Automated classification of remote sensing images using multileveled MobileNetV2 and DWT techniques

作者：

Highlights：

• A new image dataset was collected to detect space objects.

• A DWT based deep feature generator is presented.

• A commonly preferred land-use dataset was used to obtain comparative results.

• An accurate model is proposed and achieved above 95% accuracies for both datasets.

• This model outperformed.

摘要

•A new image dataset was collected to detect space objects.•A DWT based deep feature generator is presented.•A commonly preferred land-use dataset was used to obtain comparative results.•An accurate model is proposed and achieved above 95% accuracies for both datasets.•This model outperformed.

论文关键词：MobilNetV2,Multilevel feature generation,INCA,Remote sensing image classification

论文评审过程：Received 13 February 2021, Revised 25 May 2021, Accepted 22 July 2021, Available online 28 July 2021, Version of Record 30 July 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115659