Automatic change detection in high-resolution remote-sensing images by means of level set evolution and support vector machine classification

Cao, Guo; Li, Yupeng; Liu, Yazhou; Shang, Yanfeng

doi:10.1080/01431161.2014.951740

Cited by 45 publications

(25 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods identify a threshold to select training samples based on change vector analysis (CVA). Cao et al also used this method to select training samples for automatic CD in high-resolution remote sensing images [9]. However, the samples are often concentrated in one single area and the number of samples for different classes is the same, which does not meet the actual distribution of pixels in different classes of the scene.…”

mentioning

confidence: 98%

“…On the other hand, traditional supervised CD methods usually utilize one classifier to extract change information [9], [10], [18]. But a single classifier cannot detect all kinds of changes that may happen in the image effectively.…”

mentioning

confidence: 99%

“…In turn, supervised techniques generally require ground-truth information, which limits their application and reduces the degree of automation. Supervised CD methods include postclassification comparison [15], [16] and direct classification [9], [17], [18]. Postclassification comparison identifies class transitions by comparing multiple maps, which are widely applied to Landsat imagery and VHR imagery.…”

mentioning

confidence: 99%

“…The most commonly used methods for extracting information from VHR images is objectbased image analysis [2], [25], [26]. However, this approach heavily depends on the accuracy of the initial segmentation [9], [19], [27]. Another important method is the fusion of multiple features.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Automatic Change Detection in High-Resolution Remote Sensing Images by Using a Multiple Classifier System and Spectral–Spatial Features

Tan

Xiao

Plaza

et al. 2016

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Change detection (CD) is an active research topic in remote sensing applications including urban studies, disaster assessment, and deforestation monitoring. In this paper, we propose an automatic method for CD in high-resolution remote sensing images that uses a novel strategy for the selection of training samples and an ensemble of multiple classifiers. As for the selection of training samples, our proposed method uses two groups of thresholds instead of just one threshold to enhance the quality of the selected training samples by allowing for their selection in an intelligent manner. In order to achieve high CD accuracy, spatial information such as texture and morphological profiles are utilized in conjunction with spectral information. Our multiple classifier system (MCS) exploits the extreme learning machine (ELM), multinomial logistic regression (MLR), and K-nearest neighbor (KNN) classifiers. To validate our newly proposed approach, we conduct experiments using multispectral images collected by ZY-3. The proposed method provides state-of-the-art CD accuracies as compared with other approaches widely used in the literature for CD purposes.

show abstract

mentioning

confidence: 98%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Automatic Change Detection in High-Resolution Remote Sensing Images by Using a Multiple Classifier System and Spectral–Spatial Features

Tan

Xiao

Plaza

et al. 2016

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The results from analyses indicated that an object based approach provides a better means for change detection than a pixel based method because it provides an effective way to incorporate spatial information and expert knowledge into the change detection process only limitation is its applicability other than high resolution data. A method for change detection in high-resolution remote sensing images by means of Multi resolution level set (MLS) evolution and support vector machine (SVM) classification, which combined both the pixellevel method and the object-level method (Cao, 2014). Radiometric normalisation of image is prerequisite for any change detection (Mateos, 2010).…”

Section: Literature Reviewmentioning

confidence: 99%

New Change Detection Techniques to monitor land cover dynamics in mine environment

Pathak

2014

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Land use and land cover are dynamic and is an important component in understanding the interactions of the human activities with the environment and thus it is necessary to simulate environmental changes. Land use/cover (LU/LC) change detection is very essential for better understanding of landuse dynamic during a known period of time for sustainable management. Mining is one of the most dynamic processes with direct as well as indirect impact on the environment. Hence, mine area provides ideal situation for evaluating the chronological changes in land-use patterns. Digital change detection of satellite data at different time interval helps in analyzing the changes in the spatial extent of mine along with the associated activities. In present study, various algorithms Iteratively Re-weighted Multivariate Alteration Detection (MAD) on raw data where class wise comparison becomes a difficult proposition and object based segmentation and change detection as post classification comparison were assessed.

show abstract

Evaluating implementation of Coastal Zone Regulation notification in India using remote sensing change detection techniques, aided with machine learning algorithms.

Ramesh

Haridas

Mandal³

et al. 2021

Preprint

View full text Add to dashboard Cite

Automatic change detection in high-resolution remote-sensing images by means of level set evolution and support vector machine classification

Cited by 45 publications

References 27 publications

Automatic Change Detection in High-Resolution Remote Sensing Images by Using a Multiple Classifier System and Spectral–Spatial Features

Automatic Change Detection in High-Resolution Remote Sensing Images by Using a Multiple Classifier System and Spectral–Spatial Features

New Change Detection Techniques to monitor land cover dynamics in mine environment

Evaluating implementation of Coastal Zone Regulation notification in India using remote sensing change detection techniques, aided with machine learning algorithms.

Contact Info

Product

Resources

About