.png){kind=icon}
.png){kind=icon}
Return
Multiobjective sparse unmixing based hyperspectral change detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.asoc.2024.112160.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Hyperspectral unmixing can provide the composition of ground objects, while change detection can identify the changes of the same region over time. Therefore, unmixing based hyperspectral change detection can investigate changes in a subpixel-level. It can provide not only whether the change happens or not but also how to change. This paper will gradually establish an unconstrained sparse unmixing based change detection model and design a multiobjective optimization sparse unmixing approach (termed MoSU-CD) to solve it for more subpixel-level change details. Compared with the existing sparse unmixing based change detection approaches, MoSU-CD directly unmixes the difference map of multi-temporal images rather than multi-temporal images themselves respectively. Then it explores the change details of one substance in each pixel based on the unmixing results, i.e., endmembers and abundances. In addition, in order to improve the change detection accuracy, an ensemble decision strategy is designed for the Pareto optimal solutions obtained by multiobjective optimization method. Based on this strategy, the subpixel-level changes can be aggregated to generate an aggressive pixel-level change map. The experimental results on synthetic and real data sets demonstrate that the proposed MoSU-CD not only outperforms the benchmark and state-of-art approaches in terms of pixel-level change detection but also provides additional subpixel-level change information.
Keywords:
Unmixing based change detection
Multiobjective sparse unmixing
Subpixel-level
Ensemble decision strategy
Difference map