Appraisal of kappa-based metrics and disagreement indices of accuracy assessment for parametric and nonparametric techniques used in LULC classification and change detection

2020 ◽  
Vol 6 (2) ◽  
pp. 1045-1059 ◽  
Author(s):  
Pramit Verma ◽  
Aditya Raghubanshi ◽  
Prashant K. Srivastava ◽  
A. S. Raghubanshi
Keyword(s):  
Change Detection ◽  
Accuracy Assessment ◽  
Nonparametric Techniques

scholarly journals Change Detection in Coral Reef Environment Using High-Resolution Images: Comparison of Object-Based and Pixel-Based Paradigms

2018 ◽  
Vol 7 (11) ◽  
pp. 441 ◽  
Author(s):  
Zhenjin Zhou ◽  
Lei Ma ◽  
Tengyu Fu ◽  
Ge Zhang ◽  
Mengru Yao ◽  
...  
Keyword(s):  
Coral Reef ◽  
Change Detection ◽  
Accuracy Assessment ◽  
Detection Accuracy ◽  
Reef Environment ◽  
Object Based ◽  
Coral Reef Environment ◽  
Study Sites ◽  
Object Area ◽  
Segmentation Image

Despite increases in the spatial resolution of satellite imagery prompting interest in object-based image analysis, few studies have used object-based methods for monitoring changes in coral reefs. This study proposes a high accuracy object-based change detection (OBCD) method intended for coral reef environment, which uses QuickBird and WorldView-2 images. The proposed methodological framework includes image fusion, multi-temporal image segmentation, image differencing, random forests models, and object-area-based accuracy assessment. For validation, we applied the method to images of four coral reef study sites in the South China Sea. We compared the proposed OBCD method with a conventional pixel-based change detection (PBCD) method by implementing both methods under the same conditions. The average overall accuracy of OBCD exceeded 90%, which was approximately 20% higher than PBCD. The OBCD method was free from salt-and-pepper effects and was less prone to images misregistration in terms of change detection accuracy and mapping results. The object-area-based accuracy assessment reached a higher overall accuracy and per-class accuracy than the object-number-based and pixel-number-based accuracy assessment.

scholarly journals COMPARISON OF PIXEL-BASED AND OBJECT-ORIENTED LAND COVER CHANGE DETECTION METHODS

2016 ◽  
Vol XLI-B7 ◽  
pp. 579-583
Author(s):  
Zhenlei Xie ◽  
Ruoming Shi ◽  
Ling Zhu ◽  
Shu Peng ◽  
Xu Chen
Keyword(s):  
Land Cover ◽  
Change Detection ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Detection Method ◽  
Accuracy Assessment ◽  
Object Oriented ◽  
Detection Methods ◽  
Commission Error ◽  
Time Saving

Change detection method is an efficient way in the aim of land cover product updating on the basis of the existing products, and at the same time saving lots of cost and time. Considering the object-oriented change detection method for 30m resolution Landsat image, analysis of effect of different segmentation scales on the method of the object-oriented is firstly carried out. On the other hand, for analysing the effectiveness and availability of pixel-based change method, the two indices which complement each other are the differenced Normalized Difference Vegetation Index (dNDVI), the Change Vector (CV) were used. To demonstrate the performance of pixel-based and object-oriented, accuracy assessment of these two change detection results will be conducted by four indicators which include overall accuracy, omission error, commission error and Kappa coefficient.

scholarly journals Change detection analysis of reservoirs and lakes in Multi-Temporal Landsat-7 (ETM+) data over the Indian sub-continent during 2008-2018

2018 ◽  
Vol 7 (4.6) ◽  
pp. 122
Author(s):  
B. Chandrababu Naik ◽  
Prof. B. Anuradha ◽  
. .
Keyword(s):  
Land Cover ◽  
Change Detection ◽  
Accuracy Assessment ◽  
Kappa Statistics ◽  
Detection Techniques ◽  
Change Detection Analysis ◽  
Detection Analysis ◽  
Landsat 7 ◽  
Multi Temporal ◽  
Lakes And Reservoirs

Remote sensing change detection techniques are extensively used in numerous applications such as land cover monitoring, disaster monitoring, and urban sprawl. The main motive of this paper study the change detection analysis of Land Use / Land Cover (LULC) in different lakes and Reservoirs, such as Chilika Lake, Pulicat Lake, Vembanad Lake, Penna Reservoir, and Nagarjuna Sagar Reservoir located in the Indian subcontinent region.  The analyses and changes are evaluated during period of 2008 - 2018 in multi-temporal Landsat-7 (ETM+) data. The major disadvantage in Landsat-7 for data acquired from satellite sensor, is that it includes strips (gaps) in an image. On May 31, 2003 the Scan-Line-Corrector (SLC) failed completely, due to 22% of pixel information lost in the Landsat-7 data. The focal analysis method is applied to the required image for removing all strips (gaps). Change detection using Image Differencing technique, maximum changed area and unchanged area detect the different Lakes and Reservoirs in the period of 2008-2018. The unsupervised classification is used to compute the accuracy assessment analysis. Excellent results are obtained by using accuracy assessment for different Lakes and Reservoirs from 2008 to 2018, with the overall accuracy of 91.59%, and overall kappa statistics of 0.9032. The percentage of a decreased area is more in 2018 as compared to 2008 and it concludes that the percentage of decreased area is more as compared to the percentage of increased area for acquired Landsat-7 data.  

scholarly journals COMPARISON OF PIXEL-BASED AND OBJECT-ORIENTED LAND COVER CHANGE DETECTION METHODS

2016 ◽  
Vol XLI-B7 ◽  
pp. 579-583
Author(s):  
Zhenlei Xie ◽  
Ruoming Shi ◽  
Ling Zhu ◽  
Shu Peng ◽  
Xu Chen
Keyword(s):  
Land Cover ◽  
Change Detection ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Detection Method ◽  
Accuracy Assessment ◽  
Object Oriented ◽  
Detection Methods ◽  
Commission Error ◽  
Time Saving

Change detection method is an efficient way in the aim of land cover product updating on the basis of the existing products, and at the same time saving lots of cost and time. Considering the object-oriented change detection method for 30m resolution Landsat image, analysis of effect of different segmentation scales on the method of the object-oriented is firstly carried out. On the other hand, for analysing the effectiveness and availability of pixel-based change method, the two indices which complement each other are the differenced Normalized Difference Vegetation Index (dNDVI), the Change Vector (CV) were used. To demonstrate the performance of pixel-based and object-oriented, accuracy assessment of these two change detection results will be conducted by four indicators which include overall accuracy, omission error, commission error and Kappa coefficient.

scholarly journals Comparative Analysis of Change Detection Techniques In Landuse / Landcover Mapping of Oyo Town, Oyo State, Nigeria

2020 ◽  
pp. 44-62
Author(s):  
Olaniyi Saheed S. ◽  
Igbokwe J. I ◽  
Ojiako J. C.
Keyword(s):  
Principal Component Analysis ◽  
Comparative Analysis ◽  
Change Detection ◽  
Accuracy Assessment ◽  
Principal Component ◽  
Component Analysis ◽  
United States Geological Survey ◽  
Landsat Images ◽  
Detection Techniques ◽  
Analysis Of Change

Landcover is the natural surface of the earth undisturbed by human activities. It represents vegetation, natural or man-made features and every other visible evidence of land use. Landuse on the other hand refers to the use of land by humans while Change detection is the process of identifying differences in the state of an object or phenomenon by observing it in different times. This study is aimed at comparative analysis of change detection techniques in landuse/ landcover mapping of Oyo town with the objectives of comparing and evaluating the results of different change detection techniques as well as production of Landuse/ Landcover map of the study area for the period of 1990 and 2016. Landsat images of 1990, 2003 and 2016 covering the study area (Path 191, Row 54 & 55) were collected from the archives of United States Geological Survey (USGS) agency and image processing and analysis were done using ERDAS Imagine 2015 and ArcGIS 10.5. The results of the study were achieved through image pre-processing, image enhancement, image band combination, change detection through pre-classification (image differencing, image ratioing, Principal Component Analysis) and Post-Classification Comparison (PCC) methods, and results analysed. The result of accuracy assessment in this research shows that a PCA produces a better result of 91.67% while PCC delivered accuracy that ranges between 83.33% and 87.5%. However, PCC gives a better result on the change detection in the study area as it affords more analysis on the study area based on the thematic classes generated for each landuse and landcover of the study area. This study hereby recommends Post-Classification Comparison (PCC) and Principal Component Analysis (PCA) for change detection in the study area. Further research on change detection in the study area should be carried out using Object-Based Image Analysis (OBIA) using high resolution images because this research is hinge on pixel based classification of medium resolution images.

Building Damage Assessment Using Intensity SAR Data with Different Incidence Angles and Longtime Interval

2019 ◽  
Vol 14 (3) ◽  
pp. 456-465 ◽  
Author(s):  
Pinglan Ge ◽  
Hideomi Gokon ◽  
Kimiro Meguro ◽  
◽  
Keyword(s):  
Change Detection ◽  
Damage Assessment ◽  
Incidence Angle ◽  
Accuracy Assessment ◽  
Classification Performance ◽  
Temporal Changes ◽  
Building Damage ◽  
Acquisition Time ◽  
Event Data ◽  
Similar Accuracy

When carrying out change detection for building damage assessment using synthetic aperture radar (SAR) intensity images, it is desirable that the observation conditions of the images are similar and acquisition time is close to the earthquake occurrence time. In this way, the influence of the radar operating system and ground temporal changes can be minimized, facilitating high-accuracy assessment results. However, in practice, especially in poor developing areas, it is difficult to obtain ideal images owing to limited pre-event data archives. In the 2015 Gorkha, Nepal earthquake, the TerraSAR-X satellite captured the influenced Sankhu area before and after the earthquake on May 30, 2010 and May 13, 2015, respectively. The pre-event data was obtained in an ascending path with an incidence angle of 41°, whereas the post-event data was obtained in a descending path with an incidence angle of 33°. To apply the obtained data that had different observation conditions and longtime intervals for building damage assessment, two ways were considered and studied. On one hand, the feasibility of change detection considering these factors was investigated. Pixel statistic characteristics were analyzed in twelve test areas to check the influence of temporal changes, and building footprints were buffered considering two different incidence angles. On the other hand, the reliability of classification based on only post-event data was studied. The results showed good classification performance of some texture parameters, such as the “range value” and “standard deviation,” which are worthy of further study. Moreover, the classification results obtained using the post-event data achieved similar accuracy to that using both the pre- and post-event data, preliminarily indicating the research value of post-event data-based building damage detection as it can solve the pre-event data limitation problem once and for all.

scholarly journals Object-Based Building Change Detection by Fusing Pixel-Level Change Detection Results Generated from Morphological Building Index

2020 ◽  
Vol 12 (18) ◽  
pp. 2952
Author(s):  
Aisha Javed ◽  
Sejung Jung ◽  
Won Hee Lee ◽  
Youkyung Han
Keyword(s):  
Change Detection ◽  
Accuracy Assessment ◽  
Principal Component ◽  
False Alarms ◽  
Complex Objects ◽  
Number Of False Alarms ◽  
Object Based ◽  
Change Vector ◽  
New Buildings ◽  
Very High

Change detection (CD) is an important tool in remote sensing. CD can be categorized into pixel-based change detection (PBCD) and object-based change detection (OBCD). PBCD is traditionally used because of its simple and straightforward algorithms. However, with increasing interest in very-high-resolution (VHR) imagery and determining changes in small and complex objects such as buildings or roads, traditional methods showed limitations, for example, the large number of false alarms or noise in the results. Thus, researchers have focused on extending PBCD to OBCD. In this study, we proposed a method for detecting the newly built-up areas by extending PBCD results into an OBCD result through the Dempster–Shafer (D–S) theory. To this end, the morphological building index (MBI) was used to extract built-up areas in multitemporal VHR imagery. Then, three PBCD algorithms, change vector analysis, principal component analysis, and iteratively reweighted multivariate alteration detection, were applied to the MBI images. For the final CD result, the three binary change images were fused with the segmented image using the D–S theory. The results obtained from the proposed method were compared with those of PBCD, OBCD, and OBCD results generated by fusing the three binary change images using the major voting technique. Based on the accuracy assessment, the proposed method produced the highest F1-score and kappa values compared with other CD results. The proposed method can be used for detecting new buildings in built-up areas as well as changes related to demolished buildings with a low rate of false alarms and missed detections compared with other existing CD methods.

Sign in / Sign up

Export Citation Format

Share Document