Yi F.,CAS Wuhan Institute of Geodesy and Geophysics |
Yi F.,Key Laboratory for Environment and Disaster Monitoring and Evaluation of Hubei Province |
Yi F.,University of Chinese Academy of Sciences |
Li R.,CAS Wuhan Institute of Geodesy and Geophysics |
And 7 more authors.
Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering | Year: 2015
Identification of paddy fields in the hilly regions is important for policy making of food self-sufficiency in China. However, extracting image information using current image analysis techniques is difficult because of the unique terrain of hilly regions. The traditional pixel-based analysis of remotely sensed data is usually affected by pixel heterogeneity, mixed pixels, and spectral similarity, thus leading to the inaccurate identification of paddy fields in hilly regions. This study aimed to find other methods for accurate paddy field identification in hilly regions. The study area was Xiangtan City located in the mid-east of Hunan province, a good representative of hilly regions. In Xiangtan city, the land use change markedly increases with rapid economic development, leading to gradual decline of cultivated land. The Chinese environment and disaster mitigation satellite (i.e., HJ-1A/1B) image of the region was data source for land use map. The HJ-1A star was equipped with a charge-coupled device (CCD) camera and a hyperspectral imager, whereas the HJ-1B star was equipped with CCD and infrared (IR) cameras. The satellite observes the ground in widths of 700 km with a ground pixel resolution of 30 m by four multispectral imaging steps. The object-oriented image analysis technique is a new type of automatic technique under a computer environment. The information carrier used was multi-scale objects composed of multiple adjacent pixels containing rich semantic information. Image segmentation is an important classification step because high-precision remote sensing (RS) image classification depends on good segmentation. The multi-scale image segmentation algorithm was applied in the preliminary object extraction to fully interpret the RS images with the different spectral features, shape, and textural features of real ground targets. The configuration of multi-scale segmentation thresholds directly affected the integrity of features extracted from RS images. In this study, the cultivated and uncultivated lands were segmented with the scale of 40; then the cultivated land was further segmented under the scale of 30 and 20, respectively. By comparing and analyzing the segmentation results on the two scales, the optimal scales for the extraction of paddy fields in different regions were configured selectively. The phenomenon of different objects with the same spectral characteristics and same object showing different spectral characteristics may occur in the classification of RS images. The two phenomena pose challenges for RS image interpretation. In order to identify the information related with paddy field distribution in hilly regions, the key point is the RS identification between paddy field, dry field, forest and grassland. According to the classification features, k-nearest neighbor (KNN) classifier and decision tree classifier were employed to interpret the RS images of paddy field in hilly regions. The KNN classifier was improved by dividing the training samples into three sets. The result of the improved KNN classifier was better than that of traditional methods. The precision of the improved KNN classifier was 74.6%. However, the total precision and Kappa coefficient of the decision tree classifier were higher than the KNN classifier. The total identification precision of the former reached 90.25%, with commission error rate of 4.12%, omission error rate of 5.63%, and Kappa coefficient of 0.79. A comparison of the results of the two classifiers showed that the decision tree classifier is more suitable for paddy field identification based on object-oriented analysis in hilly regions. ©, 2015, Chinese Society of Agricultural Engineering. All right reserved. Source
Luo K.,CAS Wuhan Institute of Geodesy and Geophysics |
Luo K.,University of Chinese Academy of Sciences |
Luo K.,Key Laboratory for Environment and Disaster Monitoring and Evaluation of Hubei Province |
Li R.,CAS Wuhan Institute of Geodesy and Geophysics |
And 7 more authors.
Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering | Year: 2013
The rapid development of RS, GIS, and GPS technology provide a fast and effective means for the dynamic monitoring of land-cover change detection. Many scholars have researched constructing a land-cover change dynamic database with various remote sensing imageries. In conclusion, the main sources to date are abroad remote sensing imagery, while the Chinese HJ-CCD imageries rarely are used in cover-wetlands information extraction. More important, the traditional pixel-based methods which have been universally applied in land-cover/land-use information extraction for many years cannot meet the application need of land-cover/land-use information extraction because it only uses the spectral features of imagery, ignoring other information that the remote sensing imagery carries. The object-oriented technology not only uses spectral features, but also makes full use of texture features?spatial features, spatial relationship, color space, and the band ration of remote sensing imagery. Based on the data of HJ-CCD imagery in 2010, ETM imagery in 2005, and TM imagery in 2000, integrated into RS, GIS, and GPS technology, an object-oriented method was applied to the remote sensing image classification of land-cover/land-use in Hubei province. First, we achieved land-cover/land-use results as the basal map of a database using object-oriented technology in Hubei province in the e-Cognition software. After checking and improving the results, the Similarity Vectors Change Detection Approach was used to compare with the spectral difference the corresponding objects by segmentation from 2000 to 2005, and from 2005 to 2010.We needed to classify the changed area of two change periods, so the Nearest Neighbor Classification Approach belonging to object-oriented technology was applied to extract land-cover/land-use information. This process in the research contained two key steps: choosing samples and optimizing feature space. Optimizing feature space allowed us to get perfect feature extracting object information. All the results in the unchanged area in 2010 were transformed into the sample Nearest Neighbor Classification Approach needed. We used so many samples that the computer could determine the regulation of every class by detailed analysis. Fusing the classification results in the change area and the unchanged area, the land-cover/land-use results all over Hubei province can be completed successfully according to the districts now. We constructed the land-cover change database in Hubei province in the end. The classification accuracy was assessed using error matrixes though wild samples which were obtained from experimental area by GPS. The research showed that, compared with the traditional classification methods, which only consider the spectral characteristics of the targets, an object-oriented international carbon budget certification classification system comprehensively utilizes more detailed information of the remote sensing imagery including spectral characteristics, texture feature, spatial relationship, color space, and band ratio. Thus, it yields a higher accuracy of classification. The object-oriented method extracted the so-called "object, " which consists of some homogeneous pixels in the process of classification, and the objects showed a low degree of fragmentation. Therefore, this method significantly reduced the disturbance of salt-and-pepper noise in the classification results and can keep the similarity in shape with the natural objects. The research showed that this process and method using RS, GIS, GPS, object-oriented technology based on TM, ETM and Chinese HJ-CCD imagery for monitoring land-cover change information is fast, efficient, high automation, and accurate. However, we found that object-oriented technology has some disadvantages where landscape fragmentation is high. Source