Abstract
Satellite Image Time Series (SITS) have become more accessible in recent years and SITS analysis has attracted increasing research interest. Given that labeled SITS training samples are time and effort consuming to acquire, clustering or unsupervised analysis methods need to be developed. Similarity measure is critical for clustering, however, currently established methods represented by Dynamic Time Warping (DTW) still exhibit several issues when coping with SITS, such as pathological alignment, sensitivity to spike noise, and limitation on capacity. In this paper, we introduce a new time series similarity measure method named time adaptive optimal transport (TAOT) to the application of SITS clustering. TAOT inherits several promising properties of optimal transport for the comparing of time series. Statistical and visual results on two real SITS datasets with two different settings demonstrate that TAOT can effectively alleviate the issues of DTW and further improve the clustering accuracy. Thus, TAOT can serve as a usable tool to explore the potential of precious SITS data.
Highlights
Academic Editor: Dino IencoReceived: 13 August 2021Accepted: 29 September 2021Published: 6 October 2021Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.Licensee MDPI, Basel, Switzerland.Recent years have witnessed a rapid growth of satellite imagery data sources [1,2], thanks to the launch of various new satellite sensors such as the GaoFen series [3], ZiYuan series [4], Sentinel-2 [5], etc
To demonstrate the utility of TAOT for the clustering of satellite image time series (SITS), we evaluate the clustering accuracy of TAOT on two different datasets: the Reunion Island dataset and the Poyang Lake dataset
TAOT is compared with five well-established methods: Euclidean distance, Dynamic Time Warping (DTW), Sakoe–Chiba band constrained DTW (SC-DTW), piecewise DTW
Summary
Academic Editor: Dino IencoReceived: 13 August 2021Accepted: 29 September 2021Published: 6 October 2021Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.Licensee MDPI, Basel, Switzerland.Recent years have witnessed a rapid growth of satellite imagery data sources [1,2], thanks to the launch of various new satellite sensors such as the GaoFen series [3], ZiYuan series [4], Sentinel-2 [5], etc. Landsat imagery [7], have been accumulated over decades, making satellite image time series (SITS) data more accessible nowadays. Compared with a single-scene image, SITS records the evolution of land cover types over time and this kind of temporal information is sometimes critical to make land cover types more distinguishable [8,9,10]. Due to the above reasons, SITS analytics has attracted much attention in recent years and many applications have been developed to explore the rich information contained in SITS, for example, classification [15,16], clustering [1,17], class noise reduction [18], trend detection [19], disturbance detection [20], etc
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
