A feed‐forward framework integrating saliency and geometry discrimination for shadow detection in SAR images

Abstract

Shadow has been increasingly a kind of significant aid information for object extraction and scene interpretation in synthetic aperture radar images, which makes SAR shadow detection an important issue. In this paper, we propose a feed‐forward framework integrating saliency and geometry discrimination for shadow detection in SAR images. We firstly develop a global contrast based shadow saliency model to extract suspected shadows. Considering that such suspected regions mostly contain some non‐shadow areas, a discrimination strategy based on geometric relationships between objects and shadows is designed to remove falsely detected areas. Then the remaining regions become the final shadow detection results. Several experiments are carried out on images from two real datasets, Moving and Stationary Target Acquisition Recognition and MiniSAR, to evaluate the performance of our method. From the perspectives of three commonly used metrics, the proposed algorithm comprehensively outperforms two other classic methods, presenting reliable shadow detection ability. Moreover, the detection results of the two classic methods are significantly enhanced in controlling false alarms after the discrimination module is introduced. The results demonstrate that our algorithm is practically applicable to shadow detection in SAR images, and the discrimination strategy can be flexibly extended for related tasks.

Integrating Target and Shadow Features for SAR Target Recognition

“…Anisotropic diffusion filtering can effectively suppress SAR image noise while preserving the structural information of the target and shadow regions. Motivated by [15,44,45], we propose a method for extracting the shadow mask based on the target centroid-labeled. This method first employs anisotropic diffusion filtering to denoise the SAR image, followed by a dual thresholding approach to roughly segment the target and shadow regions.…”

Shadow-Based False Target Identification for SAR Images

“…Although shadows result in the loss of scene information at the corresponding loca tion, they still have some characteristics that are helpful for SAR interpretation [26]. On one hand, all shadows in SAR images are in the same direction as their corresponding targets.…”

“…As a result, the threshold μ is finally set as 1 in this paper. According to the aforementioned characteristics [26], the first-stage identification condition is proposed as:…”

“…Shadow pixels are usually distributed in a certain circle, whose origin point is the centroid of the target, and the radius is the diameter of the target. Thereinto, the diameter of the target can be obtained by measuring the diagonal length of the smallest outer rectangle [26]. Thus, the second-stage identification condition is proposed as…”