Change detection in urban landscapes: a tensor factorization approach

다국어 초록 (Multilingual Abstract)

Analysis of urban landscape has been an interesting research challenge for decades. The advent of machine learning and data mining techniques have geared the problem from simple analysis of data to knowledge discovery from data. This work attempts to mine urban landscapes to find the change pattern which has happened over the region for a period of interest. The work proposes a spatiotemporal-metric miner, which uses the spatial, temporal and landscape metric data to discover the change that has occurred in a region. The model works on a hierarchical basis, wherein, the regions of interest are chosen in a landscape and are aggregated to find the change that has happened over the entire region. The entire model is built by taking advantage of the tensorized representation of data, and thus resulting in the effective mining of tensors. The growth of a landscape is evaluated regarding two parameters, namely, Inter-class Growth Index and Intra-class Growth Index. Experiments are performed on the landscape regions of Indian cities, and a ranking of cities is presented based on the growth indices, which are validated against standards. In the experiments, Jaipur city showed the highest Inter-class Growth Index value of 2.68 and Surat city had an Intra-class Growth Index of 0.78.

참고문헌 (Reference)

1 "https://www.rvo.nl/sites/default/files/Smart%20Cities%20India. pdf"

2 "https://smartnet.niua.org/content/ce67d809-eac2-4a2e-a487-f3cec9c097db"

3 "http://smartcities.gov.in/content/innerpage/no-of-smart-cities-ineach-state.php"

4 Albert, A., "Using convolutional networks and satellite imagery to identify patterns in urban environments at a large scale" ACM 1357-1366, 2017

5 Singh, V. S., "Urban forests and open green spaces : Lessons for Jaipur, Rajasthan India" Rajasthan State Pollution Control Board 2010

6 Wang, Y., "Travel time estimation of a path using sparse trajectories" ACM 25-34, 2014

7 Chu, E., "The political economy of urban climate adaptation and development planning in Surat, India" 34 (34): 281-298, 2016

8 Saha, S., "Tensor framework and combined symmetry for hypertext mining" 97 (97): 215-234, 2009

9 Kolda, T. G., "Tensor decompositions and applications" 51 (51): 455-500, 2009

10 Hwang, D. H., "Study of the temporal and spatial analysis by using SST satellite data" 11 (11): 149-160, 2016

11 Alatrista-Salas, H., "Spatio-sequential patterns mining : Beyond the boundaries" 20 (20): 293-316, 2016

12 Liu, X., "Simulating urban growth by integrating landscape expansion index(LEI)and cellular automata" 28 (28): 148-163, 2014

13 Park, S., "Prediction and comparison of urban growth by land suitability index mapping using GIS and RS in South Korea" 99 (99): 104-114, 2011

14 Alphan, H., "Post-classification comparison of land cover using multitemporal Landsat and ASTER imagery: The case of Kahramanmaras¸. Turkey" 151 (151): 327-336, 2009

15 Acker, J. G., "Online analysis enhances use of NASA earth science data. Eos" 88 (88): 14-17, 2007

16 De Lathauwer, L., "On the best rank-1 and rank-(r1, r2, …, rn)approximation of higherorder tensors" 21 (21): 1324-1342, 2000

17 Miller, O., "Objects based change detection in a pair of gray-level images" 38 (38): 1976-1992, 2005

18 Lefebvre, A., "Objectoriented approach and texture analysis for change detection in very high resolution images" IEEE 4 : 2008

19 "Ministry of Finance, Government of India"

20 Chen, B. H., "Mining spatiotemporal chaining patterns in non-identity event databases" 21 (21): S71-S102, 2017

21 Comber, A., "Methods to quantify regional differences in land cover change" 8 (8): 176-, 2016

22 Alhamad, M. N., "Mediterranean drylands : The effect of grain size and domain of scale on landscape metrics" 11 (11): 611-621, 2011

23 Hu, T., "Mapping urban land use by using landsat images and open social data" 8 (8): 151-, 2016

24 Olofsson, P., "Making better use of accuracy data in land change studies : Estimating accuracy and area and quantifying uncertainty using stratified estimation" 129 : 122-131, 2013

25 Uuemaa, E., "Landscape metrics and indices : An overview of their use in landscape research" 3 (3): 1-28, 2009

26 Lang, S., "Landscape Metrics-A toolbox for assessing past, present and future landscape structures" 207 : 207-, 2008

27 "Landsat 7 and landsat 8 data download mirror"

28 Bhagat, R. B., "India migration report 2017" Routledge India 98-116, 2018

29 Liao, J., "Improving POI recommendation via dynamic tensor completion" 2018

30 Singh, P., "Impact of land use change and urbanization on urban heat island in Lucknow city, Central India. A remote sensing based estimate" 32 : 100-114, 2017

31 Peng, Y., "Identification of the main factors determining landscape metrics in semi-arid agropastoral ecotone" 124 : 249-256, 2016

32 Gallardo, B., "How to choose a biodiversity indicator–redundancy and complementarity of biodiversity metrics in a freshwater ecosystem" 11 (11): 1177-1184, 2011

33 Descle´e, B., "Forest change detection by statistical object-based method" 102 (102): 1-11, 2006

34 McGarigal, K., "FRAGSTATS: Spatial pattern analysis program for categorical maps" Computer software program produced by the authors at the University of Massachusetts

35 Re´jichi, S., "Expert knowledgebased method for satellite image time series analysis and interpretation" 8 (8): 2138-2150, 2015

36 Gauvin, L., "Detecting the community structure and activity patterns of temporal networks : A non-negative tensor factorization approach" 9 (9): e86028-, 2014

37 Vakalopoulou, M., "Building detection in very high resolution multispectral data with deep learning features" IEEE 1873-1876, 2015

38 Benito-Calvo, A., "Assessing regional geodiversity : The Iberian Peninsula" 34 (34): 1433-1445, 2009

39 Zhao, X., "Application of image recognition in civil aviation security based on tensor learning" 33 (33): 2145-2157, 2017

40 Stanislav Lykov, "Anomalous Traffic Pattern Detection in Large Urban Areas: Tensor-Based Approach with Continuum Modeling of Traffic Flow" Springer Science and Business Media LLC 18 (18): 13-21, 2018

41 Liu, M., "Analysis of urban public greenspace pattern based on landscape metrics in Kunming" CRC Press 127-, 2016

42 Saritha, S., "Analysis of the smart growth of kochi city through landscape metrics" IEEE 1-5, 2017

43 Conchedda, G., "An objectbased method for mapping and change analysis in mangrove ecosystems" 63 (63): 578-589, 2008

44 Bontemps, S., "An object-based change detection method accounting for temporal dependences in time series with medium to coarse spatial resolution" 112 (112): 3181-3191, 2008

45 Tan, H., "A tensor-based method for missing traffic data completion" 28 : 15-27, 2013

46 Zhou, L., "A tensor framework for geosensor data forecasting of significant societal events" 88 : 27-37, 2019

47 Lerman, R. I., "A note on the calculation and interpretation of the Gini index" 15 (15): 363-368, 1984

48 Bro, R., "A new efficient method for determining the number of components in PARAFAC models" 17 (17): 274-286, 2003

49 Li, X., "A matching algorithm for detecting land use changes using casebased reasoning" 75 (75): 1319-1332, 2009

50 Tewkesbury, A. P., "A critical synthesis of remotely sensed optical image change detection techniques" 160 : 1-14, 2015

51 Fan, C., "A comparison of spatial autocorrelation indices and landscape metrics in measuring urban landscape fragmentation" 121 : 117-128, 2014

52 Chen, X., "A Bayesian tensor decomposition approach for spatiotemporal traffic data imputation" 98 : 73-84, 2019