The increased feature space available in object-based classification environments (e.g., extended spectral feature sets per object, shape properties, or textural features) has a high potential of improving classifications. However, the availability of a large number of derived features per segmented object can also lead to a time-consuming and subjective process of optimizing the feature subset. The objectives of this study are to evaluate the effect of the advanced feature selection methods of popular supervised classifiers (Support Vector Machines (SVM) and Random Forest (RF)) for the example of object-based mapping of an agricultural area using Unmanned Aerial Vehicle (UAV) imagery, in order to optimize their usage for object-based agriculture pattern recognition tasks. In this study, several advanced feature selection methods were divided into both types of classifiers (SVM and RF) to conduct further evaluations using five feature-importance-evaluation methods and three feature-subset-evaluation methods. A visualization method was used to measure the change pattern of mean classification accuracy with the increase of features used, and a two-tailed t-test was used to determine the difference between two population means for both repeated ten classification accuracies. This study mainly contribute to the uncertainty analysis of feature selection for object-based classification instead of the per-pixel method. The results highlight that the RF classifier is relatively insensitive to the number of input features, even for a small training set size, whereby a negative impact of feature set size on the classification accuracy of the SVM classifier was observed. Overall, the SVM Recursive Feature Elimination (SVM-RFE) seems to be an appropriate method for both groups of classifiers, while the Correlation-based Feature Selection (CFS) is the best feature-subset-evaluation method. Most importantly, this study verified that feature selection for both classifiers is crucial for the evolving field of Object-based Image Analysis (OBIA): It is highly advisable for feature selection to be performed before object-based classification, even though an adverse impact could sometimes be observed from the wrapper methods.

The Urban Agglomeration in Yangtze River Delta is one of the most important economic and industrial regions in China. The City of Changzhou is one of the most important industrial citys in Yangtze River Delta Urban Agglomeration. Activities here include groundwater exploration. Groundwater overexploitation has contributed to the major land deformation in this city. The severity and magnitude of land deformation over time were investigated in Changzhou City. A Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) technology, provides a useful tool in measuring urban land deformation. In this study, a time series of COSMO-SkyMed and Sentinel-1A SAR images covering Changzhou City were acquired. SBAS-InSAR imaging technique was used to survey the extent and severity of land deformation associated with the exploitation of groundwater in Changzhou City. Leveling data was used to validate the SBAR-InSAR productions, the error of SBAR-InSAR annual subsidence results was within 2 mm. The results showed that three main land subsidence zones were detected at Xinbei, Tianning and Wujin District. Four subsidence points were selected to analyze the temporal and spatial evolution characteristics of land subsidence. The subsidence rate of P1 to P4 was −2.48 mm/year, −12.78 mm/year, −18.09 mm/year, and −12.69 mm/year respectively. Land subsidence over Changzhou showed a trend of slowing down from 2011 to 2017, especially in Wujin District. SBAR-InSAR derived land deformation that correlates with the water level change in six groundwater stations. Indicated that with groundwater rebound, the land rebound obviously, and the maximum rebound vale reached 9.13 mm.