Several machine-learning algorithms have been proposed for remote sensing image classification during the past two decades. Among these machine learning algorithms, Random Forest (RF) and Support Vector Machines (SVM) have drawn attention to image classification in several remote sensing applications. This article reviews RF and SVM concepts relevant to remote sensing image classification and applies a meta-analysis of 251 peer-reviewed journal papers. A database with more than 40 quantitative and qualitative fields was constructed from these reviewed papers. The meta-analysis mainly focuses on 1) the analysis regarding the general characteristics of the studies, such as geographical distribution, frequency of the papers considering time, journals, application domains, and remote sensing software packages used in the case studies, and 2) a comparative analysis regarding the performances of RF and SVM classification against various parameters, such as data type, RS applications, spatial resolution, and the number of extracted features in the feature engineering step. The challenges, recommendations, and potential directions for future research are also discussed in detail. Moreover, a summary of the results is provided to aid researchers to customize their efforts in order to achieve the most accurate results based on their thematic applications.

/pdf/support-vector-machine-versus-random-forest-for-remote-2imvn9our6.pdf

Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review

Cloud detection is an important preprocessing step for the precise application of optical satellite imagery. In this paper, we propose a deep learning based cloud detection method named multi-scale convolutional feature fusion (MSCFF) for remote sensing images of different sensors. In the network architecture of MSCFF, the symmetric encoder-decoder module, which provides both local and global context by densifying feature maps with trainable convolutional filter banks, is utilized to extract multi-scale and high-level spatial features. The feature maps of multiple scales are then up-sampled and concatenated, and a novel multi-scale feature fusion module is designed to fuse the features of different scales for the output. The two output feature maps of the network are cloud and cloud shadow maps, which are in turn fed to binary classifiers outside the model to obtain the final cloud and cloud shadow mask. The MSCFF method was validated on hundreds of globally distributed optical satellite images, with spatial resolutions ranging from 0.5 to 50 m, including Landsat-5/7/8, Gaofen-1/2/4, Sentinel-2, Ziyuan-3, CBERS-04, Huanjing-1, and collected high-resolution images exported from Google Earth. The experimental results show that MSCFF achieves a higher accuracy than the traditional rule-based cloud detection methods and the state-of-the-art deep learning models, especially in bright surface covered areas. The effectiveness of MSCFF means that it has great promise for the practical application of cloud detection for multiple types of medium and high-resolution remote sensing images. Our established global high-resolution cloud detection validation dataset has been made available online ( http://sendimage.whu.edu.cn/en/mscff/ ).

Deep learning based cloud detection for medium and high resolution remote sensing images of different sensors

We present xBD, a new, large-scale dataset for the advancement of change detection and building damage assessment for humanitarian assistance and disaster recovery research. Natural disaster response requires an accurate understanding of damaged buildings in an affected region. Current response strategies require in-person damage assessments within 24-48 hours of a disaster. Massive potential exists for using aerial imagery combined with computer vision algorithms to assess damage and reduce the potential danger to human life. In collaboration with multiple disaster response agencies, xBD provides pre- and post-event satellite imagery across a variety of disaster events with building polygons, ordinal labels of damage level, and corresponding satellite metadata. Furthermore, the dataset contains bounding boxes and labels for environmental factors such as fire, water, and smoke. xBD is the largest building damage assessment dataset to date, containing 850,736 building annotations across 45,362 km\textsuperscript{2} of imagery.

xBD: A Dataset for Assessing Building Damage from Satellite Imagery

Mapping forest types and tree species at regional scales to provide information for ecologists and forest managers is a new challenge for the remote sensing community. Here, we assess the potential of a U‐net convolutional network, a recent deep learning algorithm, to identify and segment (1) natural forests and eucalyptus plantations, and (2) an indicator of forest disturbance, the tree species Cecropia hololeuca, in very high resolution images (0.3 m) from the WorldView‐3 satellite in the Brazilian Atlantic rainforest region. The networks for forest types and Cecropia trees were trained with 7611 and 1568 red‐green‐blue (RGB) images, respectively, and their dense labeled masks. Eighty per cent of the images were used for training and 20% for validation. The U‐net network segmented forest types with an overall accuracy >95% and an intersection over union (IoU) of 0.96. For C. hololeuca, the overall accuracy was 97% and the IoU was 0.86. The predictions were produced over a 1600 km2 region using WorldView‐3 RGB bands pan‐sharpened at 0.3 m. Natural and eucalyptus forests compose 79 and 21% of the region's total forest cover (82 250 ha). Cecropia crowns covered 1% of the natural forest canopy. An index to describe the level of disturbance of the natural forest fragments based on the spatial distribution of Cecropia trees was developed. Our work demonstrates how a deep learning algorithm can support applications such as vegetation, tree species distributions and disturbance mapping on a regional scale.

Using the U-net convolutional network to map forest types and disturbance in the Atlantic rainforest with very high resolution images

Multi-sensor cloud and cloud shadow segmentation with a convolutional neural network

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.

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

In accordance with the characteristics of urban high-resolution color remote sensing images, we put forward an object-oriented shadow detection and removal method. In this method, shadow features are taken into consideration during image segmentation, and then, according to the statistical features of the images, suspected shadows are extracted. Furthermore, some dark objects which could be mistaken for shadows are ruled out according to object properties and spatial relationship between objects. For shadow removal, inner–outer outline profile line (IOOPL) matching is used. First, the IOOPLs are obtained with respect to the boundary lines of shadows. Shadow removal is then performed according to the homogeneous sections attained through IOOPL similarity matching. Experiments show that the new method can accurately detect shadows from urban high-resolution remote sensing images and can effectively restore shadows with a rate of over 85%.

Object-Oriented Shadow Detection and Removal From Urban High-Resolution Remote Sensing Images

A large number of publications have incorporated deep learning in the process of remote sensing change detection. In these Deep Learning Change Detection (DLCD) publications, deep learning methods have demonstrated their superiority over conventional change detection methods. However, the theoretical underpinnings of why deep learning improves the performance of change detection remain unresolved. As of today, few in-depth reviews have investigated the mechanisms of DLCD. Without such a review, five critical questions remain unclear. Does DLCD provide improved information representation for change detection? If so, how? How to select an appropriate DLCD method and why? How much does each type of change benefits from DLCD in terms of its performance? What are the major limitations of existing DLCD methods and what are the prospects for DLCD? To address these five questions, we reviewed according to the following strategies. We grouped the DLCD information assemblages into the four unique dimensions of remote sensing: spectral, spatial, temporal, and multi-sensor. For the extraction of information in each dimension, the difference between DLCD and conventional change detection methods was compared. We proposed a taxonomy of existing DLCD methods by dividing them into two distinctive pools: separate and coupled models. Their advantages, limitations, applicability, and performance were thoroughly investigated and explicitly presented. We examined the variations in performance between DLCD and conventional change detection. We depicted two limitations of DLCD, i.e. training sample and hardware and software dilemmas. Based on these analyses, we identified directions for future developments. As a result of our review, we found that DLCD’s advantages over conventional change detection can be attributed to three factors: improved information representation; improved change detection methods; and performance enhancements. DLCD has to surpass the limitations with regard to training samples and computing infrastructure. We envision this review can boost developments of deep learning in change detection applications. 

Deep learning for change detection in remote sensing: a review

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.

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

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 articl...

Wenzhuo Li

Papers

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

Object-Oriented Shadow Detection and Removal From Urban High-Resolution Remote Sensing Images

Deep learning for change detection in remote sensing: a review

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

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