Informatics Systems, Federal University of Piaui, Picos 64607-825, Piaui, Brazil.
Teleinformatics Engineering, Federal University of Ceara, Fortaleza 60455-970, Ceara, Brazil.
Sensors (Basel). 2023 Jul 1;23(13):6080. doi: 10.3390/s23136080.
This article proposes a system for Content-Based Image Retrieval (CBIR) using stochastic distance for Synthetic-Aperture Radar (SAR) images. The methodology consists of three essential steps for image retrieval. First, it estimates the roughness (α^) and scale (γ^) parameters of the GI0 distribution that models SAR data in intensity. The parameters of the model were estimated using the Maximum Likelihood Estimation and the fast approach of the Log-Cumulants method. Second, using the triangular distance, CBIR-SAR evaluates the similarity between a query image and images in the database. The stochastic distance can identify the most similar regions according to the image features, which are the estimated parameters of the data model. Third, the performance of our proposal was evaluated by applying the Mean Average Precision (MAP) measure and considering clippings from three radar sensors, i.e., UAVSAR, OrbiSaR-2, and ALOS PALSAR. The CBIR-SAR results for synthetic images achieved the highest MAP value, retrieving extremely heterogeneous regions. Regarding the real SAR images, CBIR-SAR achieved MAP values above 0.833 for all polarization channels for image samples of forest (UAVSAR) and urban areas (ORBISAR). Our results confirmed that the proposed method is sensitive to the degree of texture, and hence, it relies on good estimates. They are inputs to the stochastic distance for effective image retrieval.
本文提出了一种基于随机距离的合成孔径雷达（SAR）图像内容检索（CBIR）系统。该方法学由图像检索的三个基本步骤组成。首先，它估计 GI0 分布的粗糙度（α^）和尺度（γ^）参数，该分布模型用于 SAR 数据的强度。模型参数使用最大似然估计和对数累积量方法的快速方法进行估计。其次，使用三角距离，CBIR-SAR 评估查询图像与数据库中图像之间的相似性。随机距离可以根据图像特征（即数据模型的估计参数）识别最相似的区域。第三，通过应用平均精度（MAP）度量并考虑来自三个雷达传感器（即 UAVSAR、OrbiSaR-2 和 ALOS PALSAR）的剪辑，评估我们的提案的性能。合成图像的 CBIR-SAR 结果获得了最高的 MAP 值，检索到了极其异构的区域。对于真实的 SAR 图像，对于森林（UAVSAR）和城市地区（ORBISAR）的图像样本，CBIR-SAR 在所有极化通道上的 MAP 值均高于 0.833。我们的结果证实，所提出的方法对纹理程度敏感，因此依赖于良好的估计。它们是随机距离进行有效图像检索的输入。
