Ship Detection in Sar Image Based on Information Geometry Method

Abstract

Aiming at the problem of high false alarm rate with respect to adaptive threshold in the ship detection from synthetic aperture radar (SAR) images, a novel strategy increasing robustness when using local adaptive threshold is proposed. In this article, we establish a fusion detection model based on a combination of the information geometry and surface geometry. Information geometry from a metric viewpoint can increase the contrast between targets and clutter in SAR image. Local surface feature gives a brief application of adaptive threshold method in ship detection from SAR images by means of the constant false-alarm-rate. Experiments indicate that the proposed geometry-based approach can effectively detect ship targets from complex background SAR images by using the method of fusion processing.

Performance Evaluation of Ship Target Detection Algorithms Based on Deep Learning

“…Considering the benefits of deep learning, deep learning has been applied to various fields including image recognition [5]. The Regions with CNN features(R-CNN) method, which is the first CNN-based target detection model, was proposed by Girshick et al in 2014 [6]. After that, more and more CNNbased algorithms are released in the following decade.…”

“…The regional-suggestion-based CNN algorithm usually has relatively high accuracy, but it has poor performance in real-time performance. In the contrast, the regression-based CNN algorithms have a relatively low accuracy but do well in real-time detection [6][7][8]. And due to the different performance, it may raise problems while selecting algorithms.…”

Synthesis of physically crosslinked PAM/CNT flakes nanocomposite hydrogel films via a destructive approach

“…Degradation of CNTs is an effective way to reduce the toxicity of CNTs. Various studies have shown that CNTs can be degraded by various biological agents such as macrophages, 20,21 enzymes 22,23 and bacteria. 24 Oxidation processes in biodegraders produce reactive oxygen species (ROS) such as hydrogen peroxide (H 2 O 2 ) and superoxide anion (O 2 c À ).…”