Contrast-weighted dictionary learning based saliency detection for VHR optical remote sensing images

Highlights：

• We use l1-norm and l2,1-norm to measure the sparsity and reconstruction errors of sparse coefficients, and then combine these two measures to improve the expression of “outliers” in the coefficients. In addition, we propose a saliency map fusion method based on global gradient optimization to optimize the fusion effect of multiple saliency maps.

• Experimental results on four datasets show that the proposed model is very competitive with the state-of-the-art methods under six evaluation metrics, especially on the VSRS dataset.

摘要

•Considering the features of the training sample patch itself, we propose a novel atomic learning formula based on contrast weights. In addition, an online discriminative dictionary learning algorithm based on contrast weight (CDL) is proposed to solve the formula.•We use l1-norm and l2,1-norm to measure the sparsity and reconstruction errors of sparse coefficients, and then combine these two measures to improve the expression of “outliers” in the coefficients. In addition, we propose a saliency map fusion method based on global gradient optimization to optimize the fusion effect of multiple saliency maps.•Experimental results on four datasets show that the proposed model is very competitive with the state-of-the-art methods under six evaluation metrics, especially on the VSRS dataset.

论文评审过程：Received 3 May 2020, Revised 25 October 2020, Accepted 13 November 2020, Available online 13 November 2020, Version of Record 19 February 2021.