Object-oriented Image Analysis Method Research Articles

Quantification of Loess Landforms from Three-Dimensional Landscape Pattern Perspective by Using DEMs

Quantitative analysis of the differences and the exploration of the evolution models of different loess landform types are greatly important to the in-depth understanding of the evolution process and mechanism of the loess landforms. In this research, several typical loess landform areas in the Chinese Loess Plateau were selected, and the object-oriented image analysis (OBIA) method was employed to identify the basic loess landform types. Three-dimensional (3D) landscape pattern indices were introduced on this foundation to measure the morphological and structural features of individual loess landform objects in more detail. Compared with the traditional two-dimensional (2D) landscape pattern indices, the indices consider the topographic features, thereby providing more vertical topographic information. Furthermore, the evolution modes between different loess landform types were discussed. Results show that the OBIA method achieved satisfying classification results with an overall accuracy of 88.12%. There are evident differences in quantitative morphological indicators among loess landform types, especially in indicators such as total length of edge, mean patch size, landscape shape index, and edge dimension index. Meanwhile, significant differences are also found in the combination of loess landform types corresponding to different landform development stages. The degree of surface erosion became increasingly significant as loess landforms developed, loess tableland area rapidly reduced or even vanished, and the dominant loess landform types changed to loess ridge and loess hill. Hence, in the reconstruction and management of the Loess Plateau, the loess tableland should be the key protected loess landform type. These preliminary results are helpful to further understand the development process of loess landforms and provide a certain reference for regional soil and water conservation.

Depth Semantic Segmentation of Tobacco Planting Areas from Unmanned Aerial Vehicle Remote Sensing Images in Plateau Mountains

The tobacco in plateau mountains has the characteristics of fragmented planting, uneven growth, and mixed/interplanting of crops. It is difficult to extract effective features using an object-oriented image analysis method to accurately extract tobacco planting areas. To this end, the advantage of deep learning features self-learning is relied on in this paper. An accurate extraction method of tobacco planting areas based on a deep semantic segmentation model from the unmanned aerial vehicle (UAV) remote sensing images in plateau mountains is proposed in this paper. Firstly, the tobacco semantic segmentation dataset is established using Labelme. Four deep semantic segmentation models of DeeplabV3+, PSPNet, SegNet, and U-Net are used to train the sample data in the dataset. Among them, in order to reduce the model training time, the MobileNet series of lightweight networks are used to replace the original backbone networks of the four network models. Finally, the predictive images are semantically segmented by trained networks, and the mean Intersection over Union (mIoU) is used to evaluate the accuracy. The experimental results show that, using DeeplabV3+, PSPNet, SegNet, and U-Net to perform semantic segmentation on 71 scene prediction images, the mIoU obtained is 0.9436, 0.9118, 0.9392, and 0.9473, respectively, and the accuracy of semantic segmentation is high. The feasibility of the deep semantic segmentation method for extracting tobacco planting surface from UAV remote sensing images has been verified, and the research method can provide a reference for subsequent automatic extraction of tobacco planting areas.

Pattern identification and analysis for the traditional village using low altitude UAV-borne remote sensing: multifeatured geospatial data to support rural landscape investigation, documentation and management

• Low-altitude multispectral UAV imagery provides an effective way for landscape investigation at multiple spatial scales. • High resolution and multispectral data captures multiple features of landscapes to facilitate the refined landscape detection. • Object oriented image analysis with heritage landscape structure regulation to achieve hierarchical targeted landscape classification. • Quantitative analysis to unveil the structure and spatial pattern of the landscapes in the traditional village; Spatial pattern of landscapes is viewed as the fabric and structure of traditional village. Accurate detection and analysis for the landscapes pattern plays key role in understanding the sociocultural milieu and human-natural relations. Current methods perceive their problems. Pedestrian survey is labor and time consuming. Meanwhile, the derived data tend to be subjective, qualitative and monotonous, which can hardly be used for further analysis. Remote sensing technique has been successfully applied in the field of heritage protection for its ability in object detection. But these methods are limited by visiting circle, spatial resolution and data richness. Therefore, the scientific methods of landscape pattern detection, documentation and analysis for the traditional village has long been under discussion. By taking Baojiatun castle village as a case study, the present paper aims to detect and analyze spatial pattern of traditional village by the geospatial data from a low altitude UAV-borne remote sensing. A four-leveled hierarchical landscape recognition scheme and the corresponding landscape category regulation were established. Based on the derived data and the established scheme, a three-level classification model was construct by using Object-Oriented Image Analysis method (OBIA) method and machine learning classifiers (Random Forest classifier and SVM classifier). The model was proven to be accurate and stable by ten-fold cross validation, and five major heritage landscape elements of the village were finally extracted. Furthermore, spatial pattern characteristics and distribution differences of targeted landscapes were unveiled based on distance statistics and clustering analysis. Lastly, further discussion is fostered, which focuses on the usefulness of remote sensing technique in the field of heritage landscape investigation, documentation and management.

Extraction of road blockage information for the Jiuzhaigou earthquake based on a convolution neural network and very-high-resolution satellite images

Road blockage information extraction from a single-phase postdisaster image is difficult because roads are narrow and easily covered by vegetation. The traditional object-oriented image analysis method is restrictive, and its detection is slow. A deep learning algorithm, i.e., the convolution neural network (CNN), is applied to rapidly extract road blockage information. An algorithm for sample generation is designed to construct a typical sample library for CNN training, and an appropriate CNN structure and a complete detection process are designed to extract road blockage information. Finally, by taking the Jiuzhaigou earthquake on August 8, 2017, as an example, experimental verification is carried out. The kappa coefficient and the F1 score of the results are 77.60% and 87.95%, respectively. The extraction of road blockages can be completed with an efficiency of 14.59 km2 per hour. The requirements for disaster emergency monitoring can be met by the accuracy and efficiency of this method, which are better than those of the traditional object-oriented method.

Stratified Object-Oriented Image Classification Based on Remote Sensing Image Scene Division

The traditional remote sensing image segmentation method uses the same set of parameters for the entire image. However, due to objects’ scale-dependent nature, the optimal segmentation parameters for an overall image may not be suitable for all objects. According to the idea of spatial dependence, the same kind of objects, which have the similar spatial scale, often gather in the same scene and form a scene. Based on this scenario, this paper proposes a stratified object-oriented image analysis method based on remote sensing image scene division. This method firstly uses middle semantic which can reflect an image’s visual complexity to classify the remote sensing image into different scenes, and then within each scene, an improved grid search algorithm is employed to optimize the segmentation result of each scene, so that the optimal scale can be utmostly adopted for each scene. Because the complexity of data is effectively reduced by stratified processing, local scale optimization ensures the overall classification accuracy of the whole image, which is practically meaningful for remote sensing geo-application.

Object-oriented aquatic vegetation extracting approach based on visible vegetation indices.

Using the estimation of scale parameters (ESP) image segmentation tool to determine the ideal image segmentation scale, the optimal segmented image was created by the multi-scale segmentation method. Based on the visible vegetation indices derived from mini-UAV imaging data, we chose a set of optimal vegetation indices from a series of visible vegetation indices, and built up a decision tree rule. A membership function was used to automatically classify the study area and an aquatic vegetation map was generated. The results showed the overall accuracy of image classification using the supervised classification was 53.7%, and the overall accuracy of object-oriented image analysis (OBIA) was 91.7%. Compared with pixel-based supervised classification method, the OBIA method improved significantly the image classification result and further increased the accuracy of extracting the aquatic vegetation. The Kappa value of supervised classification was 0.4, and the Kappa value based OBIA was 0.9. The experimental results demonstrated that using visible vegetation indices derived from the mini-UAV data and OBIA method extracting the aquatic vegetation developed in this study was feasible and could be applied in other physically similar areas.

Object Oriented Image Analysis in Remote Sensing of Forest and Vineyard Areas

The study of vegetation cover, forests, orchards or vineyards and crops through satellite techniques is increasingly promoted as a result of facilities they offer. A number of methods and techniques for processing and analysis of satellite images are developed to increase the precision of the working, given the diversity of vegetation structure analysis and expected results. This study aimed to analyze the capabilities of object-oriented image analysis (OBIA) for recognition forest and vineyard areas. OBIA is automated process of object extraction by modelling of human visual system for image interpretation. The basis for classification process is object, which is created according to the set of characteristics. In object-oriented approach classification description is based on classification rules including spectral characteristics, size, shape, as well as content and texture information. Analysis is done on multispectral imagery of high and very high spatial resolution. Represented results show the usefulness of RapidEye and WorldView2 images as well as importance of classification based on OBIA. Object-oriented image analysis (OBIA) method based on satellite imagery has facilitated the recognition forest and vineyard areas with high accuracy.

Extraction Method for Earthquake-Collapsed Building Information Based on High-Resolution Remote Sensing

At present, the extraction of earthquake disaster information from remote sensing data relies on visual interpretation. However, this technique cannot effectively and quickly obtain precise and efficient information for earthquake relief and emergency management. Collapsed buildings in the town of Zipingpu after the Wenchuan earthquake were used as a case study to validate two kinds of rapid extraction methods for earthquake-collapsed building information based on pixel-oriented and object-oriented theories. The pixel-oriented method is based on multi-layer regional segments that embody the core layers and segments of the object-oriented method. The key idea is to mask layer by layer all image information, including that on the collapsed buildings. Compared with traditional techniques, the pixel-oriented method is innovative because it allows considerably rapid computer processing. As for the object-oriented method, a multi-scale segment algorithm was applied to build a three-layer hierarchy. By analyzing the spectrum, texture, shape, location, and context of individual object classes in different layers, the fuzzy determined rule system was established for the extraction of earthquake-collapsed building information. We compared the two sets of results using three variables: precision assessment, visual effect, and principle. Both methods can extract earthquake-collapsed building information quickly and accurately. The object-oriented method successfully overcomes the pepper salt noise caused by the spectral diversity of high-resolution remote sensing data and solves the problem of same object, different spectrums and that of same spectrum, different objects. With an overall accuracy of 90.38%, the method achieves more scientific and accurate results compared with the pixel-oriented method (76.84%). The object-oriented image analysis method can be extensively applied in the extraction of earthquake disaster information based on high-resolution remote sensing.

Study on Remote Sensing Image Auto-Identify Classification by Used of Object-Oriented Technology

In dealing with high-resolution remote sensing image auto-identify classification, the traditional pixel-based and spectral statistical characteristics classification technology or method has some insurmountable difficulties. In this paper, object-oriented image analysis method is by application, the auto-identify classification rules are set up based the different remote sensing image characteristics that included such as spectral, texture, scale and so on. As a case study, a petroleum reserve base auto-identify classification is selected as an example and the target is identified, in a better effective result by applications of the object-oriented method. The result appraising analysis indicates that object-oriented classification method to identify automatically high-resolution remote sensing images pattern object can get a high precision. The method of object-oriented has a widely potential application for remote sensing image automatic-identify classification in times to come.

Transferability of Object-Oriented Image Analysis Methods for Slum Identification

Updated spatial information on the dynamics of slums can be helpful to measure and evaluate progress of policies. Earlier studies have shown that semi-automatic detection of slums using remote sensing can be challenging considering the large variability in definition and appearance. In this study, we explored the potential of an object-oriented image analysis (OOA) method to detect slums, using very high resolution (VHR) imagery. This method integrated expert knowledge in the form of a local slum ontology. A set of image-based parameters was identified that was used for differentiating slums from non-slum areas in an OOA environment. The method was implemented on three subsets of the city of Ahmedabad, India. Results show that textural features such as entropy and contrast derived from a grey level co-occurrence matrix (GLCM) and the size of image segments are stable parameters for classification of built-up areas and the identification of slums. Relation with classified slum objects, in terms of enclosed by slums and relative border with slums was used to refine classification. The analysis on three different subsets showed final accuracies ranging from 47% to 68%. We conclude that our method produces useful results as it allows including location specific adaptation, whereas generically applicable rulesets for slums are still to be developed.

Extraction Method of Tree Crown Using High-Resolution Satellite Image

Crown is a key part of tree. It's the main place that photosynthesis has been taken place. It's also the important energy sources that tree need to grow. So, some researchers often study how to monitor growth of tree, predict trees' life increment and judge the quality of wood, and so on by using remote sensing technique. The appearance of commercial high-resolution satellite data supplies new resources for people to study crown structure of a tree by using remote sensing technique. In this paper, method to detecting tree crown by using QuickBird image that covers the demonstration has been studied. Base on image process, Object-Oriented image analysis method has been taken. The tree crown has been effectively extracted from the QuickBird image by using Fuzzy Classification method that bases on samples. At the same time, it can give some experiment to process high spatial resolution satellite image and make a strong base for promoting the application of high-resolution satellite image in forestry and entironment construction of our country.