GF-1 Image Research Articles

Automatic Ship Detection in Optical Remote Sensing Images Based on Anomaly Detection and SPP-PCANet

Automatic ship detection technology in optical remote sensing images has a wide range of applications in civilian and military fields. Among most important challenges encountered in ship detection, we focus on the following three selected ones: (a) ships with low contrast; (b) sea surface in complex situations; and (c) false alarm interference such as clouds and reefs. To overcome these challenges, this paper proposes coarse-to-fine ship detection strategies based on anomaly detection and spatial pyramid pooling pcanet (SPP-PCANet). The anomaly detection algorithm, based on the multivariate Gaussian distribution, regards a ship as an abnormal marine area, effectively extracting candidate regions of ships. Subsequently, we combine PCANet and spatial pyramid pooling to reduce the amount of false positives and improve the detection rate. Furthermore, the non-maximum suppression strategy is adopted to eliminate the overlapped frames on the same ship. To validate the effectiveness of the proposed method, GF-1 images and GF-2 images were utilized in the experiment, including the three scenarios mentioned above. Extensive experiments demonstrate that our method obtains superior performance in the case of complex sea background, and has a certain degree of robustness to external factors such as uneven illumination and low contrast on the GF-1 and GF-2 satellite image data.

Testing the Efficiency of Using High-Resolution Data From GF-1 in Land Cover Classifications

High-resolution remote sensing plays an important role in the study of subtle changes on the Earth's surface. The newly orbiting Chinese GF-1 satellites are designed to observe the Earth surface on a regional scale; however, the satellite efficiency requires further investigation. In this paper, the efficiency of using GF-1 01 satellite images to monitor a complex surface is tested by considering supplementary information and different land cover classification methods. Our work revealed that the GF-1 satellite observations can efficiently detect land cover fragments. When the support vector machine method is applied, the overall classification accuracy based on multisource data reaches 90.5%. The “salt and pepper phenomenon” is effectively reduced in classification images. These results also indicate that the accuracy of the GF-1 image classification is superior to the results when using the same method with the Landsat 8 and Sentinel-2A images, with the overall classification accuracy increasing by 23.6% and 13.6%. Our study suggests that GF-1 satellite observations are suitable for land cover studies on complex land surfaces. This approach can benefit various related fields such as land resource surveys, ecological assessments, environmental evaluations, and so forth.

Remote sensing interpretation of important ore-controlling geological units in Hongshan Region of Gansu Province using GF-1 image and its application

Remote sensing interpretation of important ore-controlling geological units in Hongshan Region of Gansu Province using GF-1 image and its application

太湖沿岸水体高分一号影像的邻近效应校正

太湖沿岸水体高分一号影像的邻近效应校正

Mapping regional cropping patterns by using GF-1 WFV sensor data

The successful launched Gaofen satellite no. 1 wide field-of-view (GF-1 WFV) camera is characterized by its high spatial resolution and may provide some potential for regional crop mapping. This study, taking the Bei'an City, Northeast China as the study area, aims to investigate the potential of GF-1 WFV images for crop identification and explore how to fully use its spectral, textural and temporal information to improve classification accuracy. In doing so, an object-based and Random Forest (RF) algorithm was used for crop mapping. The results showed that classification based on an optimized single temporal GF-1 image can achieve an overall accuracy of about 83%, and the addition of textural features can improve the accuracy by 8.14%. Moreover, the multi-temporal GF-1 data can produce a classification map of crops with an overall accuracy of 93.08% and the introduction of textural variables into multi-temporal GF-1 data can only increase the accuracy by about 1%, which suggests the importance of temporal information of GF-1 for crop mapping in comparison with single temporal data. By comparing classification results of GF-1 data with different feature inputs, it is concluded that GF-1 WFV data in general can meet the mapping efficiency and accuracy requirements of regional crop. But given the unique spectral characteristics of the GF-1 WFV imagery, the use of textual and temporal information is needed to yield a satisfactory accuracy.

林地资源变化对森林生态系统服务功能的影响——以南水北调核心水源地淅川县为例

PDF HTML阅读 XML下载 导出引用 引用提醒 林地资源变化对森林生态系统服务功能的影响——以南水北调核心水源地淅川县为例 DOI: 10.5846/stxb201605170954 作者: 作者单位: 作者简介: 通讯作者: 中图分类号: 基金项目: 国务院南水北调工程建设委员会办公室2015年技术咨询委托项目 Effects of forest resource changes on ecosystem function: a case study of Xichuan County, the main source of water for south-to-north water transfer in China Author: Affiliation: Fund Project: 摘要 | 图/表 | 访问统计 | 参考文献 | 相似文献 | 引证文献 | 资源附件 | 文章评论 摘要:森林生态系统是人类生存与发展的基础，其服务功能不可替代。以南水北调中线工程渠首所在地淅川县为研究区，使用2004年TM、2009年TM、2014年GF1 号影像等数据，在PIC、Arcgis10.0等软件支持下，分析其2004-2014年的林地资源变化，并利用InVEST模型对森林生态系统服务功能（水源涵养、水质净化和土壤保持）进行定量评估。结果表明：①2004-2014年县域林地资源以有林地为主，面积增长迅速，灌木林地和苗圃地面积增长缓慢，疏林地和未成林造林地面积均呈现先增后减趋势；②伴随林地资源变化，森林生态系统服务功能产生相应显著变化，10年间县域水源涵养量功能减少19%，森林水质净化功能提高29%，土壤保持功能增加6%；③同一森林类型，其生态服务功能在不同年际之间的差异表现为平均水源涵养功能逐年下降，平均水质净化能力不断提升，平均土壤保持能力先增后减；④对比5种森林类型的生态服务功能，有林地的服务功能最强，其次为灌木林地和疏林地；⑤10年间县域森林生态系统的水源涵养、水质净化和土壤保持服务功能的高低与森林覆被的高低程度呈正相关，呈现出北高南低的空间分布格局；⑥科学管理森林生态系统服务的关键在于合理配置林地与其他用地的分布格局，提高林地与其它用地镶嵌构成的复合土地利用的可持续性。同时加强服务功能重要区域的保护，避免对对服务功能较差区域的破坏。此外，未来森林经营需要从单纯的森林面积扩张，转变为提高森林质量和生产力，从而加强森林生态系统对气候变化影响的适应能力。 Abstract:Because forest ecosystems and the services they provide cannot be replaced, the main purpose of forest maintenance and management is to protect forests, as a basic resource for human survival and development. As a case study, the present study investigated Xichuan County, which is the main source of water for the middle route of the south-to-north water diversion project, by quantitatively analyzing changes in forest resources from 2004 to 2014, using TM and GF1 image data from 2004-2009 and 2014, respectively. On the basis of previous analyses, the InVEST model was used to quantitatively evaluate the ecosystem function of the forest (water conservation, water purification, and soil conservation). The results indicated that the area of forest increased rapidly, by 10.85% from 2004 to 2009 and by 7.44% from 2009 to 2014, which resulted in a forest area of 45.65% by 2014. From 2004 to 2014, the closed forest land of the county increased as well, whereas the area of shrubland and Nursery woodland increased more slowly, and the area of sparse woodland and non-wooded land both tended to increase and then decline in succession. As the forest resources changed, significant changes were also observed in the corresponding ecosystem functions, including 10-year water purification, which increased by 29%; water conservation, which increased by 19%; and soil conservation, which increased by 6%. Meanwhile, among the individual forest types, the average water conservation function decreased annually, whereas the average water purification capacity continuously improved, and the average soil holding capacity initially increased and subsequently decreased. Forest was the main type of landscape cover in the region, as well as the main contributor to total ecosystem function, followed by shrubland and sparse forest. During the study period, areas that contributed to the county's water conservation, water purification, and soil conservation services were strongly and positively correlated with forest area, and both improvement and expansion of forested areas enhanced the ecological services provided. In addition, the spatial distribution of the forest's ecosystem function was greater in the north than in the south. Analysis of the history and current condition of forest ecosystem management in the study area indicated that the key managing forest ecosystem service lies in maintaining an appropriate distribution of forestland and other land types, and the ecological function of the forests was affected by both forest area and structure (e.g., crown density, soil thickness, soil, root depth), as well as by meteorological factors. In order to improve forest quality and productivity, future forest management strategies need to promote the expansion of pure forestland and transformation and implement changes that will improve the ability of the forest ecosystem to adapt to climate change. 参考文献 相似文献 引证文献

Construction of ratio build-up index for GF-1 image

Construction of ratio build-up index for GF-1 image

Applicability of the water information extraction method based on GF-1 image

Applicability of the water information extraction method based on GF-1 image