A scale-invariant change detection method for land use/cover change research

Jin, Xing; Sieber, Renée; Caelli, Terry

doi:10.1016/j.isprsjprs.2018.04.013

Cited by 32 publications

(17 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SVM is one of the most robust and accurate binary classification algorithms in all known data mining algorithms of supervision study. Based on the hyperplane classification theory, it possesses the ability to transform feature dimensions and directly classify the changing features [85,86]. The suitable kernel function of SVM is the core to measure the similarity between input data [87], so as to cope with the nonlinear data.…”

Section: Methods Of Feature Classificationmentioning

confidence: 99%

A Survey of Change Detection Methods Based on Remote Sensing Images for Multi-Source and Multi-Objective Scenarios

2020

View full text Add to dashboard Cite

Quantities of multi-temporal remote sensing (RS) images create favorable conditions for exploring the urban change in the long term. However, diverse multi-source features and change patterns bring challenges to the change detection in urban cases. In order to sort out the development venation of urban change detection, we make an observation of the literatures on change detection in the last five years, which focuses on the disparate multi-source RS images and multi-objective scenarios determined according to scene category. Based on the survey, a general change detection framework, including change information extraction, data fusion, and analysis of multi-objective scenarios modules, is summarized. Owing to the attributes of input RS images affect the technical selection of each module, data characteristics and application domains across different categories of RS images are discussed firstly. On this basis, not only the evolution process and relationship of the representative solutions are elaborated in the module description, through emphasizing the feasibility of fusing diverse data and the manifold application scenarios, we also advocate a complete change detection pipeline. At the end of the paper, we conclude the current development situation and put forward possible research direction of urban change detection, in the hope of providing insights to the following research.

show abstract

Section: Methods Of Feature Classificationmentioning

confidence: 99%

A Survey of Change Detection Methods Based on Remote Sensing Images for Multi-Source and Multi-Objective Scenarios

2020

View full text Add to dashboard Cite

show abstract

“…1) Structural Invariant Feature: Stable local features like SIFT, SURF, which can capture and present the local geometric structure of images, have been used for CD [24]- [26]. SIFT, SURF maintain invariance to rotation, scale, and are highly robust in matching problems [22], [23].…”

Section: A Multi-level Matching Featurementioning

confidence: 99%

“…Previous works have proved that extracted feature correspondences are positioned mostly sparsely on homogeneous zones [24], and also are affected by the noise and artefacts, such as weak texture, shadows [26]. Although the structural information in HR image is sufficiently detailed, the number and distribution of matched feature points are still insufficient to cover the entire image, limiting the application of feature point matching to CD.…”

Section: A Multi-level Matching Featurementioning

confidence: 99%

“…An approach based on the SIFT algorithm and a contrario has been proposed, which can deal with multi-resolutions, multi-sensors and multi-incidence angles situations [25]. Land-cover CD method with scale invariant by using spatial voting weighting method to fuse the detection results of maximally stable external region and SIFT algorithms has been proposed [26]. However, it should be noted that most extracted keypoints are positioned on fine structures, but very sparsely on homogeneous zones [24].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Change Detection Framework in Urban Area Using Multilevel Matching Feature and Automatic Sample Extraction Strategy

Zhou

Song

Cui

et al. 2021

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

View full text Add to dashboard Cite

Urban change detection (CD) using remote sensing images is of great significance for monitoring and analyzing the spatial and temporal distribution of changes within cities, which can be used to guide urban management. In order to reduce false detections and improve the CD automation, a novel CD framework for high resolution images is proposed in this paper. Firstly, a novel multi-level matching feature is presented, combining structural invariant features with multi-scale dense matching features to comprehensively describe the invariant properties of ground objects at different levels. Secondly, a newly automatic training sample extraction strategy is proposed, in which sufficient and accurate no-change samples can be obtained by Gaussian-weighted Dempster-Shafer evidence theory and L1norm, meanwhile, typical change samples can be extracted by sequential spectral change vector analysis. Utilizing the automatic extracted samples, the final CD results are obtained using four supervised classifiers respectively (k-nearest neighbor, support vector machine, rotation forest, and extra-trees). To validate the proposed CD framework, experiments are conducted in four datasets with spectral variability, spectral confusion between the changed objects and unchanged backgrounds, and misregistration. The results demonstrate that the proposed multi-level matching feature and automatic sample extraction strategy can obtain better results with different types of supervised classifiers, and can effectively improve automation of CD, which is applicable to the large spatial extent scene.

show abstract

“…Urban center form can refer to the land use scale and land use intensity, Land use is specifically expressed by FAR(Floor Area Ratio), which is the ratio of the total area to the average area. [51], by contrast, ratio of the city center's total area to POI density area can be used to replace the ratio of total area to average area. Although the density area of POI is not equivalent to FAR, since the change of POI in urban space does not affect the change of FAR directly, POI can express the full function of the city, so the regional POI density area is more important and immediate to the morphological expression of urban centers.…”

Section: Urban Center Formmentioning

confidence: 99%

Research on the relationship between Urban economic development level and urban spatial structure—A case study of two Chinese cities

Zhang

Yuan

2020

PLoS ONE

View full text Add to dashboard Cite

The characteristics of urban spatial structure and the objective evaluation of the development level of urban economy have always been the concern of urban researchers, However, the spatial relationship between urban spatial structure and urban economic development level is often deliberately ignored. Through the point of interest (POI), the identification framework is constructed, the spatial structure of the city is identified and evaluated, and the Geographically Weighted Regression analysis is carried out with the distribution of unit GDP (Gross Domestic Product) in this study. The research shows that Kunming and Guiyang are polycentric spatial structures and Kunming's structure is more significant. Kunming's economic level is generally higher than Guiyang, but the unit area cannot be compared. The city center will promote the development of the central area in this city, and the more urban centers are distributed within the geographical and spatial range, the greater contribution would have to economic development. In addition, the results of this study will have a positive impact on urban planning and construction, and will also provide a new perspective for the study of cities and related disciplines.

show abstract

A scale-invariant change detection method for land use/cover change research

Cited by 32 publications

References 54 publications

A Survey of Change Detection Methods Based on Remote Sensing Images for Multi-Source and Multi-Objective Scenarios

A Survey of Change Detection Methods Based on Remote Sensing Images for Multi-Source and Multi-Objective Scenarios

A Novel Change Detection Framework in Urban Area Using Multilevel Matching Feature and Automatic Sample Extraction Strategy

Research on the relationship between Urban economic development level and urban spatial structure—A case study of two Chinese cities

Contact Info

Product

Resources

About