scholarly journals Unsupervised Segmentation Evaluation Using Area-Weighted Variance and Jeffries-Matusita Distance for Remote Sensing Images

2018 ◽  
Vol 10 (8) ◽  
pp. 1193 ◽  
Author(s):  
Yongji Wang ◽  
Qingwen Qi ◽  
Ying Liu
Keyword(s):  
Distance Measures ◽  
Unsupervised Segmentation ◽  
Segmentation Evaluation ◽  
Object Based Image Analysis ◽  
Object Based ◽  
Segmentation Methods ◽  
Segmentation Quality ◽  
Two Measures ◽  
Multiresolution Segmentation ◽  
Adjacent Segments

Image segmentation is an important process and a prerequisite for object-based image analysis. Thus, evaluating the performance of segmentation algorithms is essential to identify effective segmentation methods and to optimize the scale. In this paper, we propose an unsupervised evaluation (UE) method using the area-weighted variance (WV) and Jeffries-Matusita (JM) distance to compare two image partitions to evaluate segmentation quality. The two measures were calculated based on the local measure criteria, and the JM distance was improved by considering the contribution of the common border between adjacent segments and the area of each segment in the JM distance formula, which makes the heterogeneity measure more effective and objective. Then the two measures were presented as a curve when changing the scale from 8 to 20, which can reflect the segmentation quality in both over- and under-segmentation. Furthermore, the WV and JM distance measures were combined by using three different strategies. The effectiveness of the combined indicators was illustrated through supervised evaluation (SE) methods to clearly reveal the segmentation quality and capture the trade-off between the two measures. In these experiments, the multiresolution segmentation (MRS) method was adopted for evaluation. The proposed UE method was compared with two existing UE methods to further confirm their capabilities. The visual and quantitative SE results demonstrated that the proposed UE method can improve the segmentation quality.

scholarly journals Mask R-CNN and OBIA Fusion Improves the Segmentation of Scattered Vegetation in Very High-Resolution Optical Sensors

Sensors ◽  
2021 ◽  
Vol 21 (1) ◽  
pp. 320
Author(s):  
Emilio Guirado ◽  
Javier Blanco-Sacristán ◽  
Emilio Rodríguez-Caballero ◽  
Siham Tabik ◽  
Domingo Alcaraz-Segura ◽  
...  
Keyword(s):  
High Resolution ◽  
Optical Sensors ◽  
Biotic Interactions ◽  
Relevant Information ◽  
Vegetation Monitoring ◽  
Object Based Image Analysis ◽  
Object Based ◽  
Segmentation Methods ◽  
High Resolution Images ◽  
Very High

Vegetation generally appears scattered in drylands. Its structure, composition and spatial patterns are key controls of biotic interactions, water, and nutrient cycles. Applying segmentation methods to very high-resolution images for monitoring changes in vegetation cover can provide relevant information for dryland conservation ecology. For this reason, improving segmentation methods and understanding the effect of spatial resolution on segmentation results is key to improve dryland vegetation monitoring. We explored and analyzed the accuracy of Object-Based Image Analysis (OBIA) and Mask Region-based Convolutional Neural Networks (Mask R-CNN) and the fusion of both methods in the segmentation of scattered vegetation in a dryland ecosystem. As a case study, we mapped Ziziphus lotus, the dominant shrub of a habitat of conservation priority in one of the driest areas of Europe. Our results show for the first time that the fusion of the results from OBIA and Mask R-CNN increases the accuracy of the segmentation of scattered shrubs up to 25% compared to both methods separately. Hence, by fusing OBIA and Mask R-CNNs on very high-resolution images, the improved segmentation accuracy of vegetation mapping would lead to more precise and sensitive monitoring of changes in biodiversity and ecosystem services in drylands.

scholarly journals A Fast and Effective Method for Unsupervised Segmentation Evaluation of Remote Sensing Images

2020 ◽  
Vol 12 (18) ◽  
pp. 3005
Author(s):  
Maofan Zhao ◽  
Qingyan Meng ◽  
Linlin Zhang ◽  
Die Hu ◽  
Ying Zhang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Computational Cost ◽  
Visual Interpretation ◽  
Remote Sensing Images ◽  
Unsupervised Segmentation ◽  
Segmentation Evaluation ◽  
Parameters Selection ◽  
Object Based ◽  
Geographic Object ◽  
The Difference

The segmentation of remote sensing images with high spatial resolution is important and fundamental in geographic object-based image analysis (GEOBIA), so evaluating segmentation results without prior knowledge is an essential part in segmentation algorithms comparison, segmentation parameters selection, and optimization. In this study, we proposed a fast and effective unsupervised evaluation (UE) method using the area-weighted variance (WV) as intra-segment homogeneity and the difference to neighbor pixels (DTNP) as inter-segment heterogeneity. Then these two measures were combined into a fast-global score (FGS) to evaluate the segmentation. The effectiveness of DTNP and FGS was demonstrated by visual interpretation as qualitative analysis and supervised evaluation (SE) as quantitative analysis. For this experiment, the ‘‘Multi-resolution Segmentation’’ algorithm in eCognition was adopted in the segmentation and four typical study areas of GF-2 images were used as test data. The effectiveness analysis of DTNP shows that it can keep stability and remain sensitive to both over-segmentation and under-segmentation compared to two existing inter-segment heterogeneity measures. The effectiveness and computational cost analysis of FGS compared with two existing UE methods revealed that FGS can effectively evaluate segmentation results with the lowest computational cost.

scholarly journals PEMETAAN ZONA GEOMORFOLOGI DAN HABITAT BENTIK DI PULAU KOTOK BESAR MENGGUNAKAN KLASIFIKASI BERBASIS OBJEK

2018 ◽  
Vol 8 (2) ◽  
pp. 209-219
Author(s):  
Ike Dori Candra ◽  
Vicentius P. Siregar ◽  
Syamsul B. Agus
Keyword(s):  
Image Analysis ◽  
Reef Flat ◽  
Reef Slope ◽  
Reef Crest ◽  
Object Based Image Analysis ◽  
Object Based ◽  
Level 3 ◽  
Level 1 ◽  
Multiresolution Segmentation ◽  
Level 2

Penelitian ini menggunakan citra satelit resolusi tinggi worldview-2 akuisisi 5 Oktober 2013. Tujuan dari penelitian ini adalah untuk mengkaji kemampuan citra satelit resolusi tinggi worldview-2 dalam memetakan zona geomorfologi dan habitat bentik perairan dangkal di Pulau Kotok Besar. Metode yang digunakan adalah metode klasifikasi Object Based Image Analysis (OBIA). Metode ini mampu mendefinisikan kelas-kelas objek berdasarkan aspek spektral dan spasial. Segmentasi citra menggunakan algoritma multiresolution segmentation dengan parameter skala yang berbeda untuk setiap level, baik level 1, level 2 dan level 3. Shape dan compactness juga disesuaikan untuk setiap level. Penentuan kelas pada level 1 menghasilkan tiga kelas yaitu daratan, perairan dangkal dan perairan dalam. Penentuan kelas pada level 2 untuk zona geomorfologi menghasilkan tiga kelas yaitu reef flat, reef crest dan reef slope. Klasifikasi habitat bentik pada level 3 menghasilkan 7 kelas dengan akurasi keseluruhan yaitu 66.40 %.

scholarly journals ASSESSMENT OF MULTIRESOLUTION SEGMENTATION FOR EXTRACTING GREENHOUSES FROM WORLDVIEW-2 IMAGERY

2016 ◽  
Vol XLI-B7 ◽  
pp. 145-152 ◽  
Author(s):  
M. A. Aguilar ◽  
F. J. Aguilar ◽  
A. García Lorca ◽  
E. Guirado ◽  
M. Betlej ◽  
...  
Keyword(s):  
Image Objects ◽  
Object Based Image Analysis ◽  
Local Variance ◽  
Sensing Applications ◽  
Object Based ◽  
Optimum Scale ◽  
Values Assessment ◽  
Segmentation Approach ◽  
Optimal Setting ◽  
Multiresolution Segmentation

The latest breed of very high resolution (VHR) commercial satellites opens new possibilities for cartographic and remote sensing applications. In this way, object based image analysis (OBIA) approach has been proved as the best option when working with VHR satellite imagery. OBIA considers spectral, geometric, textural and topological attributes associated with meaningful image objects. Thus, the first step of OBIA, referred to as segmentation, is to delineate objects of interest. Determination of an optimal segmentation is crucial for a good performance of the second stage in OBIA, the classification process. The main goal of this work is to assess the multiresolution segmentation algorithm provided by eCognition software for delineating greenhouses from WorldView- 2 multispectral orthoimages. Specifically, the focus is on finding the optimal parameters of the multiresolution segmentation approach (i.e., Scale, Shape and Compactness) for plastic greenhouses. The optimum Scale parameter estimation was based on the idea of local variance of object heterogeneity within a scene (ESP2 tool). Moreover, different segmentation results were attained by using different combinations of Shape and Compactness values. Assessment of segmentation quality based on the discrepancy between reference polygons and corresponding image segments was carried out to identify the optimal setting of multiresolution segmentation parameters. Three discrepancy indices were used: Potential Segmentation Error (PSE), Number-of-Segments Ratio (NSR) and Euclidean Distance 2 (ED2).

scholarly journals ASSESSMENT OF MULTIRESOLUTION SEGMENTATION FOR EXTRACTING GREENHOUSES FROM WORLDVIEW-2 IMAGERY

2016 ◽  
Vol XLI-B7 ◽  
pp. 145-152 ◽  
Author(s):  
M. A. Aguilar ◽  
F. J. Aguilar ◽  
A. García Lorca ◽  
E. Guirado ◽  
M. Betlej ◽  
...  
Keyword(s):  
Image Objects ◽  
Object Based Image Analysis ◽  
Local Variance ◽  
Sensing Applications ◽  
Object Based ◽  
Optimum Scale ◽  
Values Assessment ◽  
Segmentation Approach ◽  
Optimal Setting ◽  
Multiresolution Segmentation

The latest breed of very high resolution (VHR) commercial satellites opens new possibilities for cartographic and remote sensing applications. In this way, object based image analysis (OBIA) approach has been proved as the best option when working with VHR satellite imagery. OBIA considers spectral, geometric, textural and topological attributes associated with meaningful image objects. Thus, the first step of OBIA, referred to as segmentation, is to delineate objects of interest. Determination of an optimal segmentation is crucial for a good performance of the second stage in OBIA, the classification process. The main goal of this work is to assess the multiresolution segmentation algorithm provided by eCognition software for delineating greenhouses from WorldView- 2 multispectral orthoimages. Specifically, the focus is on finding the optimal parameters of the multiresolution segmentation approach (i.e., Scale, Shape and Compactness) for plastic greenhouses. The optimum Scale parameter estimation was based on the idea of local variance of object heterogeneity within a scene (ESP2 tool). Moreover, different segmentation results were attained by using different combinations of Shape and Compactness values. Assessment of segmentation quality based on the discrepancy between reference polygons and corresponding image segments was carried out to identify the optimal setting of multiresolution segmentation parameters. Three discrepancy indices were used: Potential Segmentation Error (PSE), Number-of-Segments Ratio (NSR) and Euclidean Distance 2 (ED2).

scholarly journals LANDSLIDE EXTRACTION FROM SENTINEL-2 IMAGE IN SIWALIK OF SURKHET DISTRICT, NEPAL

2019 ◽  
Vol IV-5/W2 ◽  
pp. 9-15
Author(s):  
P. B. Budha ◽  
A. Bhardwaj
Keyword(s):  
Satellite Images ◽  
Threshold Value ◽  
Threshold Values ◽  
Geometrical Properties ◽  
Image Objects ◽  
Object Based Image Analysis ◽  
Loss And Damage ◽  
Object Based ◽  
Multiresolution Segmentation ◽  
Sentinel 2

Abstract. Locating landslides and determining its extent is deemed an important task in estimating loss and damage and carry out mitigation works. As landslides are recurring phenomena in the research site, Siwalik Hills of western Nepal, freely available Sentinel-2 satellite images were considered to delineate landslides. The method employed in this process was Object-Based Image Analysis carried out in eCognition software using multiresolution segmentation algorithm. Parameters taken for segmentation were a scale of 20, the shape of 0.3, and compactness of 0.5. When a threshold value of < 0.35 in NDVI was used to distinguish landslides from image objects, some non-landslide objects were also selected. These false positives were removed successively using the threshold values on different bands, band ratios, slope information, hillshade and geometrical properties of image objects. There were altogether 264 landslides detected in the study area with size ranging from 300 m2 to 1675 m2 and landslide density of approximately 2 per km2. The accuracy, when compared to reference inventory, showed correctness and completeness measuring 80.28% and 66.27% respectively. These results showed semi-automatic landslide extraction was successful and Sentinel-2 can be used for similar tasks in other areas of Siwalik.

scholarly journals AN UNSUPERVISED SEGMENTATION METHOD FOR REMOTE SENSING IMAGERY BASED ON CONDITIONAL RANDOM FIELDS

2020 ◽  
Vol XLII-3/W12-2020 ◽  
pp. 91-95
Author(s):  
A. R. Soares ◽  
T. S. Körting ◽  
L. M. G. Fonseca ◽  
A. K. Neves
Keyword(s):  
Remote Sensing ◽  
Random Fields ◽  
Conditional Random Fields ◽  
Fundamental Problem ◽  
Unsupervised Classification ◽  
Unsupervised Segmentation ◽  
Object Based Image Analysis ◽  
Object Based ◽  
Geographic Object ◽  
Common Operation

Abstract. Segmentation is a fundamental problem in image processing and a common operation in Remote Sensing, which has been widely used especially in Geographic Object-Based Image Analysis (GEOBIA). In this paper, we propose a new unsupervised segmentation algorithm based on the Conditional Random Fields (CRF) theory. The method relies on two levels of information: (1) that comes from an unsupervised classification with Fuzzy C-Means algorithm; (2) the 8-connected neighbourhood of a pixel. The algorithm was tested on a WorldView-2 multispectral image, with 2 m of spatial resolution. Results were evaluated using 6 quality measures, and their performance was compared with other image segmentation algorithms that are usually applied by the Remote Sensing community. Results indicate that the proposed algorithm achieved superior overall performance when compared others, despite some over-segmentation.

scholarly journals UAS photogrammetry and object-based image analysis (GEOBIA): erosion monitoring at the Kazár badland, Hungary

2016 ◽  
Vol 10 (3-4) ◽  
pp. 169-178 ◽  
Author(s):  
László Bertalan ◽  
Zoltán Túri ◽  
Gergely Szabó
Keyword(s):  
Image Analysis ◽  
Manual Control ◽  
Surface Model ◽  
Digital Surface Model ◽  
Rill Erosion ◽  
Segmentation Method ◽  
Object Based Image Analysis ◽  
Erosion Processes ◽  
Object Based ◽  
Multiresolution Segmentation

A remarkable badland valley is situated near Kazár, NE-Hungary, where rhyolite tuff outcrops as greyishwhite cliffs and white barren patches. The landform is shaped by gully and rill erosion processes. Weperformed a preliminary state UAS survey and created a digital surface model and ortophotograph. Theflight was operated with manual control in order to perform a more optimal coverage of the aerial images.The overhanging forests induced overexposed photographs due to the higher contrast with the baretuff surface. The multiresolution segmentation method allowed us to classify the ortophotograph andseparate the tuff surface and the vegetation. The applied methods and final datasets in combination withthe subsequent surveys will be used for detecting the recent erosional processes of the Kazár badland

scholarly journals Identifikasi Kawasan Pertambangan Timah Menggunakan Data Satelit Sentinel – 1 dengan Metode Object Based Image Analysis (OBIA)

2019 ◽  
Vol 17 (1) ◽  
pp. 140
Author(s):  
Udhi C Nugroho ◽  
Dony Kushardono ◽  
Esthi K Dewi
Keyword(s):  
Image Analysis ◽  
Nearest Neighbor ◽  
European Space Agency ◽  
Grey Level ◽  
Object Based Image Analysis ◽  
Space Agency ◽  
Object Based ◽  
Multiresolution Segmentation

Berdasarkan data Pendapatan Nasional Indonesia 2017, sektor pertambangan  dan penggalian mempunyai peran penting bagi Indonesia. Sektor ini menyumbangkan 7,57% pada produk domestik bruto Indonesia di tahun 2017 . Salah satu sektor pertambangan yang potensial di Indonesia adalah pertambangan mineral Timah di Pulau Bangka dan Belitung. Namun kegiatan pertambangan ini banyak menimbulkan dampak negatif dari sisi lingkungan. Salah satu upaya awal untuk menanggulangi dampak negatif terhadap lingkungan adalah melakukan identifikasi kawasan pertambangan timah secara spasial. Teknologi yang dapat membantu untuk hal ini salah satunya adalah teknologi penginderaan jauh radar. Penelitian ini menggunakan data satelit radar sentinel-1 yang diluncurkan oleh European Space Agency (ESA). Tujuan penelitian ini adalah pemanfaatan data radar Sentinel-1 untuk identifikasi kawasan pertambangan menggunakan metode Object-Base Image Analysis (OBIA). Data sentinel-1 disegmentasi menggunakan algorithma multiresolution segmentation kemudian di klasifikasi menggunakan algorithma nearest neighbor. Masukan data yang digunakan untuk proses klasifikasi dibuat menjadi dua variasi, yang pertama adalah data standar deviasi, mean, dan brightness pada masing – masing segmen di tiap band, kemudian variasi kedua adalah penambahan data tekstur berupa nilai grey level coocurance matrix (GLCM). Hasil klasifikasi menunjukan bahwa masukan data yang menggunakan data tekstur GLCM mempunyai akurasi lebih tinggi dibandingkan dengan yang tanpa data tekstur GLCM. Secara statisktik Hasil klasifikasi dengan type satu menunjukan bahwa total akurasi nya adalah sebesar 89,0 %, dengan nilai kappa sebesar 0,48 sedangkan untuk type dua menunjukan bahwa total akurasinya adalah 89,3%, dengan kappa sebesar 0,50. Hasil klasifikasi kawasan pertambangan dapat digunakan sebagai masukan awal dalam rangka identifikasi spasial kerusakan lingkungan akibat aktivitas pertambangan.

scholarly journals Aerial Image Segmentation with Clustering Using Fireworks Algorithm

2019 ◽  
Vol 4 (1) ◽  
pp. 19
Author(s):  
Muhammad Hariz Arasy ◽  
Suyanto Suyanto ◽  
Kurniawan Nur Ramadhani
Keyword(s):  
Image Segmentation ◽  
Aerial Images ◽  
Aerial Image ◽  
Segmentation Method ◽  
Unsupervised Segmentation ◽  
Local Optima ◽  
Fireworks Algorithm ◽  
Segmentation Methods ◽  
Segmentation Quality ◽  
Unsupervised Image Segmentation

Aerial images has different data characteristics when compared to other types of images. An aerial image usually contains small insignificant objects that can cause errors in the unsupervised segmentation method. K-means clustering, one of the widely used unsupervised image segmentation methods, is highly vulnerable to local optima. In this study, Adaptive Fireworks Algorithm (AFWA) is proposed as an alternative to the K-means algorithm in optimizing the clustering process in the cluster-based segmentation method. AFWA is then applied to perform aerial image segmentation and the results are compared with K-means. Based on the comparison using Probabilistic Rand Index (PRI) and Variation of Information (VI) evaluation metrics, AFWA produces an overall better segmentation quality.

Sign in / Sign up

Export Citation Format

Share Document