期容易出现速度变慢以及早熟的现象;BP神经网络的学习算法是基于梯度下降这一本质的,因此存在着容易陷于局部极小值,收敛速度慢,训练时间长等问题.针对上述现象,对粒子群优化算法进行了增强粒子多样性和避免种群陷入早熟两个方面的改进,并提出了一种基于改进算法的粒子群神经网络算法,最后通过在IRIS数据集上进行的仿真实验验证了改进的有效性.     

Vegetation classification method with biochemical composition estimated from remote sensing data

In this article, a vegetation classification hypothesis based on plant biochemical composition is presented. The basic idea of this hypothesis is that the vegetation species/crops have their own biochemical composition characteristics, which are separable from each other for those co-existing species at a specific region. Therefore, vegetation species can be classified based on the biochemical composition characteristics, which can be retrieved from hyperspectral remote-sensing data. In order to test this hypothesis, an experiment was conducted in north-western China. Field data on the biochemical compositions and spectral responses of different plants and an Earth-observing 1 (EO-1) Hyperion image were simultaneously collected. After analysing the relationship between biochemical composition and spectral data collected from Hyperion, the vegetation biochemical compositions were estimated using sample biochemical data and bands of Hyperion data. The vegetation classification was completed using the biochemical content classifier (BCC) and maximum-likelihood classifier (MLC) with all Hyperion bands (MLC_A) and selected bands (MLC_S), which were used for estimating considered biochemical contents (cellulose and carotenoid). The overall classification accuracy of the BCC (95.2%) was as good as MLC_S (95.2%) and better than MLC_A (91.1%), as was the kappa value (BCC 92.849%, MLC_S 92.845%, MLC_A 86.637%), suggesting that the BCC was a feasible classification method. The biochemical-based classification method has higher vegetation classification accuracy and execution speed, reduces data dimension and redundancy and needs only a few spectral bands to retrieve biochemical contents instead of using all of the spectral bands. It is an effective method to classify vegetation based on plant biochemical composition characteristics.