融合边界信息的高分辨率遥感影像分割优化算法

目的 针对目前区域分割算法获取的区域边界与真实地物边界不一致问题,利用高分辨率遥感影像地物内具有均质性和地物间边缘信息突出的特点,提出一种融合边界信息的高分辨率遥感影像分割优化算法。方法 首先采用Canny算法对遥感影像进行边缘提取并进行边缘连接处理,产生闭合边界;然后将边界与初始分割结果进行融合处理,获得新的分割结果;最后在闭合边界约束下,基于灰度相似性准则对新的分割结果进行区域合并,获得优化后的最终分割结果。结果 采用本文提出的分割优化算法对Mean Shift算法和eCognition软件获得的分割结果进行优化处理,优化后的分割结果与初始分割结果相比正确分割率（RR）平均提高了4%,验证了本文算法的有效性。结论 该优化算法适用性广,可优化基于区域、基于边界和基于聚类等多种分割方法,同时该算法既能保持高分辨率遥感影像分割的区域完整性,又能保持地物边缘细节特征,提高了分割精度。     

Accurate object retrieval for high-resolution remote-sensing imagery using high-order topic consistency potentials

We propose incorporating semantic topic information into a hierarchical conditional random fields (CRFs) framework to promote object recognition and retrieval accuracy. Specially, we devise convenient yet effective methods based on multiple segmentations to perform accurate image retrieval tasks for rigid and amorphous man-made objects. Through a robust topic consistency potential (RTCP) modelling approach, we perform accurate multi-class segmentation on high-resolution remote-sensing images. The generated segments can be readily used for object recognition and discovery. We report satisfactory the performance on two sets of high-resolution remote-sensing images that cover a highly populated urban area and a rural area, respectively. Experimental results demonstrate that our approach outperforms the state-of-the-art CRF models, due to its ability to capture inherent semantic information for efficient object recognition and boundary discovery.     

Detecting changes in high-resolution satellite coastal imagery using an image object detection approach

This article presents a spatial contrast-enhanced image object-based change detection approach (SICA) to identify changed areas using shape differences between bi-temporal high-resolution satellite images. Each image was segmented and intrinsic image objects were extracted from their hierarchic candidates by the proposed image object detection approach (IODA). Then, the dominant image object (DIO) presentation was labelled from the results of optimal segmentation. Comparing the form and the distribution of bi-temporal DIOs by using the raster overlay function, ground objects were recognized as being spatially changed where the corresponding image objects were detected as merged or split into geometric shapes. The result of typical spectrum-based change detection between two images was enhanced by using changed spatial information of image objects. The result showed that the change detection accuracies of the pixels with both attribute and shape changes were improved from 84% to 94% for the strong attribute pixel, and from 36% to 81% for the weak attribute pixel in study area. The proposed approach worked well on high-resolution satellite coastal images.     

结合多尺度分割和形态学运算的高分辨率遥感影像阴影检测

目的 针对阴影在高分辨率遥感影像的特性,提出了一种多尺度分割和形态学运算相结合的阴影检测方法。方法 基于面向对象思想,首先利用均值漂移法实现影像分割生成对象,并以对象为基本单元分别进行形态学膨胀和腐蚀运算,从而获得面向对象的阴影指数;然后对影像进行多尺度分割,生成阴影指数矢量;最后对阴影指数矢量和亮度均值分别指定高低阈值,进而获得阴影检测结果。结果 选取高分二号和Google earth影像进行实验,采用误检率、漏检率和总错误率3个指标进行定量分析,并将实验结果与结合多特征法和形态学阴影指数法进行比较。在阴影检测定量精度分析中,相比于对比方法,本文方法的误检率偏高,但漏检率平均降低了7.31%;在建筑物阴影检测实验中,本文方法的漏检率同样下降了4.5个百分点;在多尺度效果融合分析中,本文方法在多组尺度组合下,各项精度指标均较理想;在阴影压盖地物实验中,3种方法的误检情况差异不大,但本文方法的漏检率得到较大改善,其下降程度平均达到了19.29%。结论 本文提出的阴影检测方法具备一定的抗干扰能力,适用性强,可靠性高。     

运动目标的自动空时分割算法

在视频应用中,运动目标的提取是一个重要的研究课题。为了对运动目标进行更有效的分割,提出了一种从视频序列中自动提取运动目标的空时分割算法。该算法在时域分割中采用基于齐异矢量消除的目标检测方法来获得运动目标的初始模板。通常,该初始模板具有不连续的边界和一些"孔"。为了得到较为完整的目标区域,用具有距离约束的区域生长算法来补偿初始模板。而在空域分割中,分水岭分割则通过考虑全局信息来增强其分割的精确性。然后,精确的运动目标即可通过空时融合模块提取出来。试验结果表明,该空时分割算法是有效的。     

Object-oriented change detection based on the Kolmogorov–Smirnov test using high-resolution multispectral imagery

In this article, we propose a novel method of object-oriented change detection for high-resolution remote-sensing imagery. The method consists of three main parts: image segmentation, object adjusting and change detection. We use the Fractal Net Evolution Approach to segment the multi-temporal images. Then we adjust the object maps. By merging the objects in relatively large areas, the object -adjusting algorithm aims to obtain a set of objects with different sizes, which coincide better with the real ground objects than the single-scale results. In the third part, the Kolmogorov–Smirnov two-sample test detects each pair of objects in the multi-temporal object maps with multi-scale. The calculated value of the D-statistic is compared to the threshold of a user-defined significance level. Through these three processes, we can make full use of the spatial and spectral features in high- resolution images to detect changes. According to our experiments in two study areas employing QuickBird imagery, the overall errors of our method decreased by more than 1000 pixels compared with the conventional object-oriented change vector analysis. The proposed method can also avoid the errors resulting from classification in the method of post-classification comparison.     

Automatic change detection in high-resolution remote-sensing images by means of level set evolution and support vector machine classification

In this article, we propose a method for change detection in high-resolution remote-sensing images by means of level set evolution and support vector machine (SVM) classification, which combined both the pixel-level method and the object-level method. Both pixel-based change features and object-based ones are extracted to improve the discriminability between the changed class and the unchanged class. At the pixel level, the change detection problem is formulated as a segmentation issue using level set evolution in the difference images. At the object level, potential training samples are selected from the segmentation results without manual intervention into the SVM classifier. Thereafter, the final changes are obtained by combining the pixel-based changes and the object-based changes. A chief advantage of our approach is being able to select appropriate samples for SVM classifier training. Furthermore, our proposed method helps improve the accuracy and the degree of automation. We systematically evaluate it with various Satellite Pour l’Observation de la Terre (SPOT) 5 images and aerial images. Experimental results demonstrate the accuracy of our proposed method.     

A modified object-oriented classification algorithm and its application in high-resolution remote-sensing imagery

High-resolution satellite images offer abundant information on the Earth's surface for remote-sensing applications. The traditional pixel-based image classification method only used by spectral information has been proved to have several drawbacks. To satisfactorily interpret high-resolution imagery, other important information such as geometry, texture and semantics must be used, which are represented not only in single pixels but in meaningful image objects. So, a modified high-resolution image classification algorithm with multi-characteristics based on objects is presented in this article. First, image objects are extracted by multi-scale multi-characteristic segmentation. Second, characteristics such as spectral information, geometry, texture and semantics are extracted by the corresponding extraction algorithm. Finally, the image objects are classified by means of fuzzy-logic classification with a weighted average calculation method. Preliminary results show promise in terms of classification quality and accuracy.     

结合深度学习和超像元的高分遥感影像变化检测

目的 随着遥感影像空间分辨率的提升,相同地物的空间纹理表现形式差异变大,地物特征更加复杂多样,传统的变化检测方法已很难满足需求。为提高高分辨率遥感影像的变化检测精度,尤其对相同地物中纹理差异较大的区域做出有效判别,提出结合深度学习和超像元分割的高分辨率遥感影像变化检测方法。方法 将有限带标签数据分割成切片作训练样本,按照样本形式设计一个多切片尺度特征融合网络并对其训练,获得测试图像的初步变化检测结果;利用超像元分割算法将测试图像分割成许多无重叠的同质性区域,并将分割结果与前述检测结果叠合,得到带分割标记的变化检测结果;用举手表决算法统计带分割标记的变化检测结果中超像元的变化状况,得到最终变化检测结果。结果 在变化检测实验结果中,本文提出的多切片尺度特征融合卷积网络模型在广东数据集和香港数据集上,优于单一切片尺度下卷积神经网络模型,并且结合超像元的多切片尺度特征融合卷积网络模型得到的Kappa系数分别达到80%和82%,比相应的非超像元算法分别提高了6%和8%,在两个测试集上表现均优于长短时记忆网络、深度置信网络等对比算法。结论 本文提出的卷积神经网络变化检测方法可以充分学习切片的空间信息和其他有效特征,避免过拟合现象;多层尺度切片特征融合的方法优于单一切片尺度训练神经网络的方法;结合深度学习和超像元分割算法,检测单元实现了由切片到超像元的转变,能对同物异谱的区域做出有效判决,有利于提升变化检测精度。     

LRSS-Net:轻量级遥感地物分割网络

针对目前基于深度学习的高分辨率遥感图像分割模型由于参数量大、计算复杂而导致高延迟、低响应的问题,提出了一种轻量级遥感地物分割方法,较好的平衡了速度和精度.该方法使用MobileNetV2进行特征粗提取,通过构建空间信息嵌入分支实现不同尺度的特征细提取,不同层次之间引入密集连接以获取密集的上下文信息.解码端设计特征融合优化策略逐层融合不同尺度的特征增加对细粒度特征的感知,同时以反卷积与双线性插值交替的上采样方式减少图像边缘信息丢失.最后采用交叉熵损失与Dice损失结合的方式加快网络收敛速度.为了验证所提方法的有效性,与几种常用的语义分割方法进行了对比实验.实验结果表明,所提算法的分割准确率为93.7%,MIoU为88.01%,可以实现地物的有效分割.     

Shape-based object extraction in high-resolution remote-sensing images using deep Boltzmann machine

In this article, we proposed a novel method based on deep learning shape priors for object extraction in high-resolution (HR) remote-sensing images. Specifically, the deep Boltzmann machines (DBMs) are applied to model the shape priors via the unsupervised training process, which qualify for the advantages of deep learning method, especially the powerful feature learning and modelling ability. The deep shape model is integrated into a new energy function to eliminate the influence of disturbing background. The energy function combines image appearance information and region information. A new region term in the function is proposed to eliminate the influence of object shadow. The process of object extraction is achieved by minimizing the energy function with an iterative optimization algorithm and the Split Bregman method is applied to derive a global solution during the minimization process. Quantitative and qualitative experiments are conducted on the aircraft data set acquired by QuickBird with 60 cm resolution and the results demonstrate the effectiveness of the proposed method.     

特征注意金字塔调制网络的视频目标分割

目的 视频目标分割是在给定第1帧标注对象掩模条件下,实现对整个视频序列中感兴趣目标的分割。但是由于分割对象尺度的多样性,现有的视频目标分割算法缺乏有效的策略来融合不同尺度的特征信息。因此,本文提出一种特征注意金字塔调制网络模块用于视频目标分割。方法 首先利用视觉调制器网络和空间调制器网络学习分割对象的视觉和空间信息,并以此为先验引导分割模型适应特定对象的外观。然后通过特征注意金字塔模块挖掘全局上下文信息,解决分割对象多尺度的问题。结果 实验表明,在DAVIS 2016数据集上,本文方法在不使用在线微调的情况下,与使用在线微调的最先进方法相比,表现出更具竞争力的结果,J-mean指标达到了78.7%。在使用在线微调后,本文方法的性能在DAVIS 2017数据集上实现了最好的结果,J-mean指标达到了68.8%。结论 特征注意金字塔调制网络的视频目标分割算法在对感兴趣对象分割的同时,针对不同尺度的对象掩模能有效结合上下文信息,减少细节信息的丢失,实现高质量视频对象分割。     

Extraction of bridges over water from high-resolution optical remote-sensing images based on mathematical morphology

Bridges over water are typical man-made structures on the land’s surface. An accurate extraction of such bridges from high-resolution optical remote-sensing images plays an important role in civil, commercial, and military applications. Considering the complex features of ground objects within high-resolution optical remote-sensing images and the inefficiency of previous methods of bridge extraction with random bridge orientation, direction-augmented linear structuring elements were constructed and applied in this study by using mathematical morphology to identify and extract bridges over water with different orientations. First, the image pre-processing is performed to facilitate the object extraction. Then by using the histogram-based threshold segmentation method, water bodies such as rivers are extracted and described as a binary image. Based on water bodies, the appropriate direction-augmented linear structuring element is then selected. Together with mathematical morphology operations, such as dilation and erosion, potential bridges are extracted by overlay analysis. Assisted by prior knowledge of bridges, false bridges are screened out and post-processing is finally performed to refine the extracted true bridges. This approach was validated with experiments in Shanghai and Beijing, China. The results show that the direction-augmented linear structuring elements are of high precision and have the capability of extracting bridges over water in different directions within the high-resolution optical remote-sensing image, considering both qualitative and quantitative aspects. Therefore, this approach may be useful in updating geographical databases of bridges and facilitating the assessment of bridge damage caused by natural disasters.     

Object discovery in high-resolution remote sensing images: a semantic perspective

Given its importance, the problem of object discovery in high-resolution remote-sensing (HRRS) imagery has received a lot of attention in the literature. Despite the vast amount of expert endeavor spent on this problem, more efforts have been expected to discover and utilize hidden semantics of images for object detection. To that end, in this paper, we address this problem from two semantic perspectives. First, we propose a semantic-aware two-stage image segmentation approach, which preserves the semantics of real-world objects during the segmentation process. Second, to better capture semantic features for object discovery, we exploit a hyperclique pattern discovery method to find complex objects that consist of several co-existing individual objects that usually form a unique semantic concept. We consider the identified groups of co-existing objects as new feature sets and feed them into the learning model for better performance of image retrieval. Experiments with real-world datasets show that, with reliable segmentation and new semantic features as starting points, we can improve the performance of object discovery in terms of various external criteria.

---

多信息动态融合的运动目标检测方法

针对基于视觉显著性的运动目标检测算法存在时空信息简单融合及忽略运动信息的问题,提出一种动态融合视觉显著性信息和运动信息的运动目标检测方法。该方法首先计算每个像素的局部显著度和全局显著度,并通过贝叶斯准则生成空间显著图;然后,利用结构随机森林算法预测运动边界,生成运动边界图;其次,根据空间显著图和运动边界图属性的变化,动态确定最佳融合权值;最后,根据动态融合权值计算并标记运动目标。该方法既发挥了显著性算法和运动边界算法的优势,又克服了各自的不足,与传统背景差分法和三帧差分法相比,检出率和误检率的最大优化幅度超过40%。实验结果表明,该方法能够准确、完整地检测出运动目标,提升了对场景的适应性。     

Integrating multiple cues into adaptive hierarchical segmentation for high-resolution remote-sensing images

Image segmentation has been, and still is, a hot research topic in computer vision and pattern recognition. However, few existing segmentation algorithms are suitable for all objects presented in high-resolution remote-sensing (HRRS) images, because the relevant methods often implement segmentation in the same mode for the whole image rather than considering the different characteristics of various objects. Therefore, this article proposes an adaptive hierarchical segmentation framework for HRRS images by integrating multiple cues (e.g. intensity, texture and boundary). This two-stage framework first analyses the class of region presented in the study image, then according to this analysis, partitions each region class by adaptively utilizing the proper segmentation method with the most representative features. The distinctive characteristics of this framework are that the first stage simplifies the problem before using the segmentation method, and the second stage guarantees that the segmentation is carried out with the representative cues and corresponding suitable method for these cues. The performance of the proposed segmentation framework is demonstrated through a complete set of experimental results and substantiated using quantitative criteria.     

A multilevel decision fusion approach for urban mapping using very high-resolution multi/hyperspectral imagery

A novel multilevel decision fusion approach is proposed for urban mapping using very-high-resolution (VHR) multi/hyperspectral imagery. The proposed framework consists of three levels: (1) at level I, we first propose a self-dual filter for extracting structural features from the VHR imagery–subsequently, the spectral and structural features are integrated based on a weighted probability fusion; (2) level II extends level I by implementing the spectral–structural fusion in an object-based framework; and (3) at level III, the object-based probabilistic outputs at level II are used to identify unreliable objects, and shape attributes of these unreliable objects are then considered for refinement of classification. At this level, a decision-level object merging is used to improve the initial segmentation, since shape feature extraction is highly dependent on the quality of segmentation. Experiments were conducted on a Hyperspectral Digital Imagery Collection Experiment (HYDICE) DC Mall image and a QuickBird Beijing data set. The results revealed that the proposed approach provided progressively increasing accuracies when the multilevel features were gradually considered in the processing chain.     

A subclass supported convolutional neural network for object detection and localization in remote-sensing images

This article proposes a novel subclass-based classifier based on convolutional neural networks (CNNs) for detecting objects more accurately on remote-sensing images. The proposed classifier, called subclass supported CNN (SSCNN), is used to separate the representation of the objects into subclasses such as nearcentre, centre, and border depending on the distance of the object centre to obtain more effective feature extractor. A three-stage object recognition framework is used to evaluate the performance of the proposed classifier. In the first of these stages, the Selective Search algorithm generates object proposals from the image. Then, the proposed SSCNN classifies the proposals. Finally, subclass-based localization evaluation function has been proposed to calculate the localization of the object with classification results. Due to the limited number of satellite image samples, pretrained AlexNet is used by transfer learning approach to build effective feature extractor. The proposed method has been compared with region-based CNN (R-CNN) on a four-class remote-sensing test dataset consisting of 411 airplanes, 240 baseball diamonds, 468 storage tanks, and 83 ground track fields. In addition, Faster R-CNN has been trained with SSCNN features and the performances of the trained Faster R-CNNs are comparatively evaluated on 10-class remote-sensing image dataset. Experiment results have shown that the proposed framework can locate the objects precisely.     

基于多特征融合的视频交通数据采集方法

提出了一种基于多特征融合的视频交通数据采集方法, 核心思想是: 在图像中设置虚拟线圈, 假设车辆从虚拟线圈上驶过时引起像素变化, 通过识别这种像素变化来检测车辆并估计车速. 与现有技术相比, 本文的贡献在于: 1) 综合利用虚拟线圈内的前景面积、纹理变化、像素运动等特征来检测车辆, 提出了有效的多特征融合方法, 显著提高了车辆检测精度; 2) 根据单个虚拟线圈内的像素运动向量来估计车速, 避免了双线圈测速法的错误匹配问题. 算法测试结果表明本文算法能够在复杂多样的交通场景和天气条件下, 准确地检测车辆和估计车速. 在算法研究的基础上, 研制了一款嵌入式交通视频检测器, 在路口长期采集交通数据, 为交通信号控制和交通规律分析提供决策依据.     

A novel method for assessing the segmentation quality of high-spatial resolution remote-sensing images

Image segmentation quality significantly affects subsequent image classification accuracy. It is necessary to develop effective methods for assessing image segmentation quality. In this paper, we present a novel method for assessing the segmentation quality of high-spatial resolution remote-sensing images by measuring both area and position discrepancies between the delineated image region (DIR) and the actual image region (AIR) of a scene object. In comparison with the most frequently used area coincidence-based methods, our method can assess the segmentation quality more objectively in that it takes into consideration all image objects intersecting with the AIR of a scene object. Moreover, the proposed method is more convenient to use than the existing boundary coincidence-based methods in that the calculation of the distance between the boundary of the image object and that of the corresponding AIR of the scene object is not required. Another benefit of this method over the two types of method above is that the assessment procedure of the segmentation quality can be conducted with less human intervention. The obtained optimal segmentation result can ensure maximal delineation of the extent of scene objects and can be beneficial to subsequent classification operations. The experimental results have shown the effectiveness of this new method for both segmentation quality assessment and optimal segmentation parameter selection.