Next Article in Journal
Intercomparison of Resampling Algorithms for Advanced Technology Microwave Sounder (ATMS)
Previous Article in Journal
Water Multi-Parameter Sampling Design Method Based on Adaptive Sample Points Fusion in Weighted Space
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Seeded Classification of Satellite Image Time Series with Lower-Bounded Dynamic Time Warping

1
Aerospace Information Research Institute (AIR), Chinese Academy of Sciences (CAS), Beijing 100094, China
2
School of Marine Information Engineering, Hainan Tropical Ocean University, Sanya 572022, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2022, 14(12), 2778; https://doi.org/10.3390/rs14122778
Submission received: 29 March 2022 / Revised: 6 June 2022 / Accepted: 7 June 2022 / Published: 9 June 2022

Abstract

Satellite Image Time Series (SITS) record the continuous temporal behavior of land cover types and thus provide a new perspective for finer-grained land cover classification compared with the usual spectral and spatial information contained in a static image. In addition, SITS data is becoming more accessible in recent years due to newly launched satellites and accumulated historical data. However, the lack of labeled training samples limits the exploration of SITS data, especially with sophisticated methods. Even with a straightforward classifier, such as k-nearest neighbor, the accuracy and efficiency of the SITS similarity measure is also a pending problem. In this paper, we propose SKNN-LB-DTW, a seeded SITS classification method based on lower-bounded Dynamic Time Warping (DTW). The word “seeded” indicates that only a few labeled samples are required, and this is not only because of the lack of labeled samples but also because of our aim to explore the rich information contained in SITS, rather than letting training samples dominate the classification results. We use a combination of cascading lower bounds and early abandoning of DTW as an accurate yet efficient similarity measure for large scale tasks. The experimental results on two real SITS datasets demonstrate the utility of the proposed SKNN-LB-DTW, which could become an effective solution for SITS classification when the amount of unlabeled SITS data far exceeds the labeled data.
Keywords: satellite image time series; SITS; dynamic time warping; classification; lower bound satellite image time series; SITS; dynamic time warping; classification; lower bound
Graphical Abstract

Share and Cite

MDPI and ACS Style

Zhang, Z.; Tang, P.; Hu, C.; Liu, Z.; Zhang, W.; Tang, L. Seeded Classification of Satellite Image Time Series with Lower-Bounded Dynamic Time Warping. Remote Sens. 2022, 14, 2778. https://doi.org/10.3390/rs14122778

AMA Style

Zhang Z, Tang P, Hu C, Liu Z, Zhang W, Tang L. Seeded Classification of Satellite Image Time Series with Lower-Bounded Dynamic Time Warping. Remote Sensing. 2022; 14(12):2778. https://doi.org/10.3390/rs14122778

Chicago/Turabian Style

Zhang, Zheng, Ping Tang, Changmiao Hu, Zhiqiang Liu, Weixiong Zhang, and Liang Tang. 2022. "Seeded Classification of Satellite Image Time Series with Lower-Bounded Dynamic Time Warping" Remote Sensing 14, no. 12: 2778. https://doi.org/10.3390/rs14122778

APA Style

Zhang, Z., Tang, P., Hu, C., Liu, Z., Zhang, W., & Tang, L. (2022). Seeded Classification of Satellite Image Time Series with Lower-Bounded Dynamic Time Warping. Remote Sensing, 14(12), 2778. https://doi.org/10.3390/rs14122778

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop