共查询到20条相似文献，搜索用时 15 毫秒
1.
Crowdsourcing can efficiently complete tasks that are difficult to automate, but the quality of crowdsourced data is tricky to evaluate. Algorithms to grade volunteer work often assume that all tasks are similarly difficult, an assumption that is frequently false. We use a cropland identification game with over 2,600 participants and 165,000 unique tasks to investigate how best to evaluate the difficulty of crowdsourced tasks and to what extent this is possible based on volunteer responses alone. Inter‐volunteer agreement exceeded 90% for about 80% of the images and was negatively correlated with volunteer‐expressed uncertainty about image classification. A total of 343 relatively difficult images were independently classified as cropland, non‐cropland or impossible by two experts. The experts disagreed weakly (one said impossible while the other rated as cropland or non‐cropland) on 27% of the images, but disagreed strongly (cropland vs. non‐cropland) on only 7%. Inter‐volunteer disagreement increased significantly with inter‐expert disagreement. While volunteers agreed with expert classifications for most images, over 20% would have been mis‐categorized if only the volunteers’ majority vote was used. We end with a series of recommendations for managing the challenges posed by heterogeneous tasks in crowdsourcing campaigns. 相似文献
2.
ABSTRACTPhoto-sharing services provide a rich resource of crowdsourced spatial data consisting of georeferenced imagery and metadata. Shared photos can provide valuable information for a variety of applications and geospatial analysis tasks, such as identifying tourist hot spots or traveled routes. Understanding the spatiotemporal patterns of photo contributions will allow analysts to assess the suitability of these data for related analysis tasks. Using California as a study area, this paper analyzes various aspects of photo contribution patterns of Panoramio and Flickr. It identifies areas where annual photo contributions are still growing and areas that undergo a decline in annual contributions. Multiple regression is used to identify which environmental correlates are associated with an increase in photo-sharing activities. Furthermore, panel data of annual contributions between 2006 and 2013 for California subcounties will be used in a regression model to demonstrate that there is a positive feedback effect between Panoramio and Flickr photo contributions, but no neighborhood effect. The results of this paper provide insight into the data quality of crowdsourced image collections. These collections are commonly used for geospatial applications, including tourist information services and the computation of scenic routes. 相似文献
3.
提出了一种顾及信誉度的众源时空数据模型。在分析众源时空数据中地理要素、目标状态、对象版本、贡献者、信誉度、改变现实空间实体或信息空间对象状态的事件等要素间的相互作用机理的基础上,采用面向对象方法设计了一种顾及信誉度的众源时空数据组织方法,用UML对其进行描述,分析了与信誉度相关操作及其联动关系,得出了8条联动规则。开发了顾及信誉度的众源时空数据管理原型系统,验证了所提模型的有效性。 相似文献
4.
《International Journal of Digital Earth》2013,6(8):650-670
Crowdsourcing has become a popular means to acquire data about the Earth and its environment inexpensively, but the data-sets obtained are typically imperfect and of unknown quality. Two common imperfections with crowdsourced data are the contributions from cheats or spammers and missing cases. The effect of the latter two imperfections on a method to evaluate the accuracy of crowdsourced data via a latent class model was explored. Using simulated and real data-sets, it was shown that the method is able to derive useful information on the accuracy of crowdsourced data even when the degree of imperfection was very high. The practical potential of this ability to obtain accuracy information within the geospatial sciences and the realm of Digital Earth applications was indicated with reference to an evaluation of building damage maps produced by multiple bodies after the 2010 earthquake in Haiti. Critically, the method allowed data-sets to be ranked in approximately the correct order of accuracy and this could help ensure that the most appropriate data-sets are used. 相似文献
5.
ABSTRACTMaps are explicitly positioned within the realms of power, representation, and epistemology; this article sets out to explore how these ideas are manifest in the academic Geographic Information Science (GIScience) literature. We analyze 10 years of literature (2005–2014) from top tier GIScience journals specific to the geoweb and geographic crowdsourcing. We then broaden our search to include three additional journals outside the technical GIScience journals and contrast them to the initial findings. We use this comparison to discuss the apparent technical and social divide present within the literature. Our findings demonstrate little explicit engagement with topics of social justice, marginalization, and empowerment within our subset of almost 1200 GIScience papers. The social, environmental, and political nature of participation, mapmaking, and maps necessitates greater reflection on the creation, design, and implementation of the geoweb and geographic crowdsourcing. We argue that the merging of the technical and social has already occurred in practice, and for GIScience to remain relevant for contributors and users of crowdsourced maps, researchers and practitioners must heed two decades of calls for substantial and critical engagement with the geoweb and crowdsourcing as social, environmental, and political processes. 相似文献
6.
《International Journal of Digital Earth》2013,6(5):504-520
Abstract Because the removal of topographic effects is one the most important pre-processing steps when extracting information from satellite images in digital Earth applications, the problem of differential terrain illumination on satellite imagery has been investigated for at least 20 years. As there is no superior topographic correction method applicable to all areas and all images, a comparison of topographic normalization methods in different regions and images is necessary. In this study, common topographic correction methods were applied on an ALOS AVNIR-2 image of a rugged forest area, and the results were evaluated through different criteria. The results show that the simple correction methods [Cosine, Sun-Canopy-sensor (SCS), and Minnaert correction] are inefficient in exceptionally rough forests. Among the improved correction methods (SCS+C, modified Minnaert, and pixel-based Minnaert), the best result was achieved using a pixel-based Minnaert approach in which a separate correction factor in various slope angles is used. Thus, this method should be considered for topographic correction, especially in forests with severe topography. 相似文献
7.
Soe Win Myint 《国际地球制图》2013,28(4):29-40
Abstract Attempts to analyze urban features and to classify land use and land cover directly from high‐resolution satellite data with traditional computer classification techniques have proven to be inefficient for two primary reasons. First, urban landscapes are composed of complex features. Second, traditional classifiers employ spectral information based on single pixel value and ignore a great amount of spatial information. Texture plays an important role in image segmentation and object recognition, as well as in interpretation of images in a variety of applications. This study analyzes urban texture features in multi‐spectral image data. Recent developments in the very powerful mathematical theory of wavelet transforms have received overwhelming attention by image analysts. An evaluation of the ability of wavelet transform in urban feature extraction and classification was performed in this study, with six types of urban land cover features classified. The preliminary results of this research indicate that the accuracy of texture analysis in classifying urban features in fine resolution image data could be significantly improved with the use of wavelet transform approach. 相似文献
8.
《International Journal of Digital Earth》2013,6(7):737-748
ABSTRACTSupervised image classification has been widely utilized in a variety of remote sensing applications. When large volume of satellite imagery data and aerial photos are increasingly available, high-performance image processing solutions are required to handle large scale of data. This paper introduces how maximum likelihood classification approach is parallelized for implementation on a computer cluster and a graphics processing unit to achieve high performance when processing big imagery data. The solution is scalable and satisfies the need of change detection, object identification, and exploratory analysis on large-scale high-resolution imagery data in remote sensing applications. 相似文献
9.
AbstractLand use/land cover (LULC) classification with high accuracy is necessary, especially in eco-environment research, urban planning, vegetation condition study and soil management. Over the last decade a number of classification algorithms have been developed for the analysis of remotely sensed data. The most notable algorithms are the object-oriented K-Nearest Neighbour (K-NN), Support Vector Machines (SVMs) and the Decision Trees (DTs) amongst many others. In this study, LULC types of Selangor area were analyzed on the basis of the classification results acquired using the pixel-based and object-based image analysis approaches. SPOT 5 satellite images with four spectral bands from 2003 and 2010 were used to carry out the image classification and ground truth data were collected from Google Earth and field trips. In pixel-based image analysis, a supervised classification was performed using the DT classifier. On the other hand, object-oriented (K-NN) image analysis was evaluated using standard nearest neighbour as classifier. Subsequently SVM object-based classification was performed. Five LULC categories were extracted and the results were compared between them. The overall classification accuracies for 2003 and 2010 showed that the object-oriented (K-NN) (90.5% and 91%) performed better results than the pixel-based DT (68.6% and 68.4%) and object-based SVM (80.6% and 78.15%). In general, the object-oriented (K-NN) performed better than both DTs and SVMs. The obtained LULC classification maps can be used to improve various applications such as change detection, urban design, environmental management and zooning. 相似文献
10.
11.
Abstract With the availability of high‐resolution satellite imagery featuring as high as 1 meter resolution in the panchromatic mode and 3‐meter resolution in the multispectral mode, there is an interest by many new commercial and public service applications such as cellular telephones coverage area design, urban/land cover planning, and real estate marketing to extract features from images automatically. To that end, the demand for unsupervised classification techniques is growing. In this paper, the Maximum Likelihood (ML) and Maximum A prior Probability (MAP) algorithms are used as decision rules to find boundaries of classes computed by the Iterative Self‐Organizing Data (ISOADATA) algorithm. Different satellite images with different resolutions were used to experiment with these algorithms. The results of comparing and analyzing the algorithms revealed that MAP‐ISODATA performed better than ML‐ISODATA even when the same initial matrix was used. It was shown that there was no significant difference between ML‐ISODATA and MAP‐ISODATA in terms of accuracy. It was also realized that better results could be obtained if homogenous initialization strategies were used. 相似文献
12.
针对全球导航卫星系统（global navigation satellite system,GNSS）拒止环境下大范围无人机视觉绝对定位问题,提出了一种聚合深度学习特征的卫星基准影像检索方法。首先,利用预训练的深度学习模型提取无人机与卫星基准影像的局部卷积特征;然后,对局部特征描述符进行聚合,生成影像全局表达;最后,利用影像全局特征进行相似性检索,并采用检索结果精匹配重排序的后处理方法,进一步提高检索准确率。设计了一个新的面向无人机绝对定位的卫星基准影像数据集并进行实验,结果表明,使用所提方法检索无人机影像适配区域的卫星基准影像的准确率达76.07%,可为后续基于视觉的无人机绝对定位提供参考。 相似文献
13.
《International Journal of Digital Earth》2013,6(1):88-106
Abstract Digital Earth essentially consists of 3D and moreD models and attached semantic information (attributes). Techniques for generating such models efficiently are required very urgently. Reality-based 3D modelling using images as prime data source plays an important role in this context. Images contain a wealth of information that can be advantageously used for model generation. Images are increasingly available from satellite, aerial and terrestrial platforms. This contribution briefly describes some of the problems which we encounter if the process of model generation is to be automatised. With the help of some examples from Digital Terrain Model generation, Cultural Heritage and 3D city modelling we show briefly what can be achieved. Special attention is directed towards the use of model helicopters for image data acquisition. Some problems with interactive visualisation are discussed. Also, issues surrounding R&D, professional practice and education are also addressed. 相似文献
14.
高分三号卫星全极化SAR影像九寨沟地震滑坡普查 总被引：1，自引：1，他引：0
基于光学遥感影像的区域滑坡普查易受云雾天气的影响,存在滑坡体调查不全面的问题,无法满足震后应急调查与恢复重建的需求。本文提出了一种极化SAR卫星数据滑坡普查方法,采用高分三号全极化SAR卫星影像数据,以九寨沟地震震区为实验区,在深入分析滑坡体和其他地物类型散射特征的基础上,融合极化特征、纹理特征和地形特征等多维特征信息,结合高分二号影像获取的训练样本,构建基于BP神经网络的全极化SAR数据滑坡自动识别模型,实现滑坡体的自动快速识别。与高分辨率光学影像与无人机航空影像目视解译结果相比较,总体识别精度为92.8%,Kappa系数为0.715,识别准确度满足地震应急实际应用的需求。研究成果可用于震区大区域滑坡体的普查,为后续开展无人机高分辨率影像滑坡体详查、灾后应急与景区恢复提供辅助信息支撑,并促进国产高分SAR卫星数据在防震减灾中的应用。 相似文献
15.
QuickBird satellite imagery acquired in June 2003 and September 2004 was evaluated for detecting the noxious weed spiny aster [Leucosyris spinosa (Benth.) Greene] on a south Texas, USA rangeland area. A subset of each of the satellite images representing a diversity of cover types was extracted and used as a study site. The satellite imagery had a spatial resolution of 2.8 m and contained 11-bit data. Unsupervised and supervised classification techniques were used to classify false colour composite (green, red, and near-infrared bands) images of the study site. Imagery acquired in June was superior to that obtained in September for distinguishing spiny aster infestations. This was attributed to differences in spiny aster phenology between the two dates. An unsupervised classification of the June image showed that spiny aster had producer's and user's accuracies of 90% and 93.1%, respectively, whereas a supervised classification of the June image had producer's and user's accuracies of 90% and 81.8%, respectively. These results indicate that high resolution satellite imagery coupled with image analysis techniques can be used successfully for detecting spiny aster infestations on rangelands. 相似文献
16.
通过对GF-2卫星影像正射校正及波段模拟配准误差试验,分析GF-2卫星正射校正方法的选择以及不同配准误差下对GF-2卫星影像自动分类结果的影响;最后介绍GF-2遥感影像在森林资源监测应用中的初步测试。研究结果表明:正射校正时,当校正精度要求控制在RMS2时,控制点数量选择范围在85~95间较为合理,且控制点数在90个时,RMS值最小;经有理函数模型与卫片模型比较后,卫片模型校正精度较高;以目视判读为主时,实践中建议使用三次卷积重采样法输出结果最好;波段模拟配准误差试验中,配准误差与各地类面积变化间存在显著的线性关系;对于森林面积监测时,配准误差应小于0.3个像元。此研究可为新型国产卫星数据在森林资源监测中的应用提供参考。 相似文献
17.
Street‐level images taken by vehicles and pedestrians have found a role in various companies’ location‐based intelligence services. Some platforms collect their images using their own cars and drivers, while others rely on crowdsourcing; however, to what extent can we expect crowdsourced approaches to reach the imagery coverage levels obtained by paid drivers? Is capturing every single street a useful or obtainable goal? We use online coverage maps to compare Google Street View, Mapillary, and OpenStreetCam in 24 major world cities and 25 differently sized cities in Brazil. We find that Google has often taken an all‐or‐nothing approach to collecting coverage in world cities, whereas crowdsourced platforms have achieved a more even distribution of coverage across space. Extremely low‐ and high‐income neighborhoods are sometimes omitted due to visible and invisible barriers. Coverage patterns are influenced by how and why each company procures imagery, along with other social, economic, and geographic factors. 相似文献
18.
AbstractMangrove ecosystems play a very important ecological role on land–ocean interfaces in tropical regions. These ecosystems comprise of various tree species and aquatic animals, protecting the environment and providing a habitat that supports many living organisms including humans. The identification of image regions in mangrove ecosystems plays a significant role in ecosystem monitoring and conservation. Recent studies have suggested oversegmentation of colour images using superpixels as a solution to the segmentation of image regions. This study used the SLIC superpixel algorithm and k-means clustering to segment images taken from a camera mounted on a drone from a mangrove ecosystem in Fiji. The SLIC superpixel algorithm performed well to demarcate image regions with similar colour and texture information into patches and to use k-means for the segmentation of the whole image. These results lend support to the use of superpixel algorithms for the segmentation of mangrove ecosystems. Understanding how superpixels can be used for the segmentation of drone images will assist conservation efforts in mangrove ecosystems. 相似文献
19.
AbstractHyperspectral image provides abundant spectral information for remote discrimination of subtle differences in ground covers. However, the increasing spectral dimensions, as well as the information redundancy, make the analysis and interpretation of hyperspectral images a challenge. Feature extraction is a very important step for hyperspectral image processing. Feature extraction methods aim at reducing the dimension of data, while preserving as much information as possible. Particularly, nonlinear feature extraction methods (e.g. kernel minimum noise fraction (KMNF) transformation) have been reported to benefit many applications of hyperspectral remote sensing, due to their good preservation of high-order structures of the original data. However, conventional KMNF or its extensions have some limitations on noise fraction estimation during the feature extraction, and this leads to poor performances for post-applications. This paper proposes a novel nonlinear feature extraction method for hyperspectral images. Instead of estimating noise fraction by the nearest neighborhood information (within a sliding window), the proposed method explores the use of image segmentation. The approach benefits both noise fraction estimation and information preservation, and enables a significant improvement for classification. Experimental results on two real hyperspectral images demonstrate the efficiency of the proposed method. Compared to conventional KMNF, the improvements of the method on two hyperspectral image classification are 8 and 11%. This nonlinear feature extraction method can be also applied to other disciplines where high-dimensional data analysis is required. 相似文献
20.
《地理信息系统科学与遥感》2013,50(3):321-337
The launch of the Very High Resolution (VHR) sensor satellites has paved the way for further exploitation of the capabilities of satellite stereo imaging for many applications. The objective of this paper is to evaluate the level of accuracy that can be achieved by using stereo satellite images for different applications involving significantly different types of terrain. Three mathematical models for satellite sensor modeling are used: Rational Function Model (RFM), 3D polynomial model, and 3D affine model. Three stereo pairs of image datasets are tested from different satellites for different areas: (a) Indian Remote Sensing (IRS)-1D stereo images for topographic mapping and digital terrain elevation modeling for an area in Egypt; (b) IKONOS stereo images for highway alignments extraction in Toronto, Canada; and (c) IKONOS stereo images for topographic mapping and geometric parameter extraction for highway alignments in Hong Kong, China. The accuracy was evaluated by comparing the results of the data extracted using stereo satellite images and those extracted from conventional techniques, including Global Positioning System, field measurements, and aerial photogrammetry. The accuracy of the extracted features was found to be within a pixel-level. The results of this paper should be of interest to professionals from different disciplines exploring the use and accuracy of satellite stereo images for topographic and transportation applications. 相似文献