The amount of scientific literature on (Geographic) Object-based Image Analysis – GEOBIA has been and still is sharply increasing. These approaches to analysing imagery have antecedents in earlier research on image segmentation and use GIS-like spatial analysis within classification and feature extraction approaches. This article investigates these development and its implications and asks whether or not this is a new paradigm in remote sensing and Geographic Information Science (GIScience). We first discuss several limitations of prevailing per-pixel methods when applied to high resolution images. Then we explore the paradigm concept developed by Kuhn (1962) and discuss whether GEOBIA can be regarded as a paradigm according to this definition. We crystallize core concepts of GEOBIA, including the role of objects, of ontologies and the multiplicity of scales and we discuss how these conceptual developments support important methods in remote sensing such as change detection and accuracy assessment. The ramifications of the different theoretical foundations between the ‘per-pixel paradigm’ and GEOBIA are analysed, as are some of the challenges along this path from pixels, to objects, to geo-intelligence. Based on several paradigm indications as defined by Kuhn and based on an analysis of peer-reviewed scientific literature we conclude that GEOBIA is a new and evolving paradigm.

There is a growing demand for detailed and accurate landslide maps and inventories around the globe, but particularly in hazard-prone regions such as the Himalayas. Most standard mapping methods require expert knowledge, supervision and fieldwork. In this study, we use optical data from the Rapid Eye satellite and topographic factors to analyze the potential of machine learning methods, i.e., artificial neural network (ANN), support vector machines (SVM) and random forest (RF), and different deep-learning convolution neural networks (CNNs) for landslide detection. We use two training zones and one test zone to independently evaluate the performance of different methods in the highly landslide-prone Rasuwa district in Nepal. Twenty different maps are created using ANN, SVM and RF and different CNN instantiations and are compared against the results of extensive fieldwork through a mean intersection-over-union (mIOU) and other common metrics. This accuracy assessment yields the best result of 78.26% mIOU for a small window size CNN, which uses spectral information only. The additional information from a 5 m digital elevation model helps to discriminate between human settlements and landslides but does not improve the overall classification accuracy. CNNs do not automatically outperform ANN, SVM and RF, although this is sometimes claimed. Rather, the performance of CNNs strongly depends on their design, i.e., layer depth, input window sizes and training strategies. Here, we conclude that the CNN method is still in its infancy as most researchers will either use predefined parameters in solutions like Google TensorFlow or will apply different settings in a trial-and-error manner. Nevertheless, deep-learning can improve landslide mapping in the future if the effects of the different designs are better understood, enough training samples exist, and the effects of augmentation strategies to artificially increase the number of existing samples are better understood.

The spatial resolution of imaging sensors has increased dramatically in recent years, and so too have the challenges associated with extracting meaningful information from their data products. Object-based image analysis (OBIA) is gaining rapid popularity in remote sensing science as a means of bridging very high spatial resolution (VHSR) imagery and GIS. Multiscalar image segmentation is a fundamental step in OBIA, yet there is currently no tool available to objectively guide the selection of appropriate scales for segmentation. We present a technique for estimating the scale parameter in image segmentation of remotely sensed data with Definiens DeveloperÒ. The degree of heterogeneity within an image-object is controlled by a subjective measure called the 'scale parameter', as implemented in the mentioned software. We propose a tool, called estimation of scale parameter (ESP), that builds on the idea of local variance (LV) of object heterogeneity within a scene. The ESP tool iteratively generates image-objects at multiple scale levels in a bottom-up approach and calculates the LV for each scale. Variation in heterogeneity is explored by evaluating LV plotted against the corresponding scale. The thresholds in rates of change of LV (ROC-LV) indicate the scale levels at which the image can be segmented in the most appropriate manner, relative to the data properties at the scene level. Our tests on different types of imagery indicated fast processing times and accurate results. The simple yet robust ESP tool enables fast and objective parametrization when performing image segmentation and holds great potential for OBIA applications.

We introduce a new automated approach to parameterising multi-scale image segmentation of multiple layers, and we implemented it as a generic tool for the eCognition® software. This approach relies on the potential of the local variance (LV) to detect scale transitions in geospatial data. The tool detects the number of layers added to a project and segments them iteratively with a multiresolution segmentation algorithm in a bottom-up approach, where the scale factor in the segmentation, namely, the scale parameter (SP), increases with a constant increment. The average LV value of the objects in all of the layers is computed and serves as a condition for stopping the iterations: when a scale level records an LV value that is equal to or lower than the previous value, the iteration ends, and the objects segmented in the previous level are retained. Three orders of magnitude of SP lags produce a corresponding number of scale levels. Tests on very high resolution imagery provided satisfactory results for generic applicability. The tool has a significant potential for enabling objectivity and automation of GEOBIA analysis.

Abstract: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.