Kaimin Sun

Cloud Detection for High-Resolution Satellite Imagery Using Machine Learning and Multi-Feature Fusion

The accurate location of clouds in images is prerequisite for many high-resolution satellite imagery applications such as atmospheric correction, land cover classifications, and target recognition. Thus, we propose a novel approach for cloud detection using machine learning and multi-feature fusion based on a comparative analysis of typical spectral, textural, and other feature differences between clouds and backgrounds. To validate this method, we tested it on 102 Gao Fen-1(GF-1) and Gao Fen-2(GF-2) satellite images. The overall accuracy of our multi-feature fusion method for cloud detection was more than 91.45%, and the Kappa coefficient for all the tested images was greater than 80%. The producer and user accuracy were also higher at 93.67% and 95.67%, respectively; both of these values were higher than the values for the other tested feature fusion methods. Our results show that this novel multi-feature approach yields better accuracy than other feature fusion methods. In post-processing, we applied an object-oriented method to remove the influence of highly reflective ground objects and further improved the accuracy. Compared to traditional methods, our new method for cloud detection is accurate, exhibits good scalability, and produces consistent results when mapping clouds of different types and sizes over various land surfaces that contain natural vegetation, agriculture land, built-up areas, and water bodies.

An object-oriented daytime land-fog-detection approach based on the mean-shift and full lambda-schedule algorithms using EOS/MODIS data

A new algorithm is presented for land-fog detection using daytime imagery from the Earth Observing System (EOS) Moderate Resolution Imaging Spectroradiometer (MODIS) data. MODIS images constitute an ideal data source for fog detection due to their outstanding spatial and spectral resolution. In this article, a parameter named the Normalized Difference Fog Index (NDFI) is proposed, based on analysing the spectral character of fog and cloud by utilizing the Streamer radiative-transfer model and MODIS data. A mean-shift segmentation method is used to preliminary segment the NDFI image, and a full lambda-schedule algorithm is then iteratively applied to merge adjacent segments based on the combination of spectral and spatial information. Then, some properties (e.g. mean value of brightness temperature) are calculated for each segment, and each object is identified as either fog or not. The algorithms performance is evaluated against ground-based measurements over China in winter, and the algorithm is proved to be effective in detecting fog accurately based on three cases.

Detecting building façade damage from oblique aerial images using local symmetry feature and the Gini Index

ABSTRACT The Classification of damaged building types is currently a relevant topic in disaster assessment and management, and the detection of damaged building facades is important to improve the classification accuracy. In this letter, a novel approach for automatic detection of damaged facade based on local symmetry features and the Gini Index using oblique aerial images is presented. First, local symmetry points are detected in a sliding window. Then, we obtain histogram bins of local symmetrical points in the vertical and horizontal directions. Finally, damaged and undamaged of building facades are distinguished using Gini Index. An evaluation of experimental result, for a selected Beichuan earthquake ruins study site, in Sichuan, China, shows that this method is feasible and effective for the detection of damaged facades.

A New Approach to Performing Bundle Adjustment for Time Series UAV Images 3D Building Change Detection

Successful change detection in multi-temporal images relies on high spatial co-registration accuracy. However, co-registration accuracy alone cannot meet the needs of change detection when using several ground control points to separately geo-reference multi-temporal images from unmanned aerial vehicles (UAVs). This letter reports on a new approach to perform bundle adjustment—named united bundle adjustment (UBA)—to solve this co-registration problem for change detection in multi-temporal UAV images. In UBA, multi-temporal UAV images are matched with each other to construct a unified tie point net. One single bundle adjustment process is performed on the unified tie point net, placing every image into the same coordinate system and thus automatically accomplishing spatial co-registration. We then perform change detection using both orthophotos and three-dimensional height information derived from dense image matching techniques. Experimental results show that UBA co-registration accuracy is higher than the accuracy of commonly-used approaches for multi-temporal UAV images. Our proposed preprocessing method extends the capacities of consumer-level UAVs so they can eventually meet the growing need for automatic building change detection and dynamic monitoring using only RGB band images.

Radiometric Cross-Calibration of GF-4 PMS Sensor Based on Assimilation of Landsat-8 OLI Images

Earth observation data obtained from remote sensors must undergo radiometric calibration before use in quantitative applications. However, the large view angles of the panchromatic multispectral sensor (PMS) aboard the GF-4 satellite pose challenges for cross-calibration due to the effects of atmospheric radiation transfer and the bidirectional reflectance distribution function (BRDF). To address this problem, this paper introduces a novel cross-calibration method based on data assimilation considering cross-calibration as an optimal approximation problem. The GF-4 PMS was cross-calibrated with the well-calibrated Landsat-8 Operational Land Imager (OLI) as the reference sensor. In order to correct unequal bidirectional reflection effects, an adjustment factor for the BRDF was established, making complex models unnecessary. The proposed method employed the Shuffled Complex Evolution-University of Arizona (SCE-UA) algorithm to find the optimal calibration coefficients and BRDF adjustment factor through an iterative process. The validation results revealed a surface reflectance error of <5% for the new cross-calibration coefficients. The accuracy of calibration coefficients were significantly improved when compared to the officially published coefficients as well as those derived using conventional methods. The uncertainty produced by the proposed method was less than 7%, meeting the demands for future quantitative applications and research. This method is also applicable to other sensors with large view angles.

Detection of Damaged Rooftop Areas From High-Resolution Aerial Images Based on Visual Bag-of-Words Model

The classification of damaged building types has received increasing attention in recent years. The detection of damaged rooftop areas is crucial to improve the accuracy of classification of building damaged types. In this letter, an approach for the automatic detection of damaged rooftops areas based on the visual bag-of-words (BoWs) model is presented. First, the building rooftop is segmented into different superpixel areas. Then, the visual BoWs model is employed to build semantic feature vectors for damaged or nondamaged parts of each superpixel area. Finally, damaged and nondamaged parts of rooftop superpixel areas are discriminated using support vector machine. An evaluation of experimental results, for a selected study site of the Beichuan earthquake ruins, Sichuan, China, shows that this method is feasible and effective for the detection of damaged rooftop areas.

A Novel Change Detection Approach for Multi-Temporal High-Resolution Remote Sensing Images Based on Rotation Forest and Coarse-to-Fine Uncertainty Analyses

In the process of object-based change detection (OBCD), scale is a significant factor related to extraction and analyses of subsequent change data. To address this problem, this paper describes an object-based approach to urban area change detection (CD) using rotation forest (RoF) and coarse-to-fine uncertainty analyses of multi-temporal high-resolution remote sensing images. First, highly homogeneous objects with consistent spatial positions are identified through vector-raster integration and multi-scale fine segmentation. The multi-temporal images are stacked and segmented under the constraints of a historical land use vector map using a series of optimal segmentation scales, ranging from coarse to fine. Second, neighborhood correlation image analyses are performed to highlight pixels with high probabilities of being changed or unchanged, which can be used as a prerequisite for object-based analyses. Third, based on the coarse-to-fine segmentation and pixel-based pre-classification results, change possibilities are calculated for various objects. Furthermore, changed and unchanged objects identified at different scales are automatically selected to serve as training samples. The spectral and texture features of each object are extracted. Finally, uncertain objects are classified using the RoF classifier. Multi-scale classification results are combined using a majority voting rule to generate the final CD results. In experiments using two pairs of real high-resolution remote sensing datasets, our proposed approach outperformed existing methods in terms of CD accuracy, verifying its feasibility and effectiveness. (Less)

Comparison of four machine learning methods for object-oriented change detection in high-resolution satellite imagery

High resolution image change detection is one of the key technologies of remote sensing application, which is of great significance for resource survey, environmental monitoring, fine agriculture, military mapping and battlefield environment detection. In this paper, for high-resolution satellite imagery, Random Forest (RF), Support Vector Machine (SVM), Deep belief network (DBN), and Adaboost models were established to verify the possibility of different machine learning applications in change detection. In order to compare detection accuracy of four machine learning Method, we applied these four machine learning methods for two high-resolution images. The results shows that SVM has higher overall accuracy at small samples compared to RF, Adaboost, and DBN for binary and from-to change detection. With the increase in the number of samples, RF has higher overall accuracy compared to Adaboost, SVM and DBN.

A novel change detection approach based on visual saliency and random forest from multi-temporal high-resolution remote-sensing images

ABSTRACT This article presents a novel change detection (CD) approach for high-resolution remote-sensing images, which incorporates visual saliency and random forest (RF). First, highly homogeneous and compact image super-pixels are generated using super-pixel segmentation, and the optimal segmentation result is obtained through image superimposition and principal component analysis. Second, saliency detection is used to guide the search of interest regions in the initial difference image obtained via the improved robust change vector analysis algorithm. The salient regions within the difference image that correspond to the binarized saliency map are extracted, and the regions are subject to the fuzzy c-means (FCM) clustering to obtain the pixel-level pre-classification result, which can be used as a prerequisite for super-pixel-based analysis. Third, on the basis of the optimal segmentation and pixel-level pre-classification results, different super-pixel change possibilities are calculated. Furthermore, the changed and unchanged super-pixels that serve as the training samples are automatically selected. The spectral features and Gabor features of each super-pixel are extracted. Finally, super-pixel-based CD is implemented by applying RF based on these samples. Experimental results on Quickbird, Ziyuan 3 (ZY3), and Gaofen 2 (GF2) multi-spectral images show that the proposed method outperforms the compared methods in the accuracy of CD, and also confirm the feasibility and effectiveness of the proposed approach.

Multi-scale hierarchical sampling change detection using Random Forest for high-resolution satellite imagery

ABSTRACT High-resolution imagery provides rich information useful for land-use and land-cover change detection; however, methods to exploit these data lag behind data collection technologies. In this article, we propose a novel object-oriented multi-scale hierarchical sampling (MSHS) change detection method for high-resolution satellite imagery. In our method, MSHS is carried out to automatically obtain multi-scale training samples and different sample combinations. The training sample spectra, texture, and shape features are fused to build feature space after MSHS. Sample combinations and corresponding feature spaces are input into Random Forest (RF) to train multiple change classifiers. An optimal RF change detection classifier is selected when the out-of-bag error parameter in RF is at the minimum. In order to validate the proposed method, we applied it to high-resolution satellite image data and compared the detection results from our method and the single-scale sampling change detection method. These experimental results show that false alarm rates and missed detection of changed objects using our method were lower than the single-scale sampling change detection method. To demonstrate the scalability of the algorithm, different change detection methods were applied to three study sites. Experimental results show that our method delivered high overall accuracy and F1-scores. Compared to traditional methods, our method makes full use of the multi-scale characteristics of ground objects. Our approach does not extend multi-scale feature vectors directly, but instead automatically increases the amount of the training samples at multiple scales, without increasing the volume of manual processing, thus improving the ability of the algorithm to generalize features from the RF model, making it more robust.