Integration of object-based and pixel-based classification for mapping mangroves with IKONOS imagery

IKONOS 1-m panchromatic and 4-m multispectral images were used to map mangroves in a study site located at Punta Galeta on the Caribbean coast of Panama. We hypothesized that spectral separability among mangrove species would be enhanced by taking the object as the basic spatial unit as opposed to the pixel. Three different classification methods were investigated: maximum likelihood classification (MLC) at the pixel level, nearest neighbour (NN) classification at the object level, and a hybrid classification that integrates the pixel and object-based methods (MLCNN). Specifically for object segmentation, which is the key step in object-based classification, we developed a new method to choose the optimal scale parameter with the aid of Bhattacharya Distance (BD), a well-known index of class separability in traditional pixel-based classification. A comparison of BD values at the pixel level and a series of larger scales not only supported our initial hypothesis, but also helped us to determine an optimal scale at which the segmented objects have the potential to achieve the best classification accuracy. Among the three classification methods, MLCNN achieved the best average accuracy of 91.4%. The merits and restrictions of pixel-based and object-based classification methods are discussed.     

Learning multi-level and multi-scale deep representations for privacy image classification

Multimedia Tools and Applications - Privacy image classification can help people detect privacy images when people share images. In this paper, we propose a novel method using multi-level and...     

基于组合分类器的遥感图像多尺度分类研究

遥感图像（RSI）的特殊性使得图像的准确分类变得非常困难。提出了一种自适应多尺度分割的组合分类算法。采用组合分类的办法,也就是将一组功能较弱的分类器联合起来构成一个功能较强的分类器。每一个较弱的分类器都由一级分割来训练并且描述。较弱的分类器可以由线性支持向量机（SVM）和区域距离构成。实验表明该方法能够准确地实现图像的分类并且与实际图像相符。此外,采用分级的多尺度分析方法能够减少训练时间,得到一个性能更好的分类器。仿真表明该方法比其他方法性能更优。     

Bi-directional LSTM with multi-scale dense attention mechanism for hyperspectral image classification

Feature representation has always been the top priority of research in the field of hyperspectral image (HSI) classification. Efficient analysis of those features extracted from HSI massively depends on the way how features are represented. In this paper, we propose a bi-directional long short-term memory network (Bi-LSTM)-based multi-scale dense attention framework, namely MBDA-Net. In this framework, we develop a new multi-scale dense attention module (MCDA) that uses different sizes of convolution kernels to obtain multi-scale features. Then, we perform feature selection by using a multi-layer attention mechanism that assigns different weight coefficients to the extracted multi-scale features. Specifically, we use the bi-directional LSTM to obtain contextual semantic information. The extensive experiments conducted on three hyperspectral datasets demonstrate the effectiveness of our method in identifying hyperspectral images.

     

基于ECA-Net与多尺度结合的细粒度图像分类方法

针对细粒度图像分类问题提出了一种有效的算法以实现端到端的细粒度图像分类.ECA-Net中ECA(efficient channel attention)模块是一种性能优势显著的通道注意力机制,将其与经典网络ResNet-50进行融合构成新的基础卷积神经网络ResEca;通过物体级图像定位模块与部件级图像生成模块生成物体级图像和部件级图像,并结合原始图像作为网络的输入,构建以ResEca为基础的三支路网络模型Tb-ResEca-Net(three branch of ResEca network).该算法在公有数据集CUB-200-2011、FGVC-aircraft和Stanford cars datasets上进行测试训练,分别取得了89.9％、95.1％和95.3％的准确率.实验结果表明,该算法相较于其他传统的细粒度分类算法具有较高的分类准确率以及较强的鲁棒性,是一种有效的细粒度图像分类方法.     

Extraction of urban impervious surfaces from an IKONOS image

Impervious surface has been recognised as an important indicator in urban environmental assessment. However, accurate extraction of impervious surface information in urban areas is a challenge because of the complexity of impervious materials. This paper explores different approaches for impervious surface extraction with IKONOS imagery in Indianapolis, U.S.A., by using decision tree classifier (DTC) and linear spectral mixture analysis (LSMA). This research indicates that DTC is an effective approach for extraction of different impervious surface classes, including high‐, medium‐ and low‐reflectivity impervious surfaces and that LSMA‐based approach can provide quantitative measure of imperviousness. A critical step is to separate dark impervious objects/features from shadows cast by tall buildings and tree canopy and from water.     

Photogrammetric exploitation of IKONOS imagery for mapping applications

The launch of IKONOS by Space Imaging opens a new era of high-resolution satellite imagery collection and mapping. The IKONOS satellite simultaneously acquires 1?m panchromatic and 4?m multi-spectral images in four bands that are suitable for high accuracy mapping applications. Space Imaging uses the rational function model (RFM), also known as rational polynomial camera model, instead of the physical IKONOS sensor model to communicate the imaging geometry. As revealed by recent studies from several researchers, the RFM retains the full capability of performing photogrammetric processing in absence of the physical sensor model. This paper presents some RFM-based processing methods and mapping applications developed for 3D feature extraction, orthorectification and RPC model refinement using IKONOS imagery. Comprehensive tests are performed to test the accuracy of 3D reconstruction and orthorectification and to validate the feasibility of the model refinement techniques.     

Exploring the synergistic use of multi-scale image object metrics for land-use/land-cover mapping using an object-based approach

This study presents a new method for the synergistic use of multi-scale image object metrics for land-use/land-cover mapping using an object-based classification approach. This new method can integrate an object with its super-objects’ metrics. The entire classification involves two object hierarchies: (1) a five-level object hierarchy to extract object metrics at five scales, and (2) a three-level object hierarchy for the classification process. A five-level object hierarchy was developed through multi-scale segmentation to calculate and extract both spectral and textural metrics. Layers representing the hierarchy at each of the five scales were then intersected by using the overlay tool, an intersected layer was created with metrics from all five scales, and the same geometric elements were retained as those of the objects of the lowest level. A decision tree analysis was then used to build rules for the classification of the intersected layer, which subsequently served as the thematic layer in a three-level object hierarchy to identify shadow regions and produce the final map. The use of multi-scale object metrics yielded improved classification results compared with single-scale metrics, which indicates that multi-scale object metrics provide valuable spatial information. This method can fully utilize metrics at multiple scales and shows promise for use in object-based classification approaches.     

Feature selection by genetic algorithms in object-based classification of IKONOS imagery for forest mapping in Flanders, Belgium

Obtaining detailed information about the amount of forest cover is an important issue for governmental policy and forest management. This paper presents a new approach to update the Flemish Forest Map using IKONOS imagery. The proposed method is a three-step object-oriented classification routine that involves the integration of 1) image segmentation, 2) feature selection by Genetic Algorithms (GAs) and 3) joint Neural Network (NN) based object-classification. The added value of feature selection and neural network combination is investigated. Results show that, with GA-feature selection, the mean classification accuracy (in terms of Kappa Index of Agreement) is significantly higher (p < 0.01) than without feature selection. On average, the summed output of 50 networks provided a significantly higher (p < 0.01) classification accuracy than the mean output of 50 individual networks. Finally, the proposed classification routine yields a significantly higher (p < 0.01) classification accuracy as compared with a strategy without feature selection and joint network output. In addition, the proposed method showed its potential when few training data were available.     

Interactive multi-scale exploration for volume classification

Filter banks are a class of signal processing techniques that can be used to reveal the local energy of a signal at multiple scales. Utilizing such filtering allows us to consider local texture and other data characteristics, and permits volume classification and visualization that cannot be accomplished easily using conventional, transfer function-based methods. Our filter bank approach increases the dimensionality, and thus, the complexity of the classification task. We have therefore developed an interactive user interface for specifying and visualizing these higher dimensional classifiers, which enables volume data exploration and visualization in a filter-bank space. We demonstrate that this technique is particularly effective for the classification of noisy data, and for classifying regions that are difficult to approach using conventional methods.     

多尺度深度特征提取的肝脏肿瘤CT图像分类

目的 肝脏肿瘤是人体最具侵袭性的恶性肿瘤之一,传统的肿瘤诊断依靠观察患者的CT（computed tomography）图像,工作量大时易造成疲劳,难免会产生误诊,为此使用计算机辅助的方法进行诊断,但现有的深度学习方法中存在肿瘤分类准确率低、网络的特征表达能力和特征提取能力较弱等问题。对此,本文设计了一种多尺度深度特征提取的分类网络模型。方法 首先在原始CT图像中选取感兴趣区域,然后根据CT图像的头文件进行像素值转换,并进行数据增强来扩充构建数据集,最后将处理后的数据输入到本文提出的分类网络模型中输出分类结果。该网络通过多尺度特征提取模块来提取图像的多尺度特征并增加网络的感受野,使用深度特征提取模块降低背景噪声信息,并着重关注病灶区域有效特征,通过集成并行的空洞卷积使得尺度多元化,并将普通卷积用八度卷积替换来减少参数量,提升分类性能,最终实现了对肝脏肿瘤的精确分类。结果 本文模型达到了87.74%的最高准确率,比原始模型提升了9.92%;与现有主流分类网络进行比较,多项评价指标占优,达到了86.04%的召回率,87%的精准率,86.42%的F1分数;此外,通过消融实验进一步验证了所提方法的有效性。结论 本文方法可以较为准确地对肝脏肿瘤进行分类,将此方法结合到专业的医疗软件当中去,能够为医生早期的诊断和治疗提供可靠依据。     

多尺度融合注意力机制的胆囊癌显微高光谱图像分类

目的 胆囊癌作为胆道系统中一种恶性程度极高的肿瘤,早期诊断困难、预后极差,因此准确鉴别胆囊病变对早期发现胆囊癌具有重要意义。目前胆囊癌的诊断主要依赖于超声、CT(computed tomography)等传统影像学方法,但准确性较低。显微高光谱能够在获取生物组织图像信息的同时从生化角度对生物组织进行分析,从而实现对胆囊癌的早期诊断,相比于传统医学图像更具优势。因此,本文基于胆囊癌显微高光谱图像设计了一种基于多尺度融合注意力机制的网络模型,以提高分类准确率。方法 提出多尺度融合注意力模块（multiscale squeeze-andexcitation-residual, MSE-Res）。MSE-Res模块引入改进的多尺度特征提取模块实现通道维上特征的融合,用一个最大池化层和一个上采样层代替1×1的卷积层来提取图像的显著特征。为了弥补池化层丢失的局部信息,在跳跃连接中加入一个1×1的卷积层。在多尺度特征提取模块后,引入注意力机制来学习不同通道间特征的相关性,实现通道间特征的融合,并通过残差连接使网络在提取图像深层特征的同时避免出现过拟合现象。结果 在胆囊癌高光谱数据集上进行实验,本文模...     

快速图像保边界多尺度分解

提出一种新的非线性保边界平滑算法,通过对图像每个像素点的某个邻域内所有颜色相似的像素简单平均,来对图像进行平滑处理。该算法不仅能够进行保边界平滑,并且具有非常高的运算效率。应用这种平滑算法可以对图像进行快速保边界多尺度分解。运用多尺度分解实现了图像的增强、抽象化、对比度调整的效果。     

一种改进的多尺度Retinex色调映射算法

传统的低动态范围显示设备不能很好地表现高动态范围图像信息,针对这一问题,提出一种基于引导滤波的Retinex多尺度分解色调映射算法。该算法使用引导滤波对光照信息进行估计,将高动态范围图像的亮度分为光照层和反射层;然后对反射层分量进行多尺度分解,得到一系列细节层和一个基本层,将细节层和基本层进行合并和色彩还原;最后得到色调映射后的图像。实验结果表明,该算法可以较好地还原真实场景信息,映射后图像的细节和对比度较好,色彩鲜艳。     

Context inclusive function evaluation: a case study with EM-based multi-scale multi-granular image classification

Many statistical queries such as maximum likelihood estimation involve finding the best candidate model given a set of candidate models and a quality estimation function. This problem is common in important applications like land-use classification at multiple spatial resolutions from remote sensing raster data. Such a problem is computationally challenging due to the significant computation cost to evaluate the quality estimation function for each candidate model. For example, a recently proposed method of multi-scale, multi-granular classification has high computational overhead of function evaluation for various candidate models independently before comparison. In contrast, we propose an upper bound based context-inclusive approach that reduces computational overhead based on the context, i.e. the value of the quality estimation function for the best candidate model so far. We also prove that an upper bound exists for each candidate model and the proposed algorithm is correct. Experimental results using land-use classification at multiple spatial resolutions from satellite imagery show that the proposed approach reduces the computational cost significantly.     

A multi-scale attentive recurrent network for image dehazing

Multimedia Tools and Applications - Image dehazing is a pre-processing step in computer vision tasks, that has attracted considerable attention from the research community. Existing CNN-based...     

Local image quality measurement for multi-scale forensic palmprints

Numerous studies show that palmprint image quality has a significant effect on every stage of a palmprint recognition system. Although some palmprint image quality measurement(PIQM) methods are proposed, some insufficiency in classification accuracy occurs and attention to detail in measuring local area image quality of multi-scale palmprint images is lacking. On the one hand, the classification accuracy is not very high for 2-class classification and it degrades significantly as the number of classes increases. On the other hand, local area image quality measurement of multi-scale palmprint images has not yet been resolved since the handcrafted features designed through domain knowledge usually works for certain scale image blocks. Meanwhile, the intricate domain knowledge used in the previous methods is difficult for some common users to acquire. In this paper, we propose an end-to-end deep-learning method of strengthening representation ability that learns more abstract, essential, and reliable features to measure the local image quality for multi-scale forensic palmprints. Popular convolutional neural networks (CNNs) are considered because of their powerful representation ability in learning complex features. However, the powerful existing CNNs usually have complex architectures with a large amount of parameters, which need the support of high-performance computers. They are not suitable to be used directly for palmprint image quality assignment and the follow-up palmprint recognition work, which prefers real-time response on commonly available personal computers or even mobile devices. Hence, a new lightweight CNN must be designed to achieve a trade-off between high classification accuracy and practical usability. Considering the attributes of under-processed input images, we reduce the weight of the CNN architecture by reducing the amount of some parameters, and finally a lightweight CNN is designed. As a result, a raw rectangular palmprint image of variable size can be put into the trained model directly and a quality label quickly predicted with high accuracy. After comparison with previous methods, results show that the proposed method can deal with un-pre-processed raw images of a multi-scale input size. Furthermore, it can acquire a richer amount of quality classes with a higher accuracy, which are stable on many different datasets. It also leads to finer and more precise full palmprint image quality maps when compared to previous methods.

     

Exploiting multi-scale support vector regression for image compression

Unlike traditional neural networks that require predefined topology of the network, support vector regression (SVR) approach can model the data within the given level of accuracy with only a small subset of the training data, which are called support vectors (SVs). This property of sparsity has been exploited as the basis for image compression. In this paper, for still image compression, we propose a multi-scale support vector regression (MS-SVR) approach, which can model the images with steep variations and smooth variations very well resulting in good performance. We test our proposed MS-SVR based algorithm on some standard images. The experimental results verify that the proposed MS-SVR achieves better performance than standard SVR. And in a wide range of compression ratio, MS-SVR is very close to JPEG in terms of peak signal-to-noise ratio (PSNR) but exhibits better subjective quality. Furthermore, MS-SVR even outperforms JPEG on both PSNR and subjective quality when the compression ratio is higher enough, for example 25:1 for Lena image. Even when compared with JPEG-2000, the results show greatly similar trend as those in JPEG experiments, except that the compression ratio is a bit higher where our proposed MS-SVR will outperform JPEG-2000.