Deep learning and mapping based ternary change detection for information unbalanced images

作者：

Highlights：

• The problem of ternary change detection for information unbalanced images is first raised.

• The analysis of images is based on the inner feature rather than the intensity of the pixel.

• The stacked denoising autoencoder and the stacked mapping network are used.

摘要

Highlights•The problem of ternary change detection for information unbalanced images is first raised.•The analysis of images is based on the inner feature rather than the intensity of the pixel.•The stacked denoising autoencoder and the stacked mapping network are used.

论文关键词：Change detection,Information unbalanced images,Deep neural networks,Feature representation,Feature mapping

论文评审过程：Received 22 June 2016, Revised 22 November 2016, Accepted 2 January 2017, Available online 4 January 2017, Version of Record 12 March 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.01.002