This paper presents a new semi-supervised method for land cover classification using Sentinel-2 time-series images, which can deal with the problem of unclear observations. First, the MCCR method, which is constituted by the matrix completion (MC) of unclear observations and feature-adaptive collaborative representation (CR) based classifier, is adopted to handle the data quality problem. Second, by fusing RF, AdaBoost, and MCCR, a tri-training process is proposed to iteratively select the semi-labeled samples, considering the difference of classification certainty in different classifiers and classes. Experiments on two sets of Sentinel-2 images are conducted to validate the effectiveness of the proposed semi-supervised method.
|Title of host publication||2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||4|
|Publication status||Published - Jul 2019|
|Event||39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Yokohama, Japan|
Duration: 28 Jul 2019 → 2 Aug 2019
|Name||International Geoscience and Remote Sensing Symposium (IGARSS)|
|Conference||39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019|
|Period||28/07/19 → 2/08/19|
Bibliographical notePublisher Copyright:
© 2019 IEEE.
- land cover classification
- time series images