scholarly journals MULTI-TEMPORAL CLASSIFICATION AND CHANGE DETECTION USING UAV IMAGES

2018 ◽  
Vol XLII-2 ◽  
pp. 651-658 ◽  
Author(s):  
S. Makuti ◽  
F. Nex ◽  
M. Y. Yang
Keyword(s):  
Change Detection ◽  
Conditional Random Field ◽  
Building Construction ◽  
Detection Techniques ◽  
Multi Temporal ◽  
Uav Images ◽  
Uav Image ◽  
Data Collections ◽  
Fully Connected ◽  
Unary Potential

In this paper different methodologies for the classification and change detection of UAV image blocks are explored. UAV is not only the cheapest platform for image acquisition but it is also the easiest platform to operate in repeated data collections over a changing area like a building construction site. Two change detection techniques have been evaluated in this study: the pre-classification and the post-classification algorithms. These methods are based on three main steps: feature extraction, classification and change detection. A set of state of the art features have been used in the tests: colour features (HSV), textural features (GLCM) and 3D geometric features. For classification purposes Conditional Random Field (CRF) has been used: the unary potential was determined using the Random Forest algorithm while the pairwise potential was defined by the fully connected CRF. In the performed tests, different feature configurations and settings have been considered to assess the performance of these methods in such challenging task. Experimental results showed that the post-classification approach outperforms the pre-classification change detection method. This was analysed using the overall accuracy, where by post classification have an accuracy of up to 62.6 % and the pre classification change detection have an accuracy of 46.5 %. These results represent a first useful indication for future works and developments.

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 APPROACHES TO DISTINGUISH ‘REAL’ CHANGES FROM ‘UNREAL’ CHANGES BASED ON MULTI-TEMPORAL 2D BUILDING FOOTPRINT DATA

2018 ◽  
Vol XLII-4 ◽  
pp. 559-563 ◽  
Author(s):  
M. Schorcht ◽  
R. Hecht ◽  
G. Meinel
Keyword(s):  
Change Detection ◽  
Large Scale ◽  
Geospatial Data ◽  
Data Sets ◽  
Building Stock ◽  
Data Set ◽  
Detection Techniques ◽  
European Settlement ◽  
Multi Temporal ◽  
Building Footprint

<p><strong>Abstract.</strong> Building footprint data from National Mapping and Cadastral Agencies are available in Germany for 7 years as a uniform, nation-wide geospatial data set and are updated annually. These multi-temporal building data sets can form the basis for the application of change detection techniques to derive national figures on dynamics in the building stock. Since these building data sets have only been built up in recent years, it is necessary to distinguish real changes from false changes. This is done by applying vector geometry-based operations and statistical analyses, which are presented in this article. Furthermore, by the additional use of the raster dataset Copernicus &amp;ndash; European Settlement Map (classified, resolution 2.5<span class="thinspace"></span>m) it is approximately possible to estimate whether it is a correct change or not. The advantage of this approach is that large-scale comparable results can be derived simply and quickly based on uniform basic data.</p>

scholarly journals Impact of Texture Information on Crop Classification with Machine Learning and UAV Images

2019 ◽  
Vol 9 (4) ◽  
pp. 643 ◽  
Author(s):  
Geun-Ho Kwak ◽  
No-Wook Park
Keyword(s):  
Time Series ◽  
Texture Features ◽  
Classification Performance ◽  
Support Vector ◽  
Texture Information ◽  
Multi Temporal ◽  
Crop Classification ◽  
Uav Images ◽  
Uav Image ◽  
The Impact

Unmanned aerial vehicle (UAV) images that can provide thematic information at much higher spatial and temporal resolutions than satellite images have great potential in crop classification. Due to the ultra-high spatial resolution of UAV images, spatial contextual information such as texture is often used for crop classification. From a data availability viewpoint, it is not always possible to acquire time-series UAV images due to limited accessibility to the study area. Thus, it is necessary to improve classification performance for situations when a single or minimum number of UAV images are available for crop classification. In this study, we investigate the potential of gray-level co-occurrence matrix (GLCM)-based texture information for crop classification with time-series UAV images and machine learning classifiers including random forest and support vector machine. In particular, the impact of combining texture and spectral information on the classification performance is evaluated for cases that use only one UAV image or multi-temporal images as input. A case study of crop classification in Anbandegi of Korea was conducted for the above comparisons. The best classification accuracy was achieved when multi-temporal UAV images which can fully account for the growth cycles of crops were combined with GLCM-based texture features. However, the impact of the utilization of texture information was not significant. In contrast, when one August UAV image was used for crop classification, the utilization of texture information significantly affected the classification performance. Classification using texture features extracted from GLCM with larger kernel size significantly improved classification accuracy, an improvement of 7.72%p in overall accuracy for the support vector machine classifier, compared with classification based solely on spectral information. These results indicate the usefulness of texture information for classification of ultra-high-spatial-resolution UAV images, particularly when acquisition of time-series UAV images is difficult and only one UAV image is used for crop classification.

scholarly journals Affiliated Fusion Conditional Random Field for Urban UAV Image Semantic Segmentation

Sensors ◽  
2020 ◽  
Vol 20 (4) ◽  
pp. 993
Author(s):  
Yingying Kong ◽  
Bowen Zhang ◽  
Biyuan Yan ◽  
Yanjuan Liu ◽  
Henry Leung ◽  
...  
Keyword(s):  
Random Field ◽  
Conditional Random Field ◽  
Region Of Interest ◽  
Semantic Segmentation ◽  
Geographical Information ◽  
Aerial Image ◽  
Surface Model ◽  
Uav Images ◽  
Uav Image ◽  
Multiple Metrics

Unmanned aerial vehicles (UAV) have had significant progress in the last decade, which is applied to many relevant fields because of the progress of aerial image processing and the convenience to explore areas that men cannot reach. Still, as the basis of further applications such as object tracking and terrain classification, semantic image segmentation is one of the most difficult challenges in the field of computer vision. In this paper, we propose a method for urban UAV images semantic segmentation, which utilizes the geographical information of the region of interest in the form of a digital surface model (DSM). We introduce an Affiliated Fusion Conditional Random Field (AF-CRF), which combines the information of visual pictures and DSM, and a multi-scale strategy with attention to improve the segmenting results. The experiments show that the proposed structure performs better than state-of-the-art networks in multiple metrics.

Discovering Potential Illegal Construction Within Building Roofs from UAV Images Using Semantic Segmentation and Object-Based Change Detection

2021 ◽  
Vol 87 (4) ◽  
pp. 263-271
Author(s):  
Yang Liu ◽  
Yujie Sun ◽  
Shikang Tao ◽  
Min Wang ◽  
Qian Shen ◽  
...  
Keyword(s):  
Change Detection ◽  
Semantic Segmentation ◽  
Small Object ◽  
Detection Scheme ◽  
Building Roof ◽  
Object Based ◽  
Detection Stage ◽  
Aerial Vehicle ◽  
Uav Images ◽  
Uav Image

A novel potential illegal construction (PIC) detection method by bitemporal unmanned aerial vehicle (UAV ) image comparison (change detection) within building roof areas is proposed. In this method, roofs are first extracted from UAV images using a depth-channel improved UNet model. A two-step change detection scheme is then implemented for PIC detection. In the change detection stage, roofs with appearance, disappearance, and shape changes are first extracted by morphological analysis. Subroof primitives are then obtained by roof-constrained image segmentation within the remaining roof areas, and object-based iteratively reweighted multivariate alteration detection (IR-MAD ) is implemented to extract the small PICs from the subroof primitives. The proposed method organically combines deep learning and object-based image analysis, which can identify entire roof changes and locate small object changes within the roofs. Experiments show that the proposed method has better accuracy compared with the other counterparts, including the original IR-MAD, change vector analysis, and principal components analysis-K-means.

scholarly journals VEGETATION MONITORING OF MASHHAD USING AN OBJECT-ORIENTED POST CLASSIFICATION COMPARISON METHOD

2017 ◽  
Vol XLII-4/W4 ◽  
pp. 123-131
Author(s):  
N. Khalili Moghadam ◽  
M. R. Delavar ◽  
A. Forati
Keyword(s):  
Urban Development ◽  
Change Detection ◽  
Satellite Image ◽  
Object Oriented ◽  
Comparison Method ◽  
Vegetation Monitoring ◽  
Detection Techniques ◽  
Close Relationship ◽  
Multi Temporal ◽  
Landsat Satellite

By and large, todays mega cities are confronting considerable urban development in which many new buildings are being constructed in fringe areas of these cities. This remarkable urban development will probably end in vegetation reduction even though each mega city requires adequate areas of vegetation, which is considered to be crucial and helpful for these cities from a wide variety of perspectives such as air pollution reduction, soil erosion prevention, and eco system as well as environmental protection. One of the optimum methods for monitoring this vital component of each city is multi-temporal satellite images acquisition and using change detection techniques. In this research, the vegetation and urban changes of Mashhad, Iran, were monitored using an object-oriented (marker-based watershed algorithm) post classification comparison (PCC) method. A Bi-temporal multi-spectral Landsat satellite image was used from the study area to detect the changes of urban and vegetation areas and to find a relation between these changes. The results of this research demonstrate that during 1987-2017, Mashhad urban area has increased about 22525 hectares and the vegetation area has decreased approximately 4903 hectares. These statistics substantiate the close relationship between urban development and vegetation reduction. Moreover, the overall accuracies of 85.5% and 91.2% were achieved for the first and the second image classification, respectively. In addition, the overall accuracy and kappa coefficient of change detection were assessed 84.1% and 70.3%, respectively.

Sign in / Sign up

Export Citation Format

Share Document